{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.496,
  "eval_steps": 156,
  "global_step": 624,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 1.031,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.1316,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019973262032085563,
      "loss": 1.0588,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019946524064171124,
      "loss": 2.037,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019919786096256686,
      "loss": 1.0911,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019893048128342245,
      "loss": 1.8383,
      "step": 6
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019866310160427807,
      "loss": 1.8296,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001983957219251337,
      "loss": 1.8112,
      "step": 8
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001981283422459893,
      "loss": 1.7675,
      "step": 9
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019786096256684492,
      "loss": 1.7701,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019759358288770054,
      "loss": 1.7535,
      "step": 11
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019732620320855616,
      "loss": 1.7679,
      "step": 12
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019705882352941177,
      "loss": 1.7772,
      "step": 13
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001967914438502674,
      "loss": 1.7286,
      "step": 14
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000196524064171123,
      "loss": 1.6585,
      "step": 15
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019625668449197863,
      "loss": 0.9072,
      "step": 16
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019598930481283424,
      "loss": 1.6208,
      "step": 17
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019572192513368986,
      "loss": 0.9375,
      "step": 18
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019545454545454548,
      "loss": 1.5977,
      "step": 19
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019518716577540107,
      "loss": 1.7837,
      "step": 20
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001949197860962567,
      "loss": 1.5817,
      "step": 21
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001946524064171123,
      "loss": 1.7005,
      "step": 22
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019438502673796792,
      "loss": 0.7865,
      "step": 23
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019411764705882354,
      "loss": 0.7424,
      "step": 24
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019385026737967916,
      "loss": 1.6181,
      "step": 25
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019358288770053477,
      "loss": 1.5176,
      "step": 26
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001933155080213904,
      "loss": 0.8716,
      "step": 27
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019304812834224598,
      "loss": 1.6366,
      "step": 28
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001927807486631016,
      "loss": 0.861,
      "step": 29
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019251336898395722,
      "loss": 1.655,
      "step": 30
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019224598930481283,
      "loss": 0.9451,
      "step": 31
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019197860962566845,
      "loss": 1.6875,
      "step": 32
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019171122994652407,
      "loss": 1.6885,
      "step": 33
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001914438502673797,
      "loss": 1.5641,
      "step": 34
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001911764705882353,
      "loss": 1.7106,
      "step": 35
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019090909090909092,
      "loss": 0.8359,
      "step": 36
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019064171122994654,
      "loss": 1.634,
      "step": 37
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019037433155080216,
      "loss": 1.7435,
      "step": 38
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019010695187165777,
      "loss": 1.5864,
      "step": 39
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001898395721925134,
      "loss": 1.5986,
      "step": 40
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000189572192513369,
      "loss": 0.8104,
      "step": 41
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001893048128342246,
      "loss": 1.5903,
      "step": 42
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018903743315508022,
      "loss": 0.706,
      "step": 43
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018877005347593583,
      "loss": 1.6629,
      "step": 44
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018850267379679145,
      "loss": 1.6884,
      "step": 45
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018823529411764707,
      "loss": 1.622,
      "step": 46
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001879679144385027,
      "loss": 1.6225,
      "step": 47
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001877005347593583,
      "loss": 0.8068,
      "step": 48
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001874331550802139,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001871657754010695,
      "loss": 0.7136,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018689839572192513,
      "loss": 1.487,
      "step": 51
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018663101604278075,
      "loss": 1.6591,
      "step": 52
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018636363636363636,
      "loss": 1.564,
      "step": 53
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000186096256684492,
      "loss": 1.6848,
      "step": 54
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001858288770053476,
      "loss": 1.6442,
      "step": 55
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018556149732620322,
      "loss": 1.634,
      "step": 56
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018529411764705883,
      "loss": 1.6559,
      "step": 57
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018502673796791445,
      "loss": 0.8619,
      "step": 58
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018475935828877007,
      "loss": 1.4555,
      "step": 59
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001844919786096257,
      "loss": 1.6295,
      "step": 60
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001842245989304813,
      "loss": 0.8006,
      "step": 61
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018395721925133692,
      "loss": 1.7844,
      "step": 62
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001836898395721925,
      "loss": 1.5599,
      "step": 63
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018342245989304813,
      "loss": 0.8152,
      "step": 64
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018315508021390375,
      "loss": 1.5898,
      "step": 65
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018288770053475936,
      "loss": 0.8534,
      "step": 66
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018262032085561498,
      "loss": 1.6466,
      "step": 67
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001823529411764706,
      "loss": 1.7625,
      "step": 68
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018208556149732622,
      "loss": 0.6436,
      "step": 69
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8358,
      "step": 70
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018155080213903742,
      "loss": 1.5384,
      "step": 71
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018128342245989304,
      "loss": 1.5965,
      "step": 72
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00018101604278074866,
      "loss": 1.6551,
      "step": 73
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018074866310160428,
      "loss": 1.6287,
      "step": 74
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018048128342245992,
      "loss": 1.6807,
      "step": 75
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00018021390374331554,
      "loss": 0.8354,
      "step": 76
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017994652406417113,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017967914438502675,
      "loss": 1.3238,
      "step": 78
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017941176470588236,
      "loss": 0.7033,
      "step": 79
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017914438502673798,
      "loss": 1.6853,
      "step": 80
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001788770053475936,
      "loss": 1.558,
      "step": 81
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017860962566844922,
      "loss": 1.7254,
