{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984,
  "eval_steps": 500,
  "global_step": 312,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 2.3172,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 2.5335,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 2.1376,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.9307,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.8922,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 1.6593,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014,
      "loss": 1.8319,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016,
      "loss": 1.7492,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018,
      "loss": 1.6805,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.7235,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019999458931878073,
      "loss": 1.4492,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999783578606323,
      "loss": 1.6036,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019995130738201966,
      "loss": 1.6278,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999134408101731,
      "loss": 1.7926,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019986476224277165,
      "loss": 1.7498,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019980527694749952,
      "loss": 1.6711,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019973499136147606,
      "loss": 1.526,
      "step": 17
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001996539130905593,
      "loss": 1.5105,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001995620509085228,
      "loss": 1.6764,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019945941475610623,
      "loss": 1.5464,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001993460157399396,
      "loss": 1.6566,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001992218661313415,
      "loss": 1.7459,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019908697936499103,
      "loss": 1.52,
      "step": 23
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019894137003747403,
      "loss": 1.3941,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019878505390570362,
      "loss": 1.4971,
      "step": 25
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019861804788521493,
      "loss": 1.6746,
      "step": 26
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019844037004833473,
      "loss": 1.5774,
      "step": 27
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019825203962222572,
      "loss": 1.5899,
      "step": 28
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001980530769868059,
      "loss": 1.3888,
      "step": 29
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019784350367254322,
      "loss": 1.5598,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001976233423581255,
      "loss": 1.5839,
      "step": 31
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001973926168680066,
      "loss": 1.4904,
      "step": 32
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019715135216982798,
      "loss": 1.666,
      "step": 33
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001968995743717171,
      "loss": 1.6375,
      "step": 34
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019663731071946206,
      "loss": 1.5643,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019636458959356316,
      "loss": 1.548,
      "step": 36
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001960814405061619,
      "loss": 1.5101,
      "step": 37
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019578789409784727,
      "loss": 1.4541,
      "step": 38
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019548398213434007,
      "loss": 1.4757,
      "step": 39
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019516973750305532,
      "loss": 1.4002,
      "step": 40
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019484519420954354,
      "loss": 1.3392,
      "step": 41
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019451038737381077,
      "loss": 1.7327,
      "step": 42
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019416535322651818,
      "loss": 1.7479,
      "step": 43
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019381012910506146,
      "loss": 1.4793,
      "step": 44
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019344475344953012,
      "loss": 1.4659,
      "step": 45
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019306926579854821,
      "loss": 1.5368,
      "step": 46
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019268370678499533,
      "loss": 1.3053,
      "step": 47
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001922881181316097,
      "loss": 1.4054,
      "step": 48
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019188254264647337,
      "loss": 1.4907,
      "step": 49
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001914670242183795,
      "loss": 1.5888,
      "step": 50
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001910416078120832,
      "loss": 1.485,
      "step": 51
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001906063394634356,
      "loss": 1.5769,
      "step": 52
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019016126627440237,
      "loss": 1.5748,
      "step": 53
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018970643640796642,
      "loss": 1.4148,
      "step": 54
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000189241899082916,
      "loss": 1.4344,
      "step": 55
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018876770456851877,
      "loss": 1.3535,
      "step": 56
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001882839041790818,
      "loss": 1.5111,
      "step": 57
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018779055026839868,
      "loss": 1.3816,
      "step": 58
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018728769622408423,
      "loss": 1.6916,
      "step": 59
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018677539646179707,
      "loss": 1.4465,
      "step": 60
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018625370641935129,
      "loss": 1.4713,
      "step": 61
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018572268255071718,
      "loss": 1.3415,
      "step": 62
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018518238231991218,
      "loss": 1.5171,
      "step": 63
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018463286419478255,
      "loss": 1.5282,
      "step": 64
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018407418764067627,
      "loss": 1.4299,
      "step": 65
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018350641311400812,
      "loss": 1.6962,
      "step": 66
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001829296020557174,
      "loss": 1.4995,
      "step": 67
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018234381688461942,
      "loss": 1.2594,
      "step": 68
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001817491209906506,
