{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.08,
  "eval_steps": 156,
  "global_step": 156,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 0.985,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.5277,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001991031390134529,
      "loss": 0.4701,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019820627802690584,
      "loss": 0.442,
      "step": 4
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019730941704035874,
      "loss": 0.4066,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019641255605381167,
      "loss": 0.4013,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001955156950672646,
      "loss": 0.8097,
      "step": 7
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001946188340807175,
      "loss": 0.7497,
      "step": 8
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019372197309417043,
      "loss": 0.778,
      "step": 9
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019282511210762333,
      "loss": 0.4502,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019192825112107625,
      "loss": 0.4625,
      "step": 11
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019103139013452916,
      "loss": 0.3483,
      "step": 12
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019013452914798206,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018923766816143498,
      "loss": 0.7257,
      "step": 14
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001883408071748879,
      "loss": 0.3482,
      "step": 15
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018744394618834081,
      "loss": 0.8089,
      "step": 16
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018654708520179374,
      "loss": 0.7736,
      "step": 17
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018565022421524664,
      "loss": 0.3852,
      "step": 18
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018475336322869957,
      "loss": 0.789,
      "step": 19
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018385650224215247,
      "loss": 0.4096,
      "step": 20
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018295964125560537,
      "loss": 0.3812,
      "step": 21
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001820627802690583,
      "loss": 0.3078,
      "step": 22
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001811659192825112,
      "loss": 0.7426,
      "step": 23
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00018026905829596416,
      "loss": 0.7666,
      "step": 24
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017937219730941706,
      "loss": 0.348,
      "step": 25
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00017847533632286996,
      "loss": 0.7435,
      "step": 26
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001775784753363229,
      "loss": 0.7323,
      "step": 27
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001766816143497758,
      "loss": 0.7574,
      "step": 28
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017578475336322872,
      "loss": 0.6897,
      "step": 29
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017488789237668162,
      "loss": 0.313,
      "step": 30
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017399103139013452,
      "loss": 0.7074,
      "step": 31
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017309417040358745,
      "loss": 0.3258,
      "step": 32
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017219730941704037,
      "loss": 0.3411,
      "step": 33
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017130044843049328,
      "loss": 0.3514,
      "step": 34
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001704035874439462,
      "loss": 0.6684,
      "step": 35
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001695067264573991,
      "loss": 0.7809,
      "step": 36
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016860986547085203,
      "loss": 0.6523,
      "step": 37
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016771300448430493,
      "loss": 0.6381,
      "step": 38
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016681614349775784,
      "loss": 0.6418,
      "step": 39
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016591928251121076,
      "loss": 0.6454,
      "step": 40
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001650224215246637,
      "loss": 0.7451,
      "step": 41
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016412556053811662,
      "loss": 0.6925,
      "step": 42
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016322869955156952,
      "loss": 0.6882,
      "step": 43
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00016233183856502242,
      "loss": 0.3262,
      "step": 44
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016143497757847535,
      "loss": 0.7332,
      "step": 45
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00016053811659192825,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015964125560538118,
      "loss": 0.7189,
      "step": 47
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015874439461883408,
      "loss": 0.3458,
      "step": 48
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015784753363228698,
      "loss": 0.7442,
      "step": 49
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015695067264573994,
      "loss": 0.6889,
      "step": 50
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015605381165919284,
      "loss": 0.3819,
      "step": 51
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015515695067264574,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015426008968609867,
      "loss": 0.7144,
      "step": 53
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015336322869955157,
      "loss": 0.7169,
      "step": 54
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001524663677130045,
      "loss": 0.693,
      "step": 55
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001515695067264574,
      "loss": 0.4938,
      "step": 56
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00015067264573991032,
      "loss": 0.6774,
      "step": 57
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00014977578475336325,
      "loss": 0.2556,
      "step": 58
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014887892376681615,
      "loss": 0.3245,
      "step": 59
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014798206278026908,
      "loss": 0.6402,
      "step": 60
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014708520179372198,
      "loss": 0.6811,
      "step": 61
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014618834080717488,
      "loss": 0.3295,
      "step": 62
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001452914798206278,
      "loss": 0.6683,
      "step": 63
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001443946188340807,
      "loss": 0.3938,
      "step": 64
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014349775784753364,
      "loss": 0.4175,
      "step": 65
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014260089686098654,
      "loss": 0.8119,
      "step": 66
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00014170403587443947,
      "loss": 0.7478,
      "step": 67
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001408071748878924,
      "loss": 0.3655,
      "step": 68
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001399103139013453,
      "loss": 0.3293,
      "step": 69
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013901345291479823,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013811659192825113,
      "loss": 0.717,
      "step": 71
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013721973094170403,
      "loss": 0.7016,
      "step": 72
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013632286995515696,
      "loss": 0.4182,
      "step": 73
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00013542600896860986,
      "loss": 0.734,
      "step": 74
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001345291479820628,
      "loss": 0.6473,
      "step": 75
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013363228699551572,
      "loss": 0.2985,
      "step": 76
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013273542600896862,
      "loss": 0.3273,
      "step": 77
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013183856502242154,
      "loss": 0.3234,
      "step": 78
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013094170403587445,
      "loss": 0.3275,
      "step": 79
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00013004484304932735,
      "loss": 0.6376,
      "step": 80
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00012914798206278027,
      "loss": 0.6603,