      "step": 82
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017834224598930483,
      "loss": 0.8146,
      "step": 83
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017807486631016042,
      "loss": 1.6413,
      "step": 84
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017780748663101604,
      "loss": 1.5349,
      "step": 85
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00017754010695187166,
      "loss": 1.5976,
      "step": 86
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00017727272727272728,
      "loss": 0.8735,
      "step": 87
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001770053475935829,
      "loss": 1.6917,
      "step": 88
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001767379679144385,
      "loss": 1.4532,
      "step": 89
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017647058823529413,
      "loss": 1.2738,
      "step": 90
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00017620320855614975,
      "loss": 1.72,
      "step": 91
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017593582887700534,
      "loss": 1.6528,
      "step": 92
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00017566844919786095,
      "loss": 0.6675,
      "step": 93
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017540106951871657,
      "loss": 1.5316,
      "step": 94
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001751336898395722,
      "loss": 1.6082,
      "step": 95
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00017486631016042783,
      "loss": 0.8312,
      "step": 96
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017459893048128345,
      "loss": 1.7084,
      "step": 97
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00017433155080213904,
      "loss": 0.8941,
      "step": 98
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017406417112299466,
      "loss": 1.6595,
      "step": 99
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017379679144385028,
      "loss": 0.8231,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001735294117647059,
      "loss": 1.5094,
      "step": 101
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001732620320855615,
      "loss": 1.4382,
      "step": 102
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017299465240641713,
      "loss": 1.6014,
      "step": 103
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017272727272727275,
      "loss": 1.6579,
      "step": 104
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017245989304812836,
      "loss": 1.7174,
      "step": 105
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00017219251336898395,
      "loss": 1.4742,
      "step": 106
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00017192513368983957,
      "loss": 1.6524,
      "step": 107
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001716577540106952,
      "loss": 1.475,
      "step": 108
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001713903743315508,
      "loss": 1.6018,
      "step": 109
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017112299465240642,
      "loss": 1.592,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017085561497326204,
      "loss": 0.7578,
      "step": 111
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017058823529411766,
      "loss": 1.5841,
      "step": 112
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017032085561497325,
      "loss": 1.4413,
      "step": 113
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017005347593582887,
      "loss": 1.4614,
      "step": 114
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00016978609625668448,
      "loss": 1.5979,
      "step": 115
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001695187165775401,
      "loss": 0.9329,
      "step": 116
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00016925133689839575,
      "loss": 1.6472,
      "step": 117
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00016898395721925136,
      "loss": 0.8343,
      "step": 118
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016871657754010698,
      "loss": 1.8057,
      "step": 119
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016844919786096257,
      "loss": 1.6294,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001681818181818182,
      "loss": 0.7687,
      "step": 121
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001679144385026738,
      "loss": 0.852,
      "step": 122
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016764705882352942,
      "loss": 1.603,
      "step": 123
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016737967914438504,
      "loss": 0.8358,
      "step": 124
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016711229946524066,
      "loss": 1.6052,
      "step": 125
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00016684491978609628,
      "loss": 1.7125,
      "step": 126
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016657754010695187,
      "loss": 0.8034,
      "step": 127
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00016631016042780748,
      "loss": 1.538,
      "step": 128
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001660427807486631,
      "loss": 1.5907,
      "step": 129
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016577540106951872,
      "loss": 1.6852,
      "step": 130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00016550802139037434,
      "loss": 0.8292,
      "step": 131
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016524064171122995,
      "loss": 1.4263,
      "step": 132
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016497326203208557,
      "loss": 0.816,
      "step": 133
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001647058823529412,
      "loss": 0.8648,
      "step": 134
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00016443850267379678,
      "loss": 1.5239,
      "step": 135
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001641711229946524,
      "loss": 0.8859,
      "step": 136
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016390374331550801,
      "loss": 1.5103,
      "step": 137
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.6071,
      "step": 138
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016336898395721928,
      "loss": 0.6449,
      "step": 139
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001631016042780749,
      "loss": 1.7182,
      "step": 140
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016283422459893048,
      "loss": 0.6098,
      "step": 141
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001625668449197861,
      "loss": 1.4725,
      "step": 142
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00016229946524064172,
      "loss": 1.5916,
      "step": 143
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016203208556149734,
      "loss": 1.3847,
      "step": 144
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016176470588235295,
      "loss": 1.556,
      "step": 145
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00016149732620320857,
      "loss": 1.6262,
      "step": 146
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001612299465240642,
      "loss": 1.5316,
      "step": 147
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001609625668449198,
      "loss": 0.0,
      "step": 148
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001606951871657754,
      "loss": 0.7013,
      "step": 149
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016042780748663101,
      "loss": 1.734,
      "step": 150
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00016016042780748663,
      "loss": 0.9174,
      "step": 151
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015989304812834225,
      "loss": 0.6682,
      "step": 152
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00015962566844919787,
      "loss": 0.6548,
      "step": 153
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00015935828877005348,
      "loss": 1.6577,
      "step": 154
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001590909090909091,
      "loss": 1.664,
      "step": 155
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001588235294117647,
      "loss": 0.8135,
      "step": 156
    },
    {
      "epoch": 0.62,
      "eval_loss": 1.4762990474700928,
      "eval_runtime": 1875.1125,
      "eval_samples_per_second": 1.067,
      "eval_steps_per_second": 0.067,
      "step": 156
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001585561497326203,
      "loss": 1.4309,
      "step": 157
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015828877005347595,
      "loss": 0.8049,
      "step": 158
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00015802139037433157,
      "loss": 1.6503,
      "step": 159
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001577540106951872,
      "loss": 1.4392,
