{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.986175115207373,
  "eval_steps": 500,
  "global_step": 162,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 2.258,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 2.154,
      "step": 2
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012,
      "loss": 2.0787,
      "step": 3
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00016,
      "loss": 2.1022,
      "step": 4
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.5467,
      "step": 5
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019872611464968155,
      "loss": 2.222,
      "step": 6
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019745222929936306,
      "loss": 2.1879,
      "step": 7
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001961783439490446,
      "loss": 1.8396,
      "step": 8
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019490445859872614,
      "loss": 1.8801,
      "step": 9
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019363057324840765,
      "loss": 1.9303,
      "step": 10
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019235668789808918,
      "loss": 1.7077,
      "step": 11
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019108280254777072,
      "loss": 1.8204,
      "step": 12
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018980891719745223,
      "loss": 1.7697,
      "step": 13
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018853503184713377,
      "loss": 1.7407,
      "step": 14
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001872611464968153,
      "loss": 1.7197,
      "step": 15
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018598726114649682,
      "loss": 1.6274,
      "step": 16
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00018471337579617836,
      "loss": 1.7828,
      "step": 17
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018343949044585987,
      "loss": 1.6724,
      "step": 18
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001821656050955414,
      "loss": 1.6608,
      "step": 19
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00018089171974522295,
      "loss": 1.7449,
      "step": 20
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017961783439490446,
      "loss": 1.724,
      "step": 21
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000178343949044586,
      "loss": 1.67,
      "step": 22
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017707006369426754,
      "loss": 1.5856,
      "step": 23
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017579617834394905,
      "loss": 1.7545,
      "step": 24
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017452229299363059,
      "loss": 1.7722,
      "step": 25
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017324840764331212,
      "loss": 1.5361,
      "step": 26
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00017197452229299363,
      "loss": 1.6462,
      "step": 27
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00017070063694267517,
      "loss": 1.5768,
      "step": 28
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001694267515923567,
      "loss": 1.7124,
      "step": 29
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016815286624203822,
      "loss": 1.5629,
      "step": 30
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016687898089171976,
      "loss": 1.6924,
      "step": 31
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001656050955414013,
      "loss": 1.5555,
      "step": 32
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001643312101910828,
      "loss": 1.6034,
      "step": 33
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00016305732484076435,
      "loss": 1.6526,
      "step": 34
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001617834394904459,
      "loss": 1.4711,
      "step": 35
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001605095541401274,
      "loss": 1.592,
      "step": 36
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015923566878980894,
      "loss": 1.5779,
      "step": 37
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015796178343949047,
      "loss": 1.7425,
      "step": 38
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015668789808917199,
      "loss": 1.5372,
      "step": 39
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015541401273885352,
      "loss": 1.6526,
      "step": 40
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00015414012738853506,
      "loss": 1.54,
      "step": 41
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00015286624203821657,
      "loss": 1.5983,
      "step": 42
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001515923566878981,
      "loss": 1.5737,
      "step": 43
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00015031847133757962,
      "loss": 1.5084,
      "step": 44
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014904458598726113,
      "loss": 1.4372,
      "step": 45
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014777070063694267,
      "loss": 1.6501,
      "step": 46
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001464968152866242,
      "loss": 1.4461,
      "step": 47
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014522292993630572,
      "loss": 1.5514,
      "step": 48
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00014394904458598726,
      "loss": 1.5865,
      "step": 49
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001426751592356688,
      "loss": 1.5795,
      "step": 50
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001414012738853503,
      "loss": 1.4996,
      "step": 51
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00014012738853503185,
      "loss": 1.6749,
      "step": 52
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013885350318471339,
      "loss": 1.4825,
      "step": 53
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001375796178343949,
      "loss": 1.5719,
      "step": 54
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013630573248407644,
      "loss": 1.4932,
      "step": 55
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013503184713375797,
      "loss": 1.4342,
