{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9986648865153538,
  "eval_steps": 500,
  "global_step": 187,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 2.7864,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 3.1764,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-06,
      "loss": 2.5692,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0477,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.9304,
      "step": 5
    },
    {
      "epoch": 0.03,
      "learning_rate": 1e-05,
      "loss": 0.8711,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.999246866958693e-06,
      "loss": 0.6422,
      "step": 7
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.99698769471852e-06,
      "loss": 0.7042,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.993223163862385e-06,
      "loss": 0.7917,
      "step": 9
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.98795440846732e-06,
      "loss": 0.6634,
      "step": 10
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.981183015762831e-06,
      "loss": 0.7043,
      "step": 11
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.972911025652754e-06,
      "loss": 0.6872,
      "step": 12
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.963140930100713e-06,
      "loss": 0.7418,
      "step": 13
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.951875672379424e-06,
      "loss": 0.7245,
      "step": 14
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.939118646184007e-06,
      "loss": 0.7227,
      "step": 15
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.924873694609636e-06,
      "loss": 0.6843,
      "step": 16
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.909145108993794e-06,
      "loss": 0.65,
      "step": 17
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.891937627623486e-06,
      "loss": 0.7358,
      "step": 18
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.873256434307828e-06,
      "loss": 0.763,
      "step": 19
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.853107156816393e-06,
      "loss": 0.7882,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.831495865183832e-06,
      "loss": 0.6681,
      "step": 21
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.808429069881267e-06,
      "loss": 0.6109,
      "step": 22
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.783913719854977e-06,
      "loss": 0.7464,
      "step": 23
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.757957200433011e-06,
      "loss": 0.7748,
      "step": 24
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.730567331100333e-06,
      "loss": 0.6528,
      "step": 25
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.701752363143183e-06,
      "loss": 0.7256,
      "step": 26
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.67152097716334e-06,
      "loss": 0.6889,
      "step": 27
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.639882280463071e-06,
      "loss": 0.728,
      "step": 28
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.606845804301523e-06,
      "loss": 0.7518,
      "step": 29
    },
    {
      "epoch": 0.16,
      "learning_rate": 9.572421501023403e-06,
      "loss": 0.7482,
      "step": 30
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.536619741060799e-06,
      "loss": 0.6835,
      "step": 31
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.499451309809058e-06,
      "loss": 0.6588,
      "step": 32
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.460927404377647e-06,
      "loss": 0.8194,
      "step": 33
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.421059630216992e-06,
      "loss": 0.6716,
      "step": 34
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.37985999762229e-06,
      "loss": 0.7035,
      "step": 35
    },
    {
      "epoch": 0.19,
      "learning_rate": 9.337340918115385e-06,
      "loss": 0.7737,
      "step": 36
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.29351520070574e-06,
      "loss": 0.7908,
      "step": 37
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.24839604803169e-06,
      "loss": 0.7395,
      "step": 38
    },
    {
      "epoch": 0.21,
      "learning_rate": 9.201997052383107e-06,
      "loss": 0.6748,
      "step": 39
    },
    {
      "epoch": 0.21,
      "learning_rate": 9.154332191606671e-06,
      "loss": 0.6289,
      "step": 40
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.105415824895008e-06,
      "loss": 0.7595,
      "step": 41
    },
    {
      "epoch": 0.22,
      "learning_rate": 9.055262688460931e-06,
      "loss": 0.7401,
      "step": 42
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.003887891098108e-06,
      "loss": 0.6546,
      "step": 43
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.951306909629492e-06,
      "loss": 0.6714,
      "step": 44
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.89753558424488e-06,
      "loss": 0.666,
      "step": 45
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.842590113729001e-06,
      "loss": 0.6523,
      "step": 46
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.786487050581583e-06,
      "loss": 0.6988,
      "step": 47
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.729243296030851e-06,
      "loss": 0.7612,
      "step": 48
    },
    {
      "epoch": 0.26,
      "learning_rate": 8.670876094941991e-06,
      "loss": 0.7252,