      "step": 160
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001574866310160428,
      "loss": 0.709,
      "step": 161
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001572192513368984,
      "loss": 1.5783,
      "step": 162
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00015695187165775401,
      "loss": 0.65,
      "step": 163
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015668449197860963,
      "loss": 0.7895,
      "step": 164
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015641711229946525,
      "loss": 1.7057,
      "step": 165
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00015614973262032087,
      "loss": 0.8384,
      "step": 166
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00015588235294117648,
      "loss": 0.8426,
      "step": 167
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001556149732620321,
      "loss": 1.5182,
      "step": 168
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015534759358288772,
      "loss": 1.7321,
      "step": 169
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001550802139037433,
      "loss": 1.6542,
      "step": 170
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00015481283422459893,
      "loss": 1.4952,
      "step": 171
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.7496,
      "step": 172
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00015427807486631016,
      "loss": 1.4198,
      "step": 173
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015401069518716578,
      "loss": 1.5103,
      "step": 174
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001537433155080214,
      "loss": 0.7112,
      "step": 175
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00015347593582887701,
      "loss": 1.5426,
      "step": 176
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015320855614973263,
      "loss": 1.6245,
      "step": 177
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00015294117647058822,
      "loss": 1.5267,
      "step": 178
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015267379679144387,
      "loss": 1.572,
      "step": 179
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00015240641711229948,
      "loss": 1.4671,
      "step": 180
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001521390374331551,
      "loss": 1.6925,
      "step": 181
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015187165775401072,
      "loss": 1.5266,
      "step": 182
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00015160427807486634,
      "loss": 1.54,
      "step": 183
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015133689839572193,
      "loss": 1.4555,
      "step": 184
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015106951871657754,
      "loss": 1.6631,
      "step": 185
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00015080213903743316,
      "loss": 1.5531,
      "step": 186
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00015053475935828878,
      "loss": 1.4001,
      "step": 187
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001502673796791444,
      "loss": 0.7514,
      "step": 188
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.4462,
      "step": 189
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00014973262032085563,
      "loss": 0.6432,
      "step": 190
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00014946524064171122,
      "loss": 1.3762,
      "step": 191
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00014919786096256684,
      "loss": 1.6002,
      "step": 192
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00014893048128342246,
      "loss": 1.541,
      "step": 193
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00014866310160427807,
      "loss": 1.5357,
      "step": 194
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001483957219251337,
      "loss": 0.7652,
      "step": 195
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001481283422459893,
      "loss": 1.5464,
      "step": 196
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014786096256684493,
      "loss": 1.6457,
      "step": 197
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014759358288770054,
      "loss": 1.4037,
      "step": 198
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014732620320855613,
      "loss": 1.4554,
      "step": 199
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00014705882352941178,
      "loss": 1.6477,
      "step": 200
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001467914438502674,
      "loss": 0.797,
      "step": 201
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014652406417112301,
      "loss": 1.5195,
      "step": 202
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00014625668449197863,
      "loss": 1.5903,
      "step": 203
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014598930481283425,
      "loss": 0.699,
      "step": 204
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014572192513368984,
      "loss": 1.4382,
      "step": 205
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.6502,
      "step": 206
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00014518716577540107,
      "loss": 1.6292,
      "step": 207
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001449197860962567,
      "loss": 0.7866,
      "step": 208
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001446524064171123,
      "loss": 1.4458,
      "step": 209
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014438502673796793,
      "loss": 1.5261,
      "step": 210
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00014411764705882354,
      "loss": 1.5819,
      "step": 211
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014385026737967916,
      "loss": 1.6483,
      "step": 212
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00014358288770053475,
      "loss": 0.8272,
      "step": 213
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00014331550802139037,
      "loss": 1.6659,
      "step": 214
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.000143048128342246,
      "loss": 1.5782,
      "step": 215
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001427807486631016,
      "loss": 1.6261,
      "step": 216
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014251336898395722,
      "loss": 1.481,
      "step": 217
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014224598930481284,
      "loss": 1.5098,
      "step": 218
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014197860962566846,
      "loss": 0.8249,
      "step": 219
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00014171122994652405,
      "loss": 0.8338,
      "step": 220
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001414438502673797,
      "loss": 1.6072,
      "step": 221
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001411764705882353,
      "loss": 1.3685,
      "step": 222
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00014090909090909093,
      "loss": 1.4987,
      "step": 223
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00014064171122994654,
      "loss": 0.7157,
      "step": 224
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00014037433155080216,
      "loss": 1.5327,
      "step": 225
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00014010695187165778,
      "loss": 0.8074,
      "step": 226
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00013983957219251337,
      "loss": 1.5529,
      "step": 227
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.000139572192513369,
      "loss": 1.5925,
      "step": 228
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001393048128342246,
      "loss": 1.5971,
      "step": 229
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013903743315508022,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013877005347593584,
      "loss": 0.9138,
      "step": 231
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013850267379679146,
      "loss": 1.541,
      "step": 232
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013823529411764707,
      "loss": 0.7707,
      "step": 233
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013796791443850266,
      "loss": 1.5394,
      "step": 234
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013770053475935828,
      "loss": 0.8505,
      "step": 235
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001374331550802139,
      "loss": 1.7186,
      "step": 236
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013716577540106952,
      "loss": 1.6292,
      "step": 237
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013689839572192513,
      "loss": 0.7517,
      "step": 238
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013663101604278075,
      "loss": 1.4736,
      "step": 239
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.7838,
      "step": 240