      "step": 56
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013375796178343948,
      "loss": 1.4454,
      "step": 57
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00013248407643312102,
      "loss": 1.5273,
      "step": 58
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00013121019108280253,
      "loss": 1.384,
      "step": 59
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012993630573248407,
      "loss": 1.4851,
      "step": 60
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001286624203821656,
      "loss": 1.3932,
      "step": 61
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012738853503184712,
      "loss": 1.479,
      "step": 62
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012611464968152866,
      "loss": 1.4611,
      "step": 63
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001248407643312102,
      "loss": 1.4786,
      "step": 64
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001235668789808917,
      "loss": 1.2568,
      "step": 65
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00012229299363057325,
      "loss": 1.3784,
      "step": 66
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012101910828025477,
      "loss": 1.4212,
      "step": 67
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011974522292993631,
      "loss": 1.3157,
      "step": 68
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011847133757961784,
      "loss": 1.4883,
      "step": 69
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011719745222929936,
      "loss": 1.4889,
      "step": 70
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001159235668789809,
      "loss": 1.4213,
      "step": 71
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011464968152866242,
      "loss": 1.3831,
      "step": 72
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011337579617834395,
      "loss": 1.4133,
      "step": 73
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011210191082802549,
      "loss": 1.3613,
      "step": 74
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011082802547770701,
      "loss": 1.3554,
      "step": 75
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010955414012738854,
      "loss": 1.4899,
      "step": 76
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010828025477707007,
      "loss": 1.3935,
      "step": 77
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001070063694267516,
      "loss": 1.3503,
      "step": 78
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010573248407643312,
      "loss": 1.3964,
      "step": 79
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010445859872611465,
      "loss": 1.5109,
      "step": 80
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010318471337579619,
      "loss": 1.4097,
      "step": 81
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010191082802547771,
      "loss": 1.313,
      "step": 82
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00010063694267515924,
      "loss": 1.2494,
      "step": 83
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.936305732484077e-05,
      "loss": 1.4779,
      "step": 84
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.80891719745223e-05,
      "loss": 1.2957,
      "step": 85
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.681528662420382e-05,
      "loss": 1.3638,
      "step": 86
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.554140127388536e-05,
      "loss": 1.3777,
      "step": 87
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.426751592356689e-05,
      "loss": 1.4158,
      "step": 88
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.299363057324841e-05,
      "loss": 1.4125,
      "step": 89
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.171974522292994e-05,
      "loss": 1.6222,
      "step": 90
    },
    {
      "epoch": 1.68,
      "learning_rate": 9.044585987261147e-05,
      "loss": 1.335,
      "step": 91
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.9171974522293e-05,
      "loss": 1.3283,
      "step": 92
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.789808917197452e-05,
      "loss": 1.3687,
      "step": 93
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.662420382165606e-05,
      "loss": 1.345,
      "step": 94
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.535031847133759e-05,
      "loss": 1.4534,
      "step": 95
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.407643312101911e-05,
      "loss": 1.2561,
      "step": 96
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.280254777070065e-05,
      "loss": 1.3999,
      "step": 97
    },
    {
      "epoch": 1.81,
      "learning_rate": 8.152866242038217e-05,
      "loss": 1.4159,
      "step": 98
    },
    {
      "epoch": 1.82,
      "learning_rate": 8.02547770700637e-05,
      "loss": 1.3375,
      "step": 99
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.898089171974524e-05,
      "loss": 1.3709,
      "step": 100
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.770700636942676e-05,
      "loss": 1.2414,
      "step": 101
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.643312101910829e-05,
      "loss": 1.4125,
      "step": 102
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.515923566878981e-05,
      "loss": 1.4631,
      "step": 103
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.388535031847134e-05,
      "loss": 1.2543,
      "step": 104
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.261146496815286e-05,
      "loss": 1.3168,
      "step": 105
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.13375796178344e-05,
      "loss": 1.4753,
      "step": 106
    },
    {
      "epoch": 1.97,
      "learning_rate": 7.006369426751592e-05,
      "loss": 1.4155,
      "step": 107
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.878980891719745e-05,
      "loss": 1.3476,
      "step": 108
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.751592356687899e-05,
      "loss": 1.2634,
      "step": 109
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.624203821656051e-05,
      "loss": 1.236,
      "step": 110
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.496815286624204e-05,