      "step": 49
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.611403030622074e-06,
      "loss": 0.6683,
      "step": 50
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.55084201952302e-06,
      "loss": 0.6546,
      "step": 51
    },
    {
      "epoch": 0.28,
      "learning_rate": 8.489211305844216e-06,
      "loss": 0.6822,
      "step": 52
    },
    {
      "epoch": 0.28,
      "learning_rate": 8.4265294560364e-06,
      "loss": 0.7031,
      "step": 53
    },
    {
      "epoch": 0.29,
      "learning_rate": 8.362815353208441e-06,
      "loss": 0.706,
      "step": 54
    },
    {
      "epoch": 0.29,
      "learning_rate": 8.298088191438753e-06,
      "loss": 0.7278,
      "step": 55
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.23236746999302e-06,
      "loss": 0.6482,
      "step": 56
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.165672987449962e-06,
      "loss": 0.6553,
      "step": 57
    },
    {
      "epoch": 0.31,
      "learning_rate": 8.098024835736977e-06,
      "loss": 0.7261,
      "step": 58
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.029443394077356e-06,
      "loss": 0.5941,
      "step": 59
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.959949322850994e-06,
      "loss": 0.7581,
      "step": 60
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.889563557370378e-06,
      "loss": 0.6762,
      "step": 61
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.818307301573757e-06,
      "loss": 0.718,
      "step": 62
    },
    {
      "epoch": 0.34,
      "learning_rate": 7.746202021637385e-06,
      "loss": 0.6745,
      "step": 63
    },
    {
      "epoch": 0.34,
      "learning_rate": 7.67326943950877e-06,
      "loss": 0.6839,
      "step": 64
    },
    {
      "epoch": 0.35,
      "learning_rate": 7.599531526362873e-06,
      "loss": 0.7154,
      "step": 65
    },
    {
      "epoch": 0.35,
      "learning_rate": 7.525010495983202e-06,
      "loss": 0.7622,
      "step": 66
    },
    {
      "epoch": 0.36,
      "learning_rate": 7.449728798069864e-06,
      "loss": 0.6516,
      "step": 67
    },
    {
      "epoch": 0.36,
      "learning_rate": 7.373709111476498e-06,
      "loss": 0.635,
      "step": 68
    },
    {
      "epoch": 0.37,
      "learning_rate": 7.296974337378209e-06,
      "loss": 0.6369,
      "step": 69
    },
    {
      "epoch": 0.37,
      "learning_rate": 7.219547592372512e-06,
      "loss": 0.6783,
      "step": 70
    },
    {
      "epoch": 0.38,
      "learning_rate": 7.141452201515386e-06,
      "loss": 0.7469,
      "step": 71
    },
    {
      "epoch": 0.38,
      "learning_rate": 7.062711691294525e-06,
      "loss": 0.6119,
      "step": 72
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.983349782541901e-06,
      "loss": 0.6803,
      "step": 73
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.903390383287795e-06,
      "loss": 0.6944,
      "step": 74
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.822857581558423e-06,
      "loss": 0.662,
      "step": 75
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.741775638119345e-06,
      "loss": 0.7491,
      "step": 76
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.66016897916682e-06,
      "loss": 0.7162,
      "step": 77
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.57806218896935e-06,
      "loss": 0.7451,
      "step": 78
    },
    {
      "epoch": 0.42,
      "learning_rate": 6.495480002461577e-06,
      "loss": 0.5831,
      "step": 79
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.412447297792818e-06,
      "loss": 0.7656,
      "step": 80
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.328989088832431e-06,
      "loss": 0.6309,
      "step": 81
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.245130517634307e-06,
      "loss": 0.719,
      "step": 82
    },
    {
      "epoch": 0.44,
      "learning_rate": 6.160896846862754e-06,
      "loss": 0.6109,
      "step": 83
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.076313452182033e-06,
      "loss": 0.6539,
      "step": 84
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.991405814611855e-06,
      "loss": 0.6642,
      "step": 85
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.9061995128511455e-06,
      "loss": 0.6832,
      "step": 86
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.820720215572375e-06,
      "loss": 0.7376,
      "step": 87
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.734993673688801e-06,
      "loss": 0.6968,
      "step": 88
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.6490457125969035e-06,
      "loss": 0.743,
      "step": 89
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.562902224396416e-06,
      "loss": 0.6412,
      "step": 90
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.476589160090238e-06,
      "loss": 0.6313,
      "step": 91
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.390132521766626e-06,
      "loss": 0.7327,
      "step": 92
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.30355835476596e-06,
      "loss": 0.5725,
      "step": 93
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.216892739834519e-06,
      "loss": 0.6587,
      "step": 94
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.13016178526756e-06,
      "loss": 0.5893,
      "step": 95
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.043391619044122e-06,