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013609625668449199,
      "loss": 1.4784,
      "step": 241
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001358288770053476,
      "loss": 1.4102,
      "step": 242
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013556149732620322,
      "loss": 1.3916,
      "step": 243
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013529411764705884,
      "loss": 1.5464,
      "step": 244
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013502673796791446,
      "loss": 1.4083,
      "step": 245
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013475935828877007,
      "loss": 0.8571,
      "step": 246
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001344919786096257,
      "loss": 1.641,
      "step": 247
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00013422459893048128,
      "loss": 1.6397,
      "step": 248
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001339572192513369,
      "loss": 1.454,
      "step": 249
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013368983957219252,
      "loss": 1.7245,
      "step": 250
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013342245989304813,
      "loss": 1.3854,
      "step": 251
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013315508021390375,
      "loss": 1.329,
      "step": 252
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00013288770053475937,
      "loss": 0.9579,
      "step": 253
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013262032085561499,
      "loss": 1.5257,
      "step": 254
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001323529411764706,
      "loss": 1.4032,
      "step": 255
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001320855614973262,
      "loss": 1.3976,
      "step": 256
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001318181818181818,
      "loss": 1.5309,
      "step": 257
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013155080213903743,
      "loss": 1.5358,
      "step": 258
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013128342245989305,
      "loss": 1.3189,
      "step": 259
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013101604278074866,
      "loss": 0.7508,
      "step": 260
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013074866310160428,
      "loss": 1.3527,
      "step": 261
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001304812834224599,
      "loss": 1.4635,
      "step": 262
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013021390374331552,
      "loss": 1.4307,
      "step": 263
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00012994652406417113,
      "loss": 1.4932,
      "step": 264
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00012967914438502675,
      "loss": 1.4041,
      "step": 265
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00012941176470588237,
      "loss": 1.2893,
      "step": 266
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00012914438502673799,
      "loss": 0.6639,
      "step": 267
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001288770053475936,
      "loss": 0.6798,
      "step": 268
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001286096256684492,
      "loss": 1.5976,
      "step": 269
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001283422459893048,
      "loss": 1.3931,
      "step": 270
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00012807486631016043,
      "loss": 1.5177,
      "step": 271
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012780748663101605,
      "loss": 1.4111,
      "step": 272
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00012754010695187166,
      "loss": 0.8035,
      "step": 273
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.3537,
      "step": 274
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001270053475935829,
      "loss": 1.3563,
      "step": 275
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00012673796791443852,
      "loss": 1.368,
      "step": 276
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001264705882352941,
      "loss": 1.4295,
      "step": 277
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012620320855614972,
      "loss": 1.3442,
      "step": 278
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012593582887700534,
      "loss": 0.7788,
      "step": 279
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012566844919786096,
      "loss": 1.5099,
      "step": 280
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00012540106951871658,
      "loss": 0.8558,
      "step": 281
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001251336898395722,
      "loss": 0.8357,
      "step": 282
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001248663101604278,
      "loss": 1.542,
      "step": 283
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012459893048128343,
      "loss": 1.5548,
      "step": 284
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012433155080213905,
      "loss": 1.472,
      "step": 285
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00012406417112299466,
      "loss": 0.0,
      "step": 286
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012379679144385028,
      "loss": 1.4032,
      "step": 287
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001235294117647059,
      "loss": 1.4866,
      "step": 288
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012326203208556152,
      "loss": 1.312,
      "step": 289
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012299465240641713,
      "loss": 1.5577,
      "step": 290
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00012272727272727272,
      "loss": 1.3697,
      "step": 291
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012245989304812834,
      "loss": 1.4776,
      "step": 292
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012219251336898396,
      "loss": 1.4517,
      "step": 293
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012192513368983958,
      "loss": 1.4538,
      "step": 294
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001216577540106952,
      "loss": 1.364,
      "step": 295
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00012139037433155081,
      "loss": 0.6793,
      "step": 296
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012112299465240642,
      "loss": 1.6474,
      "step": 297
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012085561497326203,
      "loss": 1.3523,
      "step": 298
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012058823529411765,
      "loss": 1.3526,
      "step": 299
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012032085561497325,
      "loss": 1.5111,
      "step": 300
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012005347593582887,
      "loss": 1.4862,
      "step": 301
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00011978609625668449,
      "loss": 1.4216,
      "step": 302
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001195187165775401,
      "loss": 1.4293,
      "step": 303
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011925133689839574,
      "loss": 1.5012,
      "step": 304
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011898395721925135,
      "loss": 1.5517,
      "step": 305
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011871657754010697,
      "loss": 1.3785,
      "step": 306
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011844919786096258,
      "loss": 1.5506,
      "step": 307
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001181818181818182,
      "loss": 0.7255,
      "step": 308
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011791443850267381,
      "loss": 1.4841,
      "step": 309
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011764705882352942,
      "loss": 1.5495,
      "step": 310
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011737967914438503,
      "loss": 1.4021,
      "step": 311
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011711229946524065,
      "loss": 1.396,
      "step": 312
    },
    {
      "epoch": 1.25,
      "eval_loss": 1.4490689039230347,
      "eval_runtime": 1817.1431,
      "eval_samples_per_second": 1.101,
      "eval_steps_per_second": 0.069,
      "step": 312
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00011684491978609627,
      "loss": 0.7482,
      "step": 313
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011657754010695187,
      "loss": 1.5667,
      "step": 314
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011631016042780749,
      "loss": 1.5188,
      "step": 315
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001160427807486631,
      "loss": 1.4705,
      "step": 316
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011577540106951872,
      "loss": 1.3675,
      "step": 317
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011550802139037433,
