{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9976717112922002,
  "global_step": 858,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 0.0,
      "loss": 1.0483,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.254921071067263e-06,
      "loss": 1.0225,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.743890341169911e-06,
      "loss": 1.0688,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.509842142134527e-06,
      "loss": 1.1475,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.879620776439306e-06,
      "loss": 1.0583,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0998811412237173e-05,
      "loss": 0.9918,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.1945073611827293e-05,
      "loss": 1.093,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.276476321320179e-05,
      "loss": 1.0069,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.3487780682339822e-05,
      "loss": 1.0096,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.4134541847506571e-05,
      "loss": 1.0619,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.4719608488056167e-05,
      "loss": 1.0169,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.5253732483304438e-05,
      "loss": 0.9398,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.574507892893274e-05,
      "loss": 0.9938,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6199994682894558e-05,
      "loss": 1.027,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6623511117609218e-05,
      "loss": 1.0992,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.7019684284269053e-05,
      "loss": 0.9846,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.7391831770440535e-05,
      "loss": 1.0349,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.7742701753407083e-05,
      "loss": 1.0182,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.8074596285317475e-05,
      "loss": 1.1008,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.838946291857383e-05,
      "loss": 0.9999,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.8688963952997205e-05,
      "loss": 0.9905,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.8974529559123432e-05,
      "loss": 0.8672,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.924739908310523e-05,
      "loss": 1.037,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.95086535543717e-05,
      "loss": 0.9963,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9759241552878612e-05,
      "loss": 1.0142,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 2e-05,
      "loss": 0.9938,
      "step": 26
    },
    {
      "epoch": 0.06,
      "learning_rate": 2e-05,
      "loss": 0.9289,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9975961538461538e-05,
      "loss": 1.0366,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9951923076923078e-05,
      "loss": 0.9987,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9927884615384617e-05,
      "loss": 0.9719,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9903846153846157e-05,
      "loss": 0.9121,
      "step": 31
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9879807692307693e-05,
      "loss": 1.0601,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9855769230769233e-05,
      "loss": 1.0092,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.983173076923077e-05,
      "loss": 0.9153,
      "step": 34
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.980769230769231e-05,
      "loss": 0.977,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.978365384615385e-05,
      "loss": 0.887,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.975961538461539e-05,
      "loss": 0.9918,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9735576923076925e-05,
      "loss": 0.95,
      "step": 38
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9711538461538465e-05,
      "loss": 0.925,
      "step": 39
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.96875e-05,
      "loss": 1.0034,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.966346153846154e-05,
      "loss": 0.9703,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.963942307692308e-05,
      "loss": 0.9166,
      "step": 42
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9615384615384617e-05,
      "loss": 0.9871,
      "step": 43
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9591346153846156e-05,
      "loss": 0.919,
      "step": 44
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9567307692307693e-05,
      "loss": 1.0032,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9543269230769232e-05,
      "loss": 0.9304,
      "step": 46
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9519230769230772e-05,
      "loss": 0.9259,
      "step": 47
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.949519230769231e-05,
      "loss": 0.956,
      "step": 48
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9471153846153848e-05,
      "loss": 0.812,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9447115384615388e-05,
      "loss": 1.0034,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9423076923076924e-05,
      "loss": 0.9806,
      "step": 51
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9399038461538464e-05,
      "loss": 0.8682,
      "step": 52
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9375e-05,
      "loss": 0.8552,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.935096153846154e-05,
      "loss": 0.8743,
      "step": 54
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.932692307692308e-05,
      "loss": 0.8649,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9302884615384616e-05,
      "loss": 0.899,
      "step": 56
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9278846153846155e-05,
      "loss": 0.8708,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9254807692307692e-05,
      "loss": 0.8936,
      "step": 58
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.923076923076923e-05,
      "loss": 0.9183,
      "step": 59
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.920673076923077e-05,
      "loss": 0.9631,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.918269230769231e-05,
      "loss": 0.8698,
      "step": 61
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9158653846153847e-05,
      "loss": 0.8682,
      "step": 62
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9134615384615387e-05,
      "loss": 0.9105,
      "step": 63
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9110576923076923e-05,
      "loss": 0.8857,
      "step": 64
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9086538461538463e-05,
      "loss": 0.8901,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9062500000000003e-05,
      "loss": 0.9125,
      "step": 66