      "loss": 1.1112,
      "step": 111
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.369426751592356e-05,
      "loss": 1.2689,
      "step": 112
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.24203821656051e-05,
      "loss": 1.2972,
      "step": 113
    },
    {
      "epoch": 2.1,
      "learning_rate": 6.114649681528662e-05,
      "loss": 1.2451,
      "step": 114
    },
    {
      "epoch": 2.12,
      "learning_rate": 5.9872611464968155e-05,
      "loss": 1.3026,
      "step": 115
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.859872611464968e-05,
      "loss": 1.1526,
      "step": 116
    },
    {
      "epoch": 2.16,
      "learning_rate": 5.732484076433121e-05,
      "loss": 1.1425,
      "step": 117
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.605095541401274e-05,
      "loss": 1.2705,
      "step": 118
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.477707006369427e-05,
      "loss": 1.1392,
      "step": 119
    },
    {
      "epoch": 2.21,
      "learning_rate": 5.35031847133758e-05,
      "loss": 1.1739,
      "step": 120
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.2229299363057324e-05,
      "loss": 1.2004,
      "step": 121
    },
    {
      "epoch": 2.25,
      "learning_rate": 5.0955414012738855e-05,
      "loss": 1.2028,
      "step": 122
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.968152866242039e-05,
      "loss": 1.1971,
      "step": 123
    },
    {
      "epoch": 2.29,
      "learning_rate": 4.840764331210191e-05,
      "loss": 1.1393,
      "step": 124
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.713375796178344e-05,
      "loss": 1.1752,
      "step": 125
    },
    {
      "epoch": 2.32,
      "learning_rate": 4.585987261146497e-05,
      "loss": 1.2266,
      "step": 126
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.45859872611465e-05,
      "loss": 1.2033,
      "step": 127
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.331210191082803e-05,
      "loss": 1.1491,
      "step": 128
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.2038216560509556e-05,
      "loss": 1.1002,
      "step": 129
    },
    {
      "epoch": 2.4,
      "learning_rate": 4.076433121019109e-05,
      "loss": 1.1551,
      "step": 130
    },
    {
      "epoch": 2.41,
      "learning_rate": 3.949044585987262e-05,
      "loss": 1.2215,
      "step": 131
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.821656050955414e-05,
      "loss": 1.1303,
      "step": 132
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.694267515923567e-05,
      "loss": 1.3085,
      "step": 133
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.56687898089172e-05,
      "loss": 1.2328,
      "step": 134
    },
    {
      "epoch": 2.49,
      "learning_rate": 3.4394904458598724e-05,
      "loss": 1.2315,
      "step": 135
    },
    {
      "epoch": 2.51,
      "learning_rate": 3.3121019108280256e-05,
      "loss": 1.2797,
      "step": 136
    },
    {
      "epoch": 2.53,
      "learning_rate": 3.184713375796178e-05,
      "loss": 1.2824,
      "step": 137
    },
    {
      "epoch": 2.54,
      "learning_rate": 3.057324840764331e-05,
      "loss": 1.3541,
      "step": 138
    },
    {
      "epoch": 2.56,
      "learning_rate": 2.929936305732484e-05,
      "loss": 1.2053,
      "step": 139
    },
    {
      "epoch": 2.58,
      "learning_rate": 2.802547770700637e-05,
      "loss": 1.0262,
      "step": 140
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.67515923566879e-05,
      "loss": 1.1497,
      "step": 141
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.5477707006369428e-05,
      "loss": 1.1258,
      "step": 142
    },
    {
      "epoch": 2.64,
      "learning_rate": 2.4203821656050956e-05,
      "loss": 1.2115,
      "step": 143
    },
    {
      "epoch": 2.65,
      "learning_rate": 2.2929936305732484e-05,
      "loss": 1.2129,
      "step": 144
    },
    {
      "epoch": 2.67,
      "learning_rate": 2.1656050955414015e-05,
      "loss": 1.1673,
      "step": 145
    },
    {
      "epoch": 2.69,
      "learning_rate": 2.0382165605095544e-05,
      "loss": 1.1702,
      "step": 146
    },
    {
      "epoch": 2.71,
      "learning_rate": 1.910828025477707e-05,
      "loss": 1.2379,
      "step": 147
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.78343949044586e-05,
      "loss": 1.2548,
      "step": 148
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.6560509554140128e-05,
      "loss": 1.1624,
      "step": 149
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.5286624203821656e-05,
      "loss": 1.0972,
      "step": 150
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.4012738853503186e-05,
      "loss": 1.1634,
      "step": 151
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.2738853503184714e-05,
      "loss": 1.1169,
      "step": 152
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.1464968152866242e-05,
      "loss": 0.9829,
      "step": 153
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.0191082802547772e-05,
      "loss": 1.1863,
      "step": 154
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.9171974522293e-06,
      "loss": 1.1772,
      "step": 155
    },
    {
      "epoch": 2.88,
      "learning_rate": 7.643312101910828e-06,
      "loss": 1.2474,
      "step": 156
    },
    {
      "epoch": 2.89,
      "learning_rate": 6.369426751592357e-06,
      "loss": 1.2136,
      "step": 157
    },
    {
      "epoch": 2.91,
      "learning_rate": 5.095541401273886e-06,
      "loss": 1.0309,
      "step": 158
    },
    {
      "epoch": 2.93,
      "learning_rate": 3.821656050955414e-06,
      "loss": 1.0609,
      "step": 159
    },
    {
      "epoch": 2.95,
      "learning_rate": 2.547770700636943e-06,
      "loss": 1.2989,
      "step": 160
    },
    {
      "epoch": 2.97,
      "learning_rate": 1.2738853503184715e-06,
      "loss": 1.1991,
      "step": 161
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0,
      "loss": 1.2027,
      "step": 162
    }
  ],
  "logging_steps": 1,
  "max_steps": 162,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.4301896344240128e+16,
  "trial_name": null,
  "trial_params": null
}