      "loss": 1.397,
      "step": 318
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011524064171122995,
      "loss": 0.7067,
      "step": 319
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011497326203208556,
      "loss": 1.6246,
      "step": 320
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011470588235294118,
      "loss": 0.5517,
      "step": 321
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00011443850267379678,
      "loss": 1.3288,
      "step": 322
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001141711229946524,
      "loss": 1.5879,
      "step": 323
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011390374331550802,
      "loss": 0.6801,
      "step": 324
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011363636363636365,
      "loss": 1.4296,
      "step": 325
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00011336898395721927,
      "loss": 1.3548,
      "step": 326
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011310160427807488,
      "loss": 1.3336,
      "step": 327
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00011283422459893049,
      "loss": 1.4161,
      "step": 328
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001125668449197861,
      "loss": 1.4569,
      "step": 329
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011229946524064172,
      "loss": 1.3923,
      "step": 330
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00011203208556149734,
      "loss": 0.7172,
      "step": 331
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011176470588235294,
      "loss": 0.6755,
      "step": 332
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011149732620320856,
      "loss": 1.4229,
      "step": 333
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011122994652406418,
      "loss": 1.3606,
      "step": 334
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001109625668449198,
      "loss": 1.2319,
      "step": 335
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001106951871657754,
      "loss": 0.773,
      "step": 336
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011042780748663102,
      "loss": 1.3415,
      "step": 337
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011016042780748664,
      "loss": 1.4365,
      "step": 338
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00010989304812834224,
      "loss": 0.7139,
      "step": 339
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00010962566844919786,
      "loss": 0.0,
      "step": 340
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00010935828877005347,
      "loss": 0.667,
      "step": 341
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.777,
      "step": 342
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001088235294117647,
      "loss": 1.5484,
      "step": 343
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010855614973262031,
      "loss": 1.443,
      "step": 344
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010828877005347596,
      "loss": 1.5211,
      "step": 345
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010802139037433156,
      "loss": 1.5713,
      "step": 346
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00010775401069518718,
      "loss": 0.7555,
      "step": 347
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001074866310160428,
      "loss": 1.6702,
      "step": 348
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001072192513368984,
      "loss": 1.2528,
      "step": 349
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010695187165775402,
      "loss": 1.5392,
      "step": 350
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00010668449197860964,
      "loss": 1.476,
      "step": 351
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010641711229946525,
      "loss": 1.3388,
      "step": 352
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00010614973262032086,
      "loss": 1.5115,
      "step": 353
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010588235294117647,
      "loss": 1.4062,
      "step": 354
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010561497326203209,
      "loss": 1.4835,
      "step": 355
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010534759358288771,
      "loss": 1.328,
      "step": 356
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010508021390374331,
      "loss": 1.4516,
      "step": 357
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010481283422459893,
      "loss": 0.809,
      "step": 358
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010454545454545455,
      "loss": 0.8017,
      "step": 359
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010427807486631017,
      "loss": 0.7622,
      "step": 360
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010401069518716577,
      "loss": 0.8361,
      "step": 361
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010374331550802139,
      "loss": 1.5416,
      "step": 362
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.000103475935828877,
      "loss": 1.4239,
      "step": 363
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010320855614973262,
      "loss": 1.4299,
      "step": 364
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010294117647058823,
      "loss": 1.5841,
      "step": 365
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010267379679144387,
      "loss": 0.6902,
      "step": 366
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010240641711229947,
      "loss": 1.3335,
      "step": 367
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010213903743315509,
      "loss": 0.7347,
      "step": 368
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010187165775401071,
      "loss": 0.7148,
      "step": 369
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010160427807486633,
      "loss": 0.7521,
      "step": 370
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010133689839572193,
      "loss": 1.4992,
      "step": 371
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010106951871657755,
      "loss": 1.5119,
      "step": 372
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010080213903743317,
      "loss": 0.0,
      "step": 373
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010053475935828878,
      "loss": 1.5924,
      "step": 374
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010026737967914439,
      "loss": 1.3433,
      "step": 375
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001,
      "loss": 0.7781,
      "step": 376
    },
    {
      "epoch": 1.51,
      "learning_rate": 9.973262032085562e-05,
      "loss": 1.3294,
      "step": 377
    },
    {
      "epoch": 1.51,
      "learning_rate": 9.946524064171123e-05,
      "loss": 1.1677,
      "step": 378
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.919786096256684e-05,
      "loss": 1.4861,
      "step": 379
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.893048128342246e-05,
      "loss": 1.2648,
      "step": 380
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.866310160427808e-05,
      "loss": 0.0,
      "step": 381
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.83957219251337e-05,
      "loss": 1.5553,
      "step": 382
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.812834224598931e-05,
      "loss": 1.5253,
      "step": 383
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.786096256684493e-05,
      "loss": 1.2794,
      "step": 384
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.759358288770053e-05,
      "loss": 0.6316,
      "step": 385
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.732620320855615e-05,
      "loss": 0.0,
      "step": 386
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.705882352941177e-05,
      "loss": 1.5085,
      "step": 387
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.679144385026739e-05,
      "loss": 1.3594,
      "step": 388
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.652406417112299e-05,
      "loss": 1.4425,
      "step": 389
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.625668449197861e-05,
      "loss": 1.3698,
      "step": 390
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.598930481283423e-05,
      "loss": 1.421,
      "step": 391
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.572192513368984e-05,
      "loss": 0.7862,
      "step": 392
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.545454545454546e-05,
      "loss": 1.6053,
      "step": 393
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.518716577540108e-05,
      "loss": 1.4012,
      "step": 394
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.49197860962567e-05,
      "loss": 1.5663,
      "step": 395
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.46524064171123e-05,
      "loss": 1.3553,
      "step": 396
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.438502673796792e-05,