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.903846153846154e-05,
      "loss": 0.9316,
      "step": 67
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.901442307692308e-05,
      "loss": 0.8408,
      "step": 68
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.8990384615384615e-05,
      "loss": 0.8707,
      "step": 69
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.8966346153846155e-05,
      "loss": 0.814,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8942307692307694e-05,
      "loss": 0.9611,
      "step": 71
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8918269230769234e-05,
      "loss": 0.9297,
      "step": 72
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.889423076923077e-05,
      "loss": 0.8387,
      "step": 73
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.887019230769231e-05,
      "loss": 0.8318,
      "step": 74
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.8846153846153846e-05,
      "loss": 0.8801,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8822115384615386e-05,
      "loss": 0.8473,
      "step": 76
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8798076923076926e-05,
      "loss": 0.8585,
      "step": 77
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8774038461538465e-05,
      "loss": 0.91,
      "step": 78
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.8803,
      "step": 79
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8725961538461538e-05,
      "loss": 0.8976,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8701923076923078e-05,
      "loss": 0.9128,
      "step": 81
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8677884615384617e-05,
      "loss": 0.8877,
      "step": 82
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8653846153846157e-05,
      "loss": 0.8564,
      "step": 83
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8629807692307693e-05,
      "loss": 0.7911,
      "step": 84
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8605769230769233e-05,
      "loss": 0.8331,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.858173076923077e-05,
      "loss": 0.8848,
      "step": 86
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.855769230769231e-05,
      "loss": 0.8896,
      "step": 87
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.853365384615385e-05,
      "loss": 0.842,
      "step": 88
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.850961538461539e-05,
      "loss": 0.8668,
      "step": 89
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.8485576923076925e-05,
      "loss": 0.7879,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.8392,
      "step": 91
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.84375e-05,
      "loss": 0.8157,
      "step": 92
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.841346153846154e-05,
      "loss": 0.8149,
      "step": 93
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.8389423076923077e-05,
      "loss": 0.8053,
      "step": 94
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.8365384615384617e-05,
      "loss": 0.9207,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.8341346153846156e-05,
      "loss": 0.7988,
      "step": 96
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8317307692307693e-05,
      "loss": 0.8393,
      "step": 97
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8293269230769232e-05,
      "loss": 0.8953,
      "step": 98
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.826923076923077e-05,
      "loss": 0.8559,
      "step": 99
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.824519230769231e-05,
      "loss": 0.8547,
      "step": 100
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8221153846153848e-05,
      "loss": 0.8414,
      "step": 101
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8197115384615388e-05,
      "loss": 0.8191,
      "step": 102
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8173076923076924e-05,
      "loss": 0.805,
      "step": 103
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8149038461538464e-05,
      "loss": 0.7944,
      "step": 104
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8125e-05,
      "loss": 0.7968,
      "step": 105
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.810096153846154e-05,
      "loss": 0.8526,
      "step": 106
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.807692307692308e-05,
      "loss": 0.8057,
      "step": 107
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8052884615384616e-05,
      "loss": 0.7905,
      "step": 108
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.8028846153846156e-05,
      "loss": 0.8364,
      "step": 109
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8004807692307692e-05,
      "loss": 0.8054,
      "step": 110
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.798076923076923e-05,
      "loss": 0.8042,
      "step": 111
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.795673076923077e-05,
      "loss": 0.8093,
      "step": 112
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.793269230769231e-05,
      "loss": 0.7838,
      "step": 113
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7908653846153847e-05,
      "loss": 0.8363,
      "step": 114
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7884615384615387e-05,
      "loss": 0.8099,
      "step": 115
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7860576923076923e-05,
      "loss": 0.766,
      "step": 116
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7836538461538463e-05,
      "loss": 0.7759,
      "step": 117
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.7812500000000003e-05,
      "loss": 0.7889,
      "step": 118
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.778846153846154e-05,
      "loss": 0.7188,
      "step": 119
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.776442307692308e-05,
      "loss": 0.7963,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.7740384615384615e-05,
      "loss": 0.8051,
      "step": 121
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.7716346153846155e-05,
      "loss": 0.7253,
      "step": 122
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.7692307692307694e-05,
      "loss": 0.859,
      "step": 123
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.7668269230769234e-05,
      "loss": 0.7741,
      "step": 124
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.764423076923077e-05,
      "loss": 0.8616,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.762019230769231e-05,
      "loss": 0.7991,
      "step": 126
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7596153846153846e-05,
      "loss": 0.7313,
      "step": 127
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7572115384615386e-05,