      "loss": 1.5057,
      "step": 69
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018114557872800905,
      "loss": 2.7638,
      "step": 70
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018053325540819045,
      "loss": 1.6238,
      "step": 71
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001799122172929206,
      "loss": 1.4466,
      "step": 72
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017928253158698473,
      "loss": 1.9276,
      "step": 73
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001786442664309554,
      "loss": 4.1286,
      "step": 74
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001779974908938184,
      "loss": 6.6009,
      "step": 75
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001773422749654988,
      "loss": 3.5854,
      "step": 76
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017667868954928694,
      "loss": 2.2687,
      "step": 77
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017600680645416583,
      "loss": 1.8341,
      "step": 78
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017532669838704035,
      "loss": 1.4794,
      "step": 79
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017463843894486937,
      "loss": 1.9379,
      "step": 80
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001739421026067017,
      "loss": 1.8017,
      "step": 81
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017323776472561627,
      "loss": 1.5887,
      "step": 82
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017252550152056795,
      "loss": 1.7066,
      "step": 83
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001718053900681397,
      "loss": 1.3569,
      "step": 84
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017107750829420176,
      "loss": 1.5293,
      "step": 85
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017034193496547902,
      "loss": 1.6686,
      "step": 86
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016959874968102735,
      "loss": 1.6846,
      "step": 87
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016884803286362,
      "loss": 1.5077,
      "step": 88
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016808986575104465,
      "loss": 2.0585,
      "step": 89
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016732433038731242,
      "loss": 1.4112,
      "step": 90
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001665515096137797,
      "loss": 1.633,
      "step": 91
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016577148706018328,
      "loss": 6.6799,
      "step": 92
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016498434713559088,
      "loss": 2.0208,
      "step": 93
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016419017501926656,
      "loss": 1.755,
      "step": 94
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001633890566514535,
      "loss": 1.6762,
      "step": 95
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016258107872407375,
      "loss": 1.6067,
      "step": 96
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001617663286713474,
      "loss": 1.6935,
      "step": 97
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016094489466033043,
      "loss": 1.4747,
      "step": 98
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016011686558137448,
      "loss": 2.21,
      "step": 99
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001592823310385073,
      "loss": 1.6612,
      "step": 100
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001584413813397364,
      "loss": 1.5383,
      "step": 101
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015759410748727662,
      "loss": 1.5223,
      "step": 102
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015674060116770236,
      "loss": 1.5046,
      "step": 103
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015588095474202595,
      "loss": 1.8203,
      "step": 104
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015501526123570277,
      "loss": 1.6742,
      "step": 105
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015414361432856475,
      "loss": 1.406,
      "step": 106
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001532661083446829,
      "loss": 1.3389,
      "step": 107
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015238283824216015,
      "loss": 1.4524,
      "step": 108
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015149389960285558,
      "loss": 1.5875,
      "step": 109
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015059938862204127,
      "loss": 1.5332,
      "step": 110
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014969940209799248,
      "loss": 1.5215,
      "step": 111
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014879403742151283,
      "loss": 1.598,
      "step": 112
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014788339256539544,
      "loss": 1.3058,
      "step": 113
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001469675660738206,
      "loss": 1.5053,
      "step": 114
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014604665705169237,
      "loss": 1.415,
      "step": 115
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014512076515391375,
      "loss": 1.5635,
      "step": 116
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014418999057460276,
      "loss": 1.5195,
      "step": 117
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001432544340362501,
      "loss": 1.4387,
      "step": 118
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014231419677881966,
      "loss": 1.4878,
      "step": 119
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014136938054879283,
      "loss": 1.2613,
      "step": 120
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014042008758815818,
      "loss": 1.4854,
      "step": 121
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013946642062334766,
      "loss": 1.2463,
      "step": 122
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013850848285411994,
      "loss": 1.4409,
      "step": 123
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.000137546377942393,
      "loss": 1.2753,
      "step": 124
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013658021000102636,
      "loss": 1.5054,
      "step": 125
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013561008358255468,
      "loss": 1.3089,
      "step": 126
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013463610366787392,
      "loss": 1.5815,
      "step": 127
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013365837565488064,
      "loss": 1.4093,
      "step": 128
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001326770053470668,
      "loss": 1.3878,
      "step": 129
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001316920989420703,
      "loss": 1.3379,
      "step": 130
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013070376302018287,
      "loss": 1.2651,
      "step": 131