      "loss": 1.4471,
      "step": 397
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.411764705882353e-05,
      "loss": 1.5874,
      "step": 398
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.385026737967915e-05,
      "loss": 0.6658,
      "step": 399
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.358288770053476e-05,
      "loss": 1.3355,
      "step": 400
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.331550802139037e-05,
      "loss": 1.4611,
      "step": 401
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.3048128342246e-05,
      "loss": 1.4876,
      "step": 402
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.278074866310161e-05,
      "loss": 1.4782,
      "step": 403
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.251336898395723e-05,
      "loss": 1.6359,
      "step": 404
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.224598930481284e-05,
      "loss": 1.3812,
      "step": 405
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.197860962566846e-05,
      "loss": 1.4893,
      "step": 406
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.171122994652406e-05,
      "loss": 1.3225,
      "step": 407
    },
    {
      "epoch": 1.63,
      "learning_rate": 9.144385026737968e-05,
      "loss": 1.453,
      "step": 408
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.11764705882353e-05,
      "loss": 1.4077,
      "step": 409
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.5797,
      "step": 410
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.064171122994652e-05,
      "loss": 0.7328,
      "step": 411
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.037433155080214e-05,
      "loss": 0.6501,
      "step": 412
    },
    {
      "epoch": 1.65,
      "learning_rate": 9.010695187165777e-05,
      "loss": 0.7809,
      "step": 413
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.983957219251337e-05,
      "loss": 1.3834,
      "step": 414
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.957219251336899e-05,
      "loss": 1.4274,
      "step": 415
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.930481283422461e-05,
      "loss": 1.5683,
      "step": 416
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.903743315508021e-05,
      "loss": 1.5326,
      "step": 417
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.877005347593583e-05,
      "loss": 0.4335,
      "step": 418
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.850267379679145e-05,
      "loss": 1.3797,
      "step": 419
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.823529411764706e-05,
      "loss": 1.3507,
      "step": 420
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.796791443850267e-05,
      "loss": 1.2687,
      "step": 421
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.770053475935829e-05,
      "loss": 1.4994,
      "step": 422
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.743315508021392e-05,
      "loss": 1.2264,
      "step": 423
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.716577540106952e-05,
      "loss": 1.498,
      "step": 424
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.689839572192514e-05,
      "loss": 1.158,
      "step": 425
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.663101604278076e-05,
      "loss": 0.0,
      "step": 426
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.636363636363637e-05,
      "loss": 0.8047,
      "step": 427
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.609625668449198e-05,
      "loss": 1.3758,
      "step": 428
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.58288770053476e-05,
      "loss": 1.4653,
      "step": 429
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.556149732620321e-05,
      "loss": 1.4074,
      "step": 430
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.529411764705883e-05,
      "loss": 1.5387,
      "step": 431
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.502673796791443e-05,
      "loss": 1.4792,
      "step": 432
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.475935828877005e-05,
      "loss": 0.6999,
      "step": 433
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.449197860962568e-05,
      "loss": 0.7177,
      "step": 434
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.422459893048129e-05,
      "loss": 1.5499,
      "step": 435
    },
    {
      "epoch": 1.74,
      "learning_rate": 8.39572192513369e-05,
      "loss": 1.4556,
      "step": 436
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.368983957219252e-05,
      "loss": 1.5381,
      "step": 437
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.342245989304814e-05,
      "loss": 1.2546,
      "step": 438
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.315508021390374e-05,
      "loss": 1.4273,
      "step": 439
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.288770053475936e-05,
      "loss": 1.7713,
      "step": 440
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.262032085561498e-05,
      "loss": 1.4537,
      "step": 441
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.23529411764706e-05,
      "loss": 1.5588,
      "step": 442
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.20855614973262e-05,
      "loss": 1.4436,
      "step": 443
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.181818181818183e-05,
      "loss": 1.2643,
      "step": 444
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.155080213903745e-05,
      "loss": 1.2508,
      "step": 445
    },
    {
      "epoch": 1.78,
      "learning_rate": 8.128342245989305e-05,
      "loss": 1.3579,
      "step": 446
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.101604278074867e-05,
      "loss": 1.4784,
      "step": 447
    },
    {
      "epoch": 1.79,
      "learning_rate": 8.074866310160429e-05,
      "loss": 1.4132,
      "step": 448
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.04812834224599e-05,
      "loss": 0.7507,
      "step": 449
    },
    {
      "epoch": 1.8,
      "learning_rate": 8.021390374331551e-05,
      "loss": 1.5176,
      "step": 450
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.994652406417112e-05,
      "loss": 1.4306,
      "step": 451
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.967914438502674e-05,
      "loss": 0.5959,
      "step": 452
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.941176470588235e-05,
      "loss": 1.6221,
      "step": 453
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.914438502673798e-05,
      "loss": 0.7004,
      "step": 454
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.88770053475936e-05,
      "loss": 1.5374,
      "step": 455
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.86096256684492e-05,
      "loss": 1.5912,
      "step": 456
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.834224598930482e-05,
      "loss": 0.6562,
      "step": 457
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.807486631016043e-05,
      "loss": 0.6382,
      "step": 458
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.780748663101605e-05,
      "loss": 1.4506,
      "step": 459
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.754010695187165e-05,
      "loss": 1.4908,
      "step": 460
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.727272727272727e-05,
      "loss": 1.5851,
      "step": 461
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.700534759358289e-05,
      "loss": 0.7288,
      "step": 462
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.673796791443851e-05,
      "loss": 1.4052,
      "step": 463
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.647058823529411e-05,
      "loss": 1.4992,
      "step": 464
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.620320855614974e-05,
      "loss": 1.359,
      "step": 465
    },
    {
      "epoch": 1.86,
      "learning_rate": 7.593582887700536e-05,
      "loss": 0.7587,
      "step": 466
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.566844919786096e-05,
      "loss": 1.5194,
      "step": 467
    },
    {
      "epoch": 1.87,
      "learning_rate": 7.540106951871658e-05,
      "loss": 1.4519,
      "step": 468
    },
    {
      "epoch": 1.87,
      "eval_loss": 1.4598816633224487,
      "eval_runtime": 1929.1202,
      "eval_samples_per_second": 1.037,
      "eval_steps_per_second": 0.065,
      "step": 468
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.51336898395722e-05,
      "loss": 0.645,
      "step": 469
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.486631016042782e-05,
      "loss": 0.7295,
      "step": 470
    },
    {
      "epoch": 1.88,
      "learning_rate": 7.459893048128342e-05,
      "loss": 1.3374,
      "step": 471
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.433155080213904e-05,
      "loss": 0.7399,
      "step": 472
    },
    {
      "epoch": 1.89,