      "loss": 0.8015,
      "step": 128
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7548076923076926e-05,
      "loss": 0.8326,
      "step": 129
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.7524038461538466e-05,
      "loss": 0.8223,
      "step": 130
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 0.835,
      "step": 131
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7475961538461538e-05,
      "loss": 0.7557,
      "step": 132
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7451923076923078e-05,
      "loss": 0.8201,
      "step": 133
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7427884615384618e-05,
      "loss": 0.7927,
      "step": 134
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.7403846153846157e-05,
      "loss": 0.7665,
      "step": 135
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.7379807692307694e-05,
      "loss": 0.8599,
      "step": 136
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.7355769230769233e-05,
      "loss": 0.7581,
      "step": 137
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.733173076923077e-05,
      "loss": 0.7565,
      "step": 138
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.730769230769231e-05,
      "loss": 0.716,
      "step": 139
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.7283653846153846e-05,
      "loss": 0.8019,
      "step": 140
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.7259615384615385e-05,
      "loss": 0.8141,
      "step": 141
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.7235576923076925e-05,
      "loss": 0.7944,
      "step": 142
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.7211538461538465e-05,
      "loss": 0.7697,
      "step": 143
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.71875e-05,
      "loss": 0.8329,
      "step": 144
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.7163461538461537e-05,
      "loss": 0.7871,
      "step": 145
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.7139423076923077e-05,
      "loss": 0.8166,
      "step": 146
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.7115384615384617e-05,
      "loss": 0.8188,
      "step": 147
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.7091346153846156e-05,
      "loss": 0.7407,
      "step": 148
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.7067307692307693e-05,
      "loss": 0.756,
      "step": 149
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.7043269230769232e-05,
      "loss": 0.912,
      "step": 150
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.701923076923077e-05,
      "loss": 0.7864,
      "step": 151
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.699519230769231e-05,
      "loss": 0.7324,
      "step": 152
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.6971153846153848e-05,
      "loss": 0.7955,
      "step": 153
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.6947115384615388e-05,
      "loss": 0.7767,
      "step": 154
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.8461,
      "step": 155
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.6899038461538464e-05,
      "loss": 0.7661,
      "step": 156
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.6875e-05,
      "loss": 0.8027,
      "step": 157
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.685096153846154e-05,
      "loss": 0.7535,
      "step": 158
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.682692307692308e-05,
      "loss": 0.7497,
      "step": 159
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.6802884615384616e-05,
      "loss": 0.8104,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.6778846153846156e-05,
      "loss": 0.7874,
      "step": 161
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.6754807692307692e-05,
      "loss": 0.8582,
      "step": 162
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.673076923076923e-05,
      "loss": 0.8311,
      "step": 163
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.670673076923077e-05,
      "loss": 0.8759,
      "step": 164
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.668269230769231e-05,
      "loss": 0.7448,
      "step": 165
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.6658653846153847e-05,
      "loss": 0.8101,
      "step": 166
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.6634615384615387e-05,
      "loss": 0.7539,
      "step": 167
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.6610576923076923e-05,
      "loss": 0.8119,
      "step": 168
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.6586538461538463e-05,
      "loss": 0.8524,
      "step": 169
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.6562500000000003e-05,
      "loss": 0.774,
      "step": 170
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.653846153846154e-05,
      "loss": 0.7763,
      "step": 171
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.651442307692308e-05,
      "loss": 0.7284,
      "step": 172
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.6490384615384615e-05,
      "loss": 0.7537,
      "step": 173
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.6466346153846155e-05,
      "loss": 0.7166,
      "step": 174
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.6442307692307695e-05,
      "loss": 0.8141,
      "step": 175
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.6418269230769234e-05,
      "loss": 0.7984,
      "step": 176
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.639423076923077e-05,
      "loss": 0.7642,
      "step": 177
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.637019230769231e-05,
      "loss": 0.8379,
      "step": 178
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.6346153846153847e-05,
      "loss": 0.8104,
      "step": 179
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.6322115384615386e-05,
      "loss": 0.7393,
      "step": 180
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.6298076923076923e-05,
      "loss": 0.775,
      "step": 181
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.6274038461538462e-05,
      "loss": 0.8081,
      "step": 182
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.6250000000000002e-05,
      "loss": 0.7168,
      "step": 183
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.6225961538461538e-05,
      "loss": 0.7956,
      "step": 184
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.6201923076923078e-05,
      "loss": 0.7755,
      "step": 185
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.6177884615384614e-05,
      "loss": 0.7293,
      "step": 186
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 0.7713,
      "step": 187
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.6129807692307694e-05,