      "step": 81
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012825112107623318,
      "loss": 0.3333,
      "step": 82
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001273542600896861,
      "loss": 0.7338,
      "step": 83
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012645739910313903,
      "loss": 0.3298,
      "step": 84
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00012556053811659193,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012466367713004486,
      "loss": 0.3143,
      "step": 86
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012376681614349776,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001228699551569507,
      "loss": 0.3561,
      "step": 88
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012197309417040359,
      "loss": 0.3659,
      "step": 89
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001210762331838565,
      "loss": 0.291,
      "step": 90
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00012017937219730942,
      "loss": 0.3397,
      "step": 91
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011928251121076232,
      "loss": 0.6194,
      "step": 92
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011838565022421526,
      "loss": 0.694,
      "step": 93
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011748878923766818,
      "loss": 0.6797,
      "step": 94
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011659192825112109,
      "loss": 0.6291,
      "step": 95
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011569506726457399,
      "loss": 0.642,
      "step": 96
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011479820627802691,
      "loss": 0.3092,
      "step": 97
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011390134529147982,
      "loss": 0.5964,
      "step": 98
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011300448430493274,
      "loss": 0.3344,
      "step": 99
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011210762331838565,
      "loss": 0.3551,
      "step": 100
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011121076233183858,
      "loss": 0.5977,
      "step": 101
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001103139013452915,
      "loss": 0.3573,
      "step": 102
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010941704035874441,
      "loss": 0.3115,
      "step": 103
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010852017937219732,
      "loss": 0.5852,
      "step": 104
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010762331838565022,
      "loss": 0.7607,
      "step": 105
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010672645739910314,
      "loss": 0.6468,
      "step": 106
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010582959641255605,
      "loss": 0.3296,
      "step": 107
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010493273542600897,
      "loss": 0.6971,
      "step": 108
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010403587443946188,
      "loss": 0.3401,
      "step": 109
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010313901345291481,
      "loss": 0.3043,
      "step": 110
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010224215246636773,
      "loss": 0.347,
      "step": 111
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010134529147982064,
      "loss": 0.6435,
      "step": 112
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010044843049327355,
      "loss": 0.3714,
      "step": 113
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.955156950672646e-05,
      "loss": 0.2871,
      "step": 114
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.865470852017937e-05,
      "loss": 0.3377,
      "step": 115
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.77578475336323e-05,
      "loss": 0.3595,
      "step": 116
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.686098654708521e-05,
      "loss": 0.6403,
      "step": 117
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.596412556053813e-05,
      "loss": 0.6321,
      "step": 118
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.506726457399103e-05,
      "loss": 0.6597,
      "step": 119
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.417040358744396e-05,
      "loss": 0.5944,
      "step": 120
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.327354260089687e-05,
      "loss": 0.756,
      "step": 121
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.237668161434979e-05,
      "loss": 0.2937,
      "step": 122
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.147982062780269e-05,
      "loss": 0.6174,
      "step": 123
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.05829596412556e-05,
      "loss": 0.6237,
      "step": 124
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.968609865470853e-05,
      "loss": 0.5931,
      "step": 125
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.878923766816144e-05,
      "loss": 0.6447,
      "step": 126
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.789237668161436e-05,
      "loss": 0.6579,
      "step": 127
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.699551569506726e-05,
      "loss": 0.2917,
      "step": 128
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.609865470852019e-05,
      "loss": 0.6375,
      "step": 129
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.52017937219731e-05,
      "loss": 0.6613,
      "step": 130
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.430493273542602e-05,
      "loss": 0.5606,
      "step": 131
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.340807174887892e-05,
      "loss": 0.6292,
      "step": 132
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.251121076233185e-05,
      "loss": 0.3139,
      "step": 133
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.161434977578476e-05,
      "loss": 0.4004,
      "step": 134
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.071748878923767e-05,
      "loss": 0.3055,
      "step": 135
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.982062780269059e-05,
      "loss": 0.6018,
      "step": 136
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.892376681614349e-05,
      "loss": 0.0,
      "step": 137
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.802690582959642e-05,
      "loss": 0.6227,
      "step": 138
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.713004484304933e-05,
      "loss": 0.6831,
      "step": 139
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.623318385650225e-05,
      "loss": 0.6435,
      "step": 140
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.533632286995516e-05,
      "loss": 0.5704,
      "step": 141
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.443946188340808e-05,
      "loss": 0.628,
      "step": 142
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.354260089686099e-05,
      "loss": 0.3774,
      "step": 143
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.26457399103139e-05,
      "loss": 0.3386,
      "step": 144
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.174887892376682e-05,
      "loss": 0.6116,
      "step": 145
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.085201793721974e-05,
      "loss": 0.681,
      "step": 146
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.995515695067265e-05,
      "loss": 0.3278,
      "step": 147
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.905829596412556e-05,
      "loss": 0.5766,
      "step": 148
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.816143497757848e-05,
      "loss": 0.5407,
      "step": 149
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.72645739910314e-05,
      "loss": 0.5914,
      "step": 150
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.636771300448431e-05,
      "loss": 0.5651,
      "step": 151
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.547085201793722e-05,
      "loss": 0.6632,
      "step": 152
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.457399103139014e-05,
      "loss": 0.2726,
      "step": 153
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.367713004484305e-05,
      "loss": 0.2809,
      "step": 154
    },
    {
      "epoch": 2.07,
      "learning_rate": 6.278026905829597e-05,
      "loss": 0.282,
      "step": 155
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.188340807174888e-05,
      "loss": 0.5305,
      "step": 156
    },
    {
      "epoch": 2.08,
      "eval_loss": 0.6579097509384155,
      "eval_runtime": 780.4973,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.049,
      "step": 156
    }
  ],
  "logging_steps": 1,
  "max_steps": 225,
  "num_train_epochs": 3,
  "save_steps": 156,
  "total_flos": 1.7304111281995776e+17,
  "trial_name": null,
  "trial_params": null
}