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012971210453281674,
      "loss": 1.3203,
      "step": 132
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.000128717230790931,
      "loss": 1.2712,
      "step": 133
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012771924945341906,
      "loss": 1.2382,
      "step": 134
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012671826851545851,
      "loss": 1.2974,
      "step": 135
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001257143962968246,
      "loss": 1.3225,
      "step": 136
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012470774143016853,
      "loss": 1.4874,
      "step": 137
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012369841284926188,
      "loss": 1.4654,
      "step": 138
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012268651977720866,
      "loss": 1.3508,
      "step": 139
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012167217171462566,
      "loss": 1.3048,
      "step": 140
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001206554784277931,
      "loss": 1.4731,
      "step": 141
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011963654993677645,
      "loss": 1.2144,
      "step": 142
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011861549650352069,
      "loss": 1.3876,
      "step": 143
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011759242861991855,
      "loss": 1.3118,
      "step": 144
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011656745699585371,
      "loss": 1.2132,
      "step": 145
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011554069254722051,
      "loss": 1.4687,
      "step": 146
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011451224638392129,
      "loss": 1.2314,
      "step": 147
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011348222979784289,
      "loss": 1.2831,
      "step": 148
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011245075425081328,
      "loss": 1.4453,
      "step": 149
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011141793136253986,
      "loss": 1.2795,
      "step": 150
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001103838728985307,
      "loss": 1.446,
      "step": 151
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.000109348690758,
      "loss": 1.1897,
      "step": 152
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010831249696175918,
      "loss": 1.193,
      "step": 153
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001072754036400944,
      "loss": 1.2859,
      "step": 154
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010623752302063283,
      "loss": 1.2807,
      "step": 155
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010519896741619803,
      "loss": 1.353,
      "step": 156
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010415984921265609,
      "loss": 1.3964,
      "step": 157
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010312028085675391,
      "loss": 1.4053,
      "step": 158
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010208037484395114,
      "loss": 1.5299,
      "step": 159
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010104024370624644,
      "loss": 1.369,
      "step": 160
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.3394,
      "step": 161
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.895975629375359e-05,
      "loss": 1.3759,
      "step": 162
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.791962515604887e-05,
      "loss": 1.4539,
      "step": 163
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.687971914324607e-05,
      "loss": 1.2923,
      "step": 164
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.584015078734395e-05,
      "loss": 1.2475,
      "step": 165
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.480103258380198e-05,
      "loss": 1.3727,
      "step": 166
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.376247697936719e-05,
      "loss": 1.397,
      "step": 167
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.272459635990562e-05,
      "loss": 1.5032,
      "step": 168
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.168750303824084e-05,
      "loss": 1.2606,
      "step": 169
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.065130924199998e-05,
      "loss": 1.3416,
      "step": 170
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.961612710146934e-05,
      "loss": 1.2814,
      "step": 171
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.858206863746018e-05,
      "loss": 1.2964,
      "step": 172
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.754924574918675e-05,
      "loss": 1.426,
      "step": 173
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.651777020215712e-05,
      "loss": 1.3554,
      "step": 174
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.548775361607872e-05,
      "loss": 1.3504,
      "step": 175
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.445930745277953e-05,
      "loss": 1.2102,
      "step": 176
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.343254300414628e-05,
      "loss": 1.3667,
      "step": 177
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.240757138008149e-05,
      "loss": 1.319,
      "step": 178
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.138450349647936e-05,
      "loss": 1.2481,
      "step": 179
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.036345006322359e-05,
      "loss": 1.3552,
      "step": 180
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.934452157220694e-05,
      "loss": 1.1693,
      "step": 181
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.832782828537437e-05,
      "loss": 1.1172,
      "step": 182
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.731348022279134e-05,
      "loss": 1.1956,
      "step": 183
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.630158715073813e-05,
      "loss": 1.1351,
      "step": 184
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.52922585698315e-05,
      "loss": 1.2686,
      "step": 185
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.428560370317542e-05,
      "loss": 1.3301,
      "step": 186
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.328173148454151e-05,
      "loss": 1.3624,
      "step": 187
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.228075054658096e-05,
      "loss": 1.24,
      "step": 188
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.1282769209069e-05,
      "loss": 1.3894,
      "step": 189
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.028789546718326e-05,
      "loss": 1.3425,
      "step": 190
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.929623697981718e-05,
      "loss": 1.2425,
      "step": 191
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.830790105792973e-05,
      "loss": 1.3314,
      "step": 192
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.732299465293322e-05,
      "loss": 1.3288,
      "step": 193