      "loss": 0.6343,
      "step": 96
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.956608380955877e-06,
      "loss": 0.6764,
      "step": 97
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.869838214732441e-06,
      "loss": 0.6486,
      "step": 98
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.783107260165483e-06,
      "loss": 0.5761,
      "step": 99
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.696441645234042e-06,
      "loss": 0.6928,
      "step": 100
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.609867478233377e-06,
      "loss": 0.635,
      "step": 101
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.523410839909764e-06,
      "loss": 0.6497,
      "step": 102
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.437097775603587e-06,
      "loss": 0.6256,
      "step": 103
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.350954287403099e-06,
      "loss": 0.6605,
      "step": 104
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.265006326311199e-06,
      "loss": 0.6458,
      "step": 105
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.179279784427625e-06,
      "loss": 0.6496,
      "step": 106
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.093800487148857e-06,
      "loss": 0.6505,
      "step": 107
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.008594185388146e-06,
      "loss": 0.6259,
      "step": 108
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.9236865478179685e-06,
      "loss": 0.6401,
      "step": 109
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.839103153137247e-06,
      "loss": 0.5964,
      "step": 110
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.7548694823656945e-06,
      "loss": 0.6578,
      "step": 111
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.671010911167572e-06,
      "loss": 0.6361,
      "step": 112
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.5875527022071808e-06,
      "loss": 0.6685,
      "step": 113
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.5045199975384225e-06,
      "loss": 0.5762,
      "step": 114
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.4219378110306523e-06,
      "loss": 0.5239,
      "step": 115
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.3398310208331806e-06,
      "loss": 0.6064,
      "step": 116
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.2582243618806574e-06,
      "loss": 0.6162,
      "step": 117
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.177142418441578e-06,
      "loss": 0.5415,
      "step": 118
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.096609616712207e-06,
      "loss": 0.5404,
      "step": 119
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.0166502174581012e-06,
      "loss": 0.6535,
      "step": 120
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.937288308705475e-06,
      "loss": 0.6472,
      "step": 121
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.858547798484613e-06,
      "loss": 0.5469,
      "step": 122
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.7804524076274898e-06,
      "loss": 0.699,
      "step": 123
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.7030256626217932e-06,
      "loss": 0.6188,
      "step": 124
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.6262908885235046e-06,
      "loss": 0.6024,
      "step": 125
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.550271201930136e-06,
      "loss": 0.5934,
      "step": 126
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.474989504016798e-06,
      "loss": 0.6309,
      "step": 127
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.4004684736371276e-06,
      "loss": 0.6157,
      "step": 128
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.32673056049123e-06,
      "loss": 0.6419,
      "step": 129
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.253797978362617e-06,
      "loss": 0.5713,
      "step": 130
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.1816926984262454e-06,
      "loss": 0.6575,
      "step": 131
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.1104364426296237e-06,
      "loss": 0.6824,
      "step": 132
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.040050677149008e-06,
      "loss": 0.6374,
      "step": 133
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.970556605922645e-06,
      "loss": 0.5793,
      "step": 134
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.9019751642630252e-06,
      "loss": 0.5671,
      "step": 135
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.8343270125500379e-06,
      "loss": 0.6081,
      "step": 136
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.7676325300069824e-06,
      "loss": 0.5478,
      "step": 137
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.7019118085612474e-06,
      "loss": 0.6179,
      "step": 138
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.6371846467915603e-06,
      "loss": 0.6195,
      "step": 139
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.5734705439636017e-06,
      "loss": 0.6112,
      "step": 140
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.5107886941557853e-06,
      "loss": 0.5949,
      "step": 141
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.4491579804769817e-06,
      "loss": 0.6089,
      "step": 142
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.3885969693779277e-06,