      "loss": 0.7599,
      "step": 188
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.6105769230769233e-05,
      "loss": 0.7648,
      "step": 189
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.608173076923077e-05,
      "loss": 0.7296,
      "step": 190
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.605769230769231e-05,
      "loss": 0.7411,
      "step": 191
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.6033653846153846e-05,
      "loss": 0.7602,
      "step": 192
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.6009615384615385e-05,
      "loss": 0.7661,
      "step": 193
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.5985576923076925e-05,
      "loss": 0.7468,
      "step": 194
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.5961538461538465e-05,
      "loss": 0.7961,
      "step": 195
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.59375e-05,
      "loss": 0.7311,
      "step": 196
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.5913461538461537e-05,
      "loss": 0.8229,
      "step": 197
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.5889423076923077e-05,
      "loss": 0.7642,
      "step": 198
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.5865384615384617e-05,
      "loss": 0.6928,
      "step": 199
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.5841346153846157e-05,
      "loss": 0.7556,
      "step": 200
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.5817307692307693e-05,
      "loss": 0.814,
      "step": 201
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.5793269230769233e-05,
      "loss": 0.8152,
      "step": 202
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.576923076923077e-05,
      "loss": 0.675,
      "step": 203
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.574519230769231e-05,
      "loss": 0.7087,
      "step": 204
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.5721153846153848e-05,
      "loss": 0.8538,
      "step": 205
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.5697115384615388e-05,
      "loss": 0.8116,
      "step": 206
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.5673076923076924e-05,
      "loss": 0.7346,
      "step": 207
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.5649038461538464e-05,
      "loss": 0.7081,
      "step": 208
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.5625e-05,
      "loss": 0.835,
      "step": 209
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.560096153846154e-05,
      "loss": 0.7269,
      "step": 210
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.557692307692308e-05,
      "loss": 0.7451,
      "step": 211
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.5552884615384616e-05,
      "loss": 0.7725,
      "step": 212
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.5528846153846156e-05,
      "loss": 0.7269,
      "step": 213
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.5504807692307692e-05,
      "loss": 0.7733,
      "step": 214
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.5480769230769232e-05,
      "loss": 0.7684,
      "step": 215
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.545673076923077e-05,
      "loss": 0.7509,
      "step": 216
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.543269230769231e-05,
      "loss": 0.7126,
      "step": 217
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.5408653846153847e-05,
      "loss": 0.7416,
      "step": 218
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.7922,
      "step": 219
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.5360576923076923e-05,
      "loss": 0.7533,
      "step": 220
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.5336538461538463e-05,
      "loss": 0.7549,
      "step": 221
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.5312500000000003e-05,
      "loss": 0.7321,
      "step": 222
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.528846153846154e-05,
      "loss": 0.7941,
      "step": 223
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.526442307692308e-05,
      "loss": 0.7364,
      "step": 224
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.5240384615384615e-05,
      "loss": 0.7847,
      "step": 225
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.5216346153846155e-05,
      "loss": 0.7893,
      "step": 226
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.5192307692307693e-05,
      "loss": 0.7664,
      "step": 227
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.5168269230769233e-05,
      "loss": 0.7136,
      "step": 228
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.514423076923077e-05,
      "loss": 0.7442,
      "step": 229
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.512019230769231e-05,
      "loss": 0.7737,
      "step": 230
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.5096153846153847e-05,
      "loss": 0.7583,
      "step": 231
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.5072115384615386e-05,
      "loss": 0.7817,
      "step": 232
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.5048076923076924e-05,
      "loss": 0.7708,
      "step": 233
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.5024038461538464e-05,
      "loss": 0.7865,
      "step": 234
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7547,
      "step": 235
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.4975961538461538e-05,
      "loss": 0.8063,
      "step": 236
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.4951923076923078e-05,
      "loss": 0.8344,
      "step": 237
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.4927884615384616e-05,
      "loss": 0.7404,
      "step": 238
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.4903846153846156e-05,
      "loss": 0.7797,
      "step": 239
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.4879807692307692e-05,
      "loss": 0.7372,
      "step": 240
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.4855769230769232e-05,
      "loss": 0.764,
      "step": 241
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.483173076923077e-05,
      "loss": 0.8245,
      "step": 242
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.480769230769231e-05,
      "loss": 0.8036,
      "step": 243
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.4783653846153848e-05,
      "loss": 0.7704,
      "step": 244
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.4759615384615387e-05,
      "loss": 0.7686,
      "step": 245
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.4735576923076924e-05,
      "loss": 0.7013,
      "step": 246
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.4711538461538463e-05,
      "loss": 0.712,