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.63416243451194e-05,
      "loss": 1.2598,
      "step": 194
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.536389633212609e-05,
      "loss": 1.41,
      "step": 195
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.43899164174453e-05,
      "loss": 1.0983,
      "step": 196
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.341978999897365e-05,
      "loss": 1.348,
      "step": 197
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.245362205760704e-05,
      "loss": 1.0783,
      "step": 198
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.149151714588009e-05,
      "loss": 1.4513,
      "step": 199
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.053357937665237e-05,
      "loss": 1.3207,
      "step": 200
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.957991241184184e-05,
      "loss": 1.3934,
      "step": 201
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.863061945120719e-05,
      "loss": 1.1897,
      "step": 202
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.768580322118034e-05,
      "loss": 1.2173,
      "step": 203
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6745565963749925e-05,
      "loss": 1.321,
      "step": 204
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.5810009425397294e-05,
      "loss": 1.3495,
      "step": 205
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.487923484608629e-05,
      "loss": 1.1517,
      "step": 206
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.395334294830765e-05,
      "loss": 1.3929,
      "step": 207
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.3032433926179395e-05,
      "loss": 1.5032,
      "step": 208
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.211660743460458e-05,
      "loss": 1.2021,
      "step": 209
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1205962578487155e-05,
      "loss": 1.5604,
      "step": 210
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.030059790200756e-05,
      "loss": 1.251,
      "step": 211
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.940061137795876e-05,
      "loss": 1.474,
      "step": 212
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.850610039714444e-05,
      "loss": 1.1798,
      "step": 213
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.761716175783989e-05,
      "loss": 1.2076,
      "step": 214
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.673389165531714e-05,
      "loss": 1.1569,
      "step": 215
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.585638567143529e-05,
      "loss": 1.0849,
      "step": 216
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.498473876429726e-05,
      "loss": 1.1121,
      "step": 217
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.411904525797408e-05,
      "loss": 1.4072,
      "step": 218
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.325939883229766e-05,
      "loss": 1.2595,
      "step": 219
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.240589251272342e-05,
      "loss": 1.2651,
      "step": 220
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.155861866026364e-05,
      "loss": 1.0955,
      "step": 221
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.071766896149273e-05,
      "loss": 1.2663,
      "step": 222
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.988313441862553e-05,
      "loss": 1.1684,
      "step": 223
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.9055105339669595e-05,
      "loss": 1.5317,
      "step": 224
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.823367132865265e-05,
      "loss": 1.3378,
      "step": 225
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.741892127592625e-05,
      "loss": 1.2381,
      "step": 226
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.6610943348546526e-05,
      "loss": 1.2223,
      "step": 227
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.580982498073344e-05,
      "loss": 1.4056,
      "step": 228
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.501565286440914e-05,
      "loss": 1.1969,
      "step": 229
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.422851293981676e-05,
      "loss": 1.1027,
      "step": 230
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.3448490386220355e-05,
      "loss": 1.0746,
      "step": 231
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2675669612687565e-05,
      "loss": 1.2298,
      "step": 232
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.191013424895536e-05,
      "loss": 1.2005,
      "step": 233
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.115196713638e-05,
      "loss": 1.0378,
      "step": 234
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.040125031897264e-05,
      "loss": 1.3243,
      "step": 235
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9658065034520978e-05,
      "loss": 1.2563,
      "step": 236
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.892249170579826e-05,
      "loss": 1.2879,
      "step": 237
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8194609931860316e-05,
      "loss": 1.1762,
      "step": 238
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7474498479432087e-05,
      "loss": 1.1478,
      "step": 239
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6762235274383772e-05,
      "loss": 1.2598,
      "step": 240
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6057897393298324e-05,
      "loss": 1.3739,
      "step": 241
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.536156105513062e-05,
      "loss": 1.2612,
      "step": 242
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4673301612959654e-05,
      "loss": 1.2202,
      "step": 243
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.399319354583418e-05,
      "loss": 1.1055,
      "step": 244
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3321310450713062e-05,
      "loss": 1.3746,
      "step": 245
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.265772503450122e-05,
      "loss": 1.3418,
      "step": 246
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2002509106181624e-05,
      "loss": 1.3636,
      "step": 247
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1355733569044635e-05,
      "loss": 1.3,
      "step": 248
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0717468413015283e-05,
      "loss": 1.2459,
      "step": 249
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.008778270707944e-05,
      "loss": 1.3297,
      "step": 250
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.946674459180955e-05,
      "loss": 1.1628,
      "step": 251
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8854421271990964e-05,
      "loss": 1.0611,
      "step": 252
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8250879009349398e-05,
      "loss": 1.2078,
      "step": 253
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7656183115380577e-05,
      "loss": 1.072,
      "step": 254