      "learning_rate": 7.406417112299465e-05,
      "loss": 1.3815,
      "step": 473
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.379679144385027e-05,
      "loss": 1.3802,
      "step": 474
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.352941176470589e-05,
      "loss": 1.3687,
      "step": 475
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.326203208556151e-05,
      "loss": 0.8355,
      "step": 476
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.299465240641712e-05,
      "loss": 1.469,
      "step": 477
    },
    {
      "epoch": 1.91,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.4634,
      "step": 478
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.245989304812835e-05,
      "loss": 1.4963,
      "step": 479
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.219251336898396e-05,
      "loss": 1.3808,
      "step": 480
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.192513368983958e-05,
      "loss": 1.5888,
      "step": 481
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.165775401069518e-05,
      "loss": 1.1737,
      "step": 482
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.13903743315508e-05,
      "loss": 1.4853,
      "step": 483
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.112299465240642e-05,
      "loss": 1.2292,
      "step": 484
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.085561497326202e-05,
      "loss": 0.7759,
      "step": 485
    },
    {
      "epoch": 1.94,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.4033,
      "step": 486
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.032085561497327e-05,
      "loss": 1.4443,
      "step": 487
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.005347593582889e-05,
      "loss": 0.0,
      "step": 488
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.97860962566845e-05,
      "loss": 0.7743,
      "step": 489
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.951871657754011e-05,
      "loss": 1.4706,
      "step": 490
    },
    {
      "epoch": 1.96,
      "learning_rate": 6.925133689839573e-05,
      "loss": 1.4723,
      "step": 491
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.898395721925133e-05,
      "loss": 1.3785,
      "step": 492
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.871657754010695e-05,
      "loss": 1.3848,
      "step": 493
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.844919786096257e-05,
      "loss": 1.362,
      "step": 494
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.818181818181818e-05,
      "loss": 0.7792,
      "step": 495
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.79144385026738e-05,
      "loss": 1.4883,
      "step": 496
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.764705882352942e-05,
      "loss": 1.3965,
      "step": 497
    },
    {
      "epoch": 1.99,
      "learning_rate": 6.737967914438504e-05,
      "loss": 1.3523,
      "step": 498
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.711229946524064e-05,
      "loss": 1.5477,
      "step": 499
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.684491978609626e-05,
      "loss": 0.7701,
      "step": 500
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.657754010695188e-05,
      "loss": 1.3462,
      "step": 501
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.631016042780749e-05,
      "loss": 1.2878,
      "step": 502
    },
    {
      "epoch": 2.01,
      "learning_rate": 6.60427807486631e-05,
      "loss": 1.2517,
      "step": 503
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.577540106951871e-05,
      "loss": 0.6838,
      "step": 504
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.550802139037433e-05,
      "loss": 0.5911,
      "step": 505
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.524064171122995e-05,
      "loss": 1.3103,
      "step": 506
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.497326203208557e-05,
      "loss": 1.4199,
      "step": 507
    },
    {
      "epoch": 2.03,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.4253,
      "step": 508
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.44385026737968e-05,
      "loss": 0.5759,
      "step": 509
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.41711229946524e-05,
      "loss": 1.3032,
      "step": 510
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.390374331550802e-05,
      "loss": 0.6768,
      "step": 511
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.363636363636364e-05,
      "loss": 1.5451,
      "step": 512
    },
    {
      "epoch": 2.05,
      "learning_rate": 6.336898395721926e-05,
      "loss": 1.325,
      "step": 513
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.310160427807486e-05,
      "loss": 0.5231,
      "step": 514
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.283422459893048e-05,
      "loss": 1.2246,
      "step": 515
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.25668449197861e-05,
      "loss": 1.2088,
      "step": 516
    },
    {
      "epoch": 2.07,
      "learning_rate": 6.229946524064171e-05,
      "loss": 0.6522,
      "step": 517
    },
    {
      "epoch": 2.07,
      "learning_rate": 6.203208556149733e-05,
      "loss": 1.2557,
      "step": 518
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.176470588235295e-05,
      "loss": 0.6342,
      "step": 519
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.149732620320857e-05,
      "loss": 1.2905,
      "step": 520
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.122994652406417e-05,
      "loss": 0.7026,
      "step": 521
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.096256684491979e-05,
      "loss": 0.0,
      "step": 522
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.0695187165775406e-05,
      "loss": 1.3462,
      "step": 523
    },
    {
      "epoch": 2.1,
      "learning_rate": 6.0427807486631016e-05,
      "loss": 0.6842,
      "step": 524
    },
    {
      "epoch": 2.1,
      "learning_rate": 6.016042780748663e-05,
      "loss": 1.1985,
      "step": 525
    },
    {
      "epoch": 2.1,
      "learning_rate": 5.9893048128342244e-05,
      "loss": 1.2946,
      "step": 526
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.962566844919787e-05,
      "loss": 0.5533,
      "step": 527
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.9358288770053486e-05,
      "loss": 1.3705,
      "step": 528
    },
    {
      "epoch": 2.12,
      "learning_rate": 5.90909090909091e-05,
      "loss": 1.3784,
      "step": 529
    },
    {
      "epoch": 2.12,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.4377,
      "step": 530
    },
    {
      "epoch": 2.12,
      "learning_rate": 5.8556149732620325e-05,
      "loss": 1.5401,
      "step": 531
    },
    {
      "epoch": 2.13,
      "learning_rate": 5.8288770053475936e-05,
      "loss": 0.7267,
      "step": 532
    },
    {
      "epoch": 2.13,
      "learning_rate": 5.802139037433155e-05,
      "loss": 1.4631,
      "step": 533
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.7754010695187164e-05,
      "loss": 1.2999,
      "step": 534
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.748663101604278e-05,
      "loss": 1.4007,
      "step": 535
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.721925133689839e-05,
      "loss": 1.2896,
      "step": 536
    },
    {
      "epoch": 2.15,
      "learning_rate": 5.695187165775401e-05,
      "loss": 0.6588,
      "step": 537
    },
    {
      "epoch": 2.15,
      "learning_rate": 5.6684491978609634e-05,
      "loss": 1.3118,
      "step": 538
    },
    {
      "epoch": 2.16,
      "learning_rate": 5.6417112299465244e-05,
      "loss": 1.4214,
      "step": 539
    },
    {
      "epoch": 2.16,
      "learning_rate": 5.614973262032086e-05,
      "loss": 0.707,
      "step": 540
    },
    {
      "epoch": 2.16,
      "learning_rate": 5.588235294117647e-05,
      "loss": 0.6199,
      "step": 541
    },
    {
      "epoch": 2.17,
      "learning_rate": 5.561497326203209e-05,
      "loss": 1.6548,
      "step": 542
    },
    {
      "epoch": 2.17,
      "learning_rate": 5.53475935828877e-05,
      "loss": 0.6053,
      "step": 543
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.508021390374332e-05,
      "loss": 0.6968,
      "step": 544
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.481283422459893e-05,
      "loss": 1.3714,
      "step": 545
    },
    {
      "epoch": 2.18,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.4276,
      "step": 546
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.427807486631016e-05,
      "loss": 1.3744,
      "step": 547
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.401069518716578e-05,
      "loss": 1.4243,
      "step": 548
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.37433155080214e-05,
      "loss": 0.6886,
      "step": 549
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.347593582887701e-05,