      "loss": 0.6091,
      "step": 143
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.3291239050580085e-06,
      "loss": 0.6016,
      "step": 144
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.2707567039691505e-06,
      "loss": 0.6553,
      "step": 145
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.213512949418419e-06,
      "loss": 0.633,
      "step": 146
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.1574098862709993e-06,
      "loss": 0.6151,
      "step": 147
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.1024644157551206e-06,
      "loss": 0.6017,
      "step": 148
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.0486930903705095e-06,
      "loss": 0.5714,
      "step": 149
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.961121089018933e-07,
      "loss": 0.6089,
      "step": 150
    },
    {
      "epoch": 0.81,
      "learning_rate": 9.447373115390702e-07,
      "loss": 0.5789,
      "step": 151
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.945841751049916e-07,
      "loss": 0.6077,
      "step": 152
    },
    {
      "epoch": 0.82,
      "learning_rate": 8.45667808393329e-07,
      "loss": 0.5956,
      "step": 153
    },
    {
      "epoch": 0.82,
      "learning_rate": 7.980029476168943e-07,
      "loss": 0.4987,
      "step": 154
    },
    {
      "epoch": 0.83,
      "learning_rate": 7.516039519683105e-07,
      "loss": 0.5695,
      "step": 155
    },
    {
      "epoch": 0.83,
      "learning_rate": 7.064847992942614e-07,
      "loss": 0.6005,
      "step": 156
    },
    {
      "epoch": 0.84,
      "learning_rate": 6.626590818846163e-07,
      "loss": 0.569,
      "step": 157
    },
    {
      "epoch": 0.84,
      "learning_rate": 6.201400023777105e-07,
      "loss": 0.5699,
      "step": 158
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.789403697830104e-07,
      "loss": 0.7248,
      "step": 159
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.390725956223531e-07,
      "loss": 0.7469,
      "step": 160
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.005486901909429e-07,
      "loss": 0.7068,
      "step": 161
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.6338025893920167e-07,
      "loss": 0.5459,
      "step": 162
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.275784989765985e-07,
      "loss": 0.6079,
      "step": 163
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.93154195698478e-07,
      "loss": 0.5906,
      "step": 164
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.6011771953693044e-07,
      "loss": 0.6135,
      "step": 165
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.284790228366602e-07,
      "loss": 0.4893,
      "step": 166
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.982476368568177e-07,
      "loss": 0.5953,
      "step": 167
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.6943266889966624e-07,
      "loss": 0.6246,
      "step": 168
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.4204279956698994e-07,
      "loss": 0.5807,
      "step": 169
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.1608628014502364e-07,
      "loss": 0.6546,
      "step": 170
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.915709301187335e-07,
      "loss": 0.5779,
      "step": 171
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.6850413481616868e-07,
      "loss": 0.6579,
      "step": 172
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.468928431836092e-07,
      "loss": 0.6288,
      "step": 173
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.2674356569217282e-07,
      "loss": 0.6266,
      "step": 174
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.080623723765134e-07,
      "loss": 0.6483,
      "step": 175
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.085489100620737e-08,
      "loss": 0.5573,
      "step": 176
    },
    {
      "epoch": 0.95,
      "learning_rate": 7.512630539036502e-08,
      "loss": 0.5503,
      "step": 177
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.088135381599414e-08,
      "loss": 0.6147,
      "step": 178
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.8124327620576726e-08,
      "loss": 0.6135,
      "step": 179
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.685906989928656e-08,
      "loss": 0.6094,
      "step": 180
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.7088974347246888e-08,
      "loss": 0.6843,
      "step": 181
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.8816984237169378e-08,
      "loss": 0.5167,
      "step": 182
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.2045591532681145e-08,
      "loss": 0.5398,
      "step": 183
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.7768361376152616e-09,
      "loss": 0.5482,
      "step": 184
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.0123052814812203e-09,
      "loss": 0.6061,
      "step": 185
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.53133041307974e-10,
      "loss": 0.5735,
      "step": 186
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.5353,
      "step": 187
    }
  ],
  "log_save_evaluate_time": 3923.0782437324524,
  "logging_steps": 1.0,
  "max_steps": 187,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "total_flos": 7.673772156280793e+19,
  "total_tokens": 900759552.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}