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.707039794428259e-05,
      "loss": 1.3753,
      "step": 255
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.649358688599191e-05,
      "loss": 1.2396,
      "step": 256
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5925812359323745e-05,
      "loss": 1.02,
      "step": 257
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5367135805217458e-05,
      "loss": 1.1991,
      "step": 258
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4817617680087825e-05,
      "loss": 1.4701,
      "step": 259
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4277317449282834e-05,
      "loss": 1.1954,
      "step": 260
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3746293580648717e-05,
      "loss": 1.2761,
      "step": 261
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3224603538202929e-05,
      "loss": 1.1929,
      "step": 262
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2712303775915802e-05,
      "loss": 1.2954,
      "step": 263
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.220944973160133e-05,
      "loss": 1.253,
      "step": 264
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1716095820918216e-05,
      "loss": 1.0924,
      "step": 265
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1232295431481222e-05,
      "loss": 1.1281,
      "step": 266
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0758100917083991e-05,
      "loss": 1.2917,
      "step": 267
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0293563592033595e-05,
      "loss": 1.2331,
      "step": 268
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.838733725597615e-06,
      "loss": 1.0373,
      "step": 269
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.393660536564408e-06,
      "loss": 1.2092,
      "step": 270
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.958392187916841e-06,
      "loss": 1.3602,
      "step": 271
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.532975781620512e-06,
      "loss": 1.0881,
      "step": 272
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.117457353526625e-06,
      "loss": 1.2997,
      "step": 273
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.711881868390291e-06,
      "loss": 1.1992,
      "step": 274
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.3162932150046885e-06,
      "loss": 1.198,
      "step": 275
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.930734201451816e-06,
      "loss": 1.2064,
      "step": 276
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.555246550469907e-06,
      "loss": 1.3395,
      "step": 277
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.189870894938587e-06,
      "loss": 1.1888,
      "step": 278
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.834646773481811e-06,
      "loss": 1.2374,
      "step": 279
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.489612626189245e-06,
      "loss": 1.149,
      "step": 280
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.154805790456485e-06,
      "loss": 1.3549,
      "step": 281
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.830262496944693e-06,
      "loss": 1.3259,
      "step": 282
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.516017865659949e-06,
      "loss": 1.2184,
      "step": 283
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.21210590215273e-06,
      "loss": 1.2918,
      "step": 284
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.918559493838114e-06,
      "loss": 1.2417,
      "step": 285
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.6354104064368566e-06,
      "loss": 1.4384,
      "step": 286
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.3626892805379562e-06,
      "loss": 1.3165,
      "step": 287
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.100425628282899e-06,
      "loss": 1.2784,
      "step": 288
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.848647830172024e-06,
      "loss": 1.5392,
      "step": 289
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.607383131993424e-06,
      "loss": 1.0516,
      "step": 290
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3766576418745022e-06,
      "loss": 1.3022,
      "step": 291
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.1564963274568027e-06,
      "loss": 1.2401,
      "step": 292
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9469230131940907e-06,
      "loss": 1.1793,
      "step": 293
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7479603777742938e-06,
      "loss": 1.3182,
      "step": 294
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.559629951665298e-06,
      "loss": 1.1788,
      "step": 295
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3819521147851123e-06,
      "loss": 1.3857,
      "step": 296
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2149460942964098e-06,
      "loss": 1.1947,
      "step": 297
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.05862996252597e-06,
      "loss": 1.2379,
      "step": 298
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.130206350089765e-07,
      "loss": 1.0906,
      "step": 299
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.781338686584927e-07,
      "loss": 1.181,
      "step": 300
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.539842600603918e-07,
      "loss": 1.2511,
      "step": 301
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.405852438937764e-07,
      "loss": 1.3397,
      "step": 302
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.3794909147720773e-07,
      "loss": 1.1058,
      "step": 303
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.4608690944071263e-07,
      "loss": 1.258,
      "step": 304
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.6500863852395584e-07,
      "loss": 1.4846,
      "step": 305
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.947230525005006e-07,
      "loss": 1.2382,
      "step": 306
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3523775722834587e-07,
      "loss": 1.3235,
      "step": 307
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.655918982689581e-08,
      "loss": 1.2589,
      "step": 308
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.8692617980350406e-08,
      "loss": 1.2572,
      "step": 309
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.164213936770576e-08,
      "loss": 1.1785,
      "step": 310
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.410681219286673e-09,
      "loss": 1.1204,
      "step": 311
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.0616,
      "step": 312
    },
    {
      "epoch": 1.0,
      "step": 312,
      "total_flos": 3.181343428260659e+16,
      "train_loss": 1.4551883145020559,
      "train_runtime": 2400.5166,
      "train_samples_per_second": 2.083,
      "train_steps_per_second": 0.13
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 312,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 3.181343428260659e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}