      "loss": 1.3409,
      "step": 550
    },
    {
      "epoch": 2.2,
      "learning_rate": 5.320855614973263e-05,
      "loss": 1.2544,
      "step": 551
    },
    {
      "epoch": 2.21,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.5045,
      "step": 552
    },
    {
      "epoch": 2.21,
      "learning_rate": 5.2673796791443855e-05,
      "loss": 1.3408,
      "step": 553
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.2406417112299466e-05,
      "loss": 0.5976,
      "step": 554
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.213903743315508e-05,
      "loss": 0.6946,
      "step": 555
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.1871657754010694e-05,
      "loss": 0.7075,
      "step": 556
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.160427807486631e-05,
      "loss": 1.3134,
      "step": 557
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.1336898395721935e-05,
      "loss": 0.6443,
      "step": 558
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.1069518716577546e-05,
      "loss": 1.2005,
      "step": 559
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.0802139037433164e-05,
      "loss": 1.2439,
      "step": 560
    },
    {
      "epoch": 2.24,
      "learning_rate": 5.0534759358288774e-05,
      "loss": 1.2592,
      "step": 561
    },
    {
      "epoch": 2.25,
      "learning_rate": 5.026737967914439e-05,
      "loss": 1.2921,
      "step": 562
    },
    {
      "epoch": 2.25,
      "learning_rate": 5e-05,
      "loss": 0.6906,
      "step": 563
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.973262032085561e-05,
      "loss": 1.5856,
      "step": 564
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.946524064171123e-05,
      "loss": 1.2068,
      "step": 565
    },
    {
      "epoch": 2.26,
      "learning_rate": 4.919786096256685e-05,
      "loss": 1.5172,
      "step": 566
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.8930481283422465e-05,
      "loss": 1.2724,
      "step": 567
    },
    {
      "epoch": 2.27,
      "learning_rate": 4.8663101604278076e-05,
      "loss": 1.3549,
      "step": 568
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.8395721925133694e-05,
      "loss": 1.2922,
      "step": 569
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.8128342245989304e-05,
      "loss": 1.1215,
      "step": 570
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.786096256684492e-05,
      "loss": 1.2911,
      "step": 571
    },
    {
      "epoch": 2.29,
      "learning_rate": 4.759358288770054e-05,
      "loss": 1.2171,
      "step": 572
    },
    {
      "epoch": 2.29,
      "learning_rate": 4.732620320855615e-05,
      "loss": 1.1559,
      "step": 573
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.3786,
      "step": 574
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.679144385026738e-05,
      "loss": 1.3532,
      "step": 575
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.6524064171123e-05,
      "loss": 1.326,
      "step": 576
    },
    {
      "epoch": 2.31,
      "learning_rate": 4.625668449197861e-05,
      "loss": 1.3435,
      "step": 577
    },
    {
      "epoch": 2.31,
      "learning_rate": 4.598930481283423e-05,
      "loss": 0.7063,
      "step": 578
    },
    {
      "epoch": 2.32,
      "learning_rate": 4.572192513368984e-05,
      "loss": 1.294,
      "step": 579
    },
    {
      "epoch": 2.32,
      "learning_rate": 4.545454545454546e-05,
      "loss": 0.6401,
      "step": 580
    },
    {
      "epoch": 2.32,
      "learning_rate": 4.518716577540107e-05,
      "loss": 1.4263,
      "step": 581
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.491978609625669e-05,
      "loss": 1.4469,
      "step": 582
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.4652406417112304e-05,
      "loss": 1.2339,
      "step": 583
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.4385026737967915e-05,
      "loss": 1.4478,
      "step": 584
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.411764705882353e-05,
      "loss": 0.5989,
      "step": 585
    },
    {
      "epoch": 2.34,
      "learning_rate": 4.385026737967914e-05,
      "loss": 0.7184,
      "step": 586
    },
    {
      "epoch": 2.35,
      "learning_rate": 4.358288770053476e-05,
      "loss": 1.3133,
      "step": 587
    },
    {
      "epoch": 2.35,
      "learning_rate": 4.331550802139038e-05,
      "loss": 0.6392,
      "step": 588
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.304812834224599e-05,
      "loss": 1.2456,
      "step": 589
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.2780748663101606e-05,
      "loss": 0.5998,
      "step": 590
    },
    {
      "epoch": 2.36,
      "learning_rate": 4.251336898395722e-05,
      "loss": 1.2969,
      "step": 591
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.224598930481284e-05,
      "loss": 1.463,
      "step": 592
    },
    {
      "epoch": 2.37,
      "learning_rate": 4.197860962566845e-05,
      "loss": 1.3047,
      "step": 593
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.171122994652407e-05,
      "loss": 1.3019,
      "step": 594
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.144385026737968e-05,
      "loss": 1.4478,
      "step": 595
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.1726,
      "step": 596
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 0.7182,
      "step": 597
    },
    {
      "epoch": 2.39,
      "learning_rate": 4.0641711229946525e-05,
      "loss": 1.5264,
      "step": 598
    },
    {
      "epoch": 2.4,
      "learning_rate": 4.037433155080214e-05,
      "loss": 1.2031,
      "step": 599
    },
    {
      "epoch": 2.4,
      "learning_rate": 4.0106951871657754e-05,
      "loss": 1.251,
      "step": 600
    },
    {
      "epoch": 2.4,
      "learning_rate": 3.983957219251337e-05,
      "loss": 1.3863,
      "step": 601
    },
    {
      "epoch": 2.41,
      "learning_rate": 3.957219251336899e-05,
      "loss": 1.3897,
      "step": 602
    },
    {
      "epoch": 2.41,
      "learning_rate": 3.93048128342246e-05,
      "loss": 1.3974,
      "step": 603
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.903743315508022e-05,
      "loss": 1.4126,
      "step": 604
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.877005347593583e-05,
      "loss": 1.3108,
      "step": 605
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.8502673796791445e-05,
      "loss": 1.4013,
      "step": 606
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.8235294117647055e-05,
      "loss": 0.5406,
      "step": 607
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.796791443850268e-05,
      "loss": 0.6561,
      "step": 608
    },
    {
      "epoch": 2.44,
      "learning_rate": 3.770053475935829e-05,
      "loss": 1.3784,
      "step": 609
    },
    {
      "epoch": 2.44,
      "learning_rate": 3.743315508021391e-05,
      "loss": 0.6025,
      "step": 610
    },
    {
      "epoch": 2.44,
      "learning_rate": 3.716577540106952e-05,
      "loss": 0.6405,
      "step": 611
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.6898395721925136e-05,
      "loss": 0.0,
      "step": 612
    },
    {
      "epoch": 2.45,
      "learning_rate": 3.6631016042780753e-05,
      "loss": 1.2733,
      "step": 613
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.322,
      "step": 614
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.609625668449198e-05,
      "loss": 0.6051,
      "step": 615
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.582887700534759e-05,
      "loss": 1.2809,
      "step": 616
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.556149732620321e-05,
      "loss": 1.2519,
      "step": 617
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.3455,
      "step": 618
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.5026737967914445e-05,
      "loss": 1.3249,
      "step": 619
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.4759358288770055e-05,
      "loss": 1.386,
      "step": 620
    },
    {
      "epoch": 2.48,
      "learning_rate": 3.4491978609625666e-05,
      "loss": 0.6617,
      "step": 621
    },
    {
      "epoch": 2.49,
      "learning_rate": 3.4224598930481284e-05,
      "loss": 1.3334,
      "step": 622
    },
    {
      "epoch": 2.49,
      "learning_rate": 3.39572192513369e-05,
      "loss": 1.3032,
      "step": 623
    },
    {
      "epoch": 2.5,
      "learning_rate": 3.368983957219252e-05,
      "loss": 1.316,
      "step": 624
    },
    {
      "epoch": 2.5,
      "eval_loss": 1.4671682119369507,
      "eval_runtime": 1873.2618,
      "eval_samples_per_second": 1.068,
      "eval_steps_per_second": 0.067,
      "step": 624
    }
  ],
  "logging_steps": 1,
  "max_steps": 750,
  "num_train_epochs": 3,
  "save_steps": 156,
  "total_flos": 5.868557043695616e+17,
  "trial_name": null,
  "trial_params": null
}