      "step": 247
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.4687500000000001e-05,
      "loss": 0.7107,
      "step": 248
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.466346153846154e-05,
      "loss": 0.8375,
      "step": 249
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.4639423076923079e-05,
      "loss": 0.7629,
      "step": 250
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.4615384615384615e-05,
      "loss": 0.7042,
      "step": 251
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.4591346153846155e-05,
      "loss": 0.7676,
      "step": 252
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.4567307692307693e-05,
      "loss": 0.7578,
      "step": 253
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.4543269230769233e-05,
      "loss": 0.7231,
      "step": 254
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.451923076923077e-05,
      "loss": 0.7189,
      "step": 255
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.449519230769231e-05,
      "loss": 0.712,
      "step": 256
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.4471153846153847e-05,
      "loss": 0.7324,
      "step": 257
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.4447115384615386e-05,
      "loss": 0.7761,
      "step": 258
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.4423076923076924e-05,
      "loss": 0.7842,
      "step": 259
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.4399038461538464e-05,
      "loss": 0.7634,
      "step": 260
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.4375e-05,
      "loss": 0.7812,
      "step": 261
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.4350961538461538e-05,
      "loss": 0.8088,
      "step": 262
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.4326923076923078e-05,
      "loss": 0.7412,
      "step": 263
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.4302884615384616e-05,
      "loss": 0.7756,
      "step": 264
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.4278846153846156e-05,
      "loss": 0.7228,
      "step": 265
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.4254807692307692e-05,
      "loss": 0.7834,
      "step": 266
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.4230769230769232e-05,
      "loss": 0.7778,
      "step": 267
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.420673076923077e-05,
      "loss": 0.7891,
      "step": 268
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.418269230769231e-05,
      "loss": 0.7817,
      "step": 269
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.4158653846153848e-05,
      "loss": 0.7471,
      "step": 270
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.4134615384615387e-05,
      "loss": 0.7259,
      "step": 271
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.4110576923076924e-05,
      "loss": 0.7364,
      "step": 272
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.4086538461538463e-05,
      "loss": 0.7308,
      "step": 273
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.4062500000000001e-05,
      "loss": 0.7144,
      "step": 274
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.403846153846154e-05,
      "loss": 0.7699,
      "step": 275
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.4014423076923079e-05,
      "loss": 0.7474,
      "step": 276
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.3990384615384615e-05,
      "loss": 0.7784,
      "step": 277
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.3966346153846155e-05,
      "loss": 0.767,
      "step": 278
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.3942307692307693e-05,
      "loss": 0.7675,
      "step": 279
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.3918269230769233e-05,
      "loss": 0.797,
      "step": 280
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.3894230769230769e-05,
      "loss": 0.7344,
      "step": 281
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.3870192307692309e-05,
      "loss": 0.7731,
      "step": 282
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.8022,
      "step": 283
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.3822115384615386e-05,
      "loss": 0.7794,
      "step": 284
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.3798076923076924e-05,
      "loss": 0.7722,
      "step": 285
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.3774038461538464e-05,
      "loss": 0.6938,
      "step": 286
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.375e-05,
      "loss": 0.7141,
      "step": 287
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.3725961538461538e-05,
      "loss": 0.7139,
      "step": 288
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.3701923076923078e-05,
      "loss": 0.8106,
      "step": 289
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.3677884615384616e-05,
      "loss": 0.6667,
      "step": 290
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.3653846153846156e-05,
      "loss": 0.7822,
      "step": 291
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.3629807692307692e-05,
      "loss": 0.7589,
      "step": 292
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.3605769230769232e-05,
      "loss": 0.7201,
      "step": 293
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.358173076923077e-05,
      "loss": 0.7368,
      "step": 294
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.355769230769231e-05,
      "loss": 0.7426,
      "step": 295
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.3533653846153848e-05,
      "loss": 0.7307,
      "step": 296
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.3509615384615387e-05,
      "loss": 0.7377,
      "step": 297
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.3485576923076924e-05,
      "loss": 0.7529,
      "step": 298
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.3461538461538463e-05,
      "loss": 0.7624,
      "step": 299
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.3437500000000001e-05,
      "loss": 0.7876,
      "step": 300
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.341346153846154e-05,
      "loss": 0.7677,
      "step": 301
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.3389423076923077e-05,
      "loss": 0.7167,
      "step": 302
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.3365384615384615e-05,
      "loss": 0.8006,
      "step": 303
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.3341346153846155e-05,
      "loss": 0.7516,
      "step": 304
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.3317307692307693e-05,
      "loss": 0.7548,
      "step": 305
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.3293269230769233e-05,
      "loss": 0.7375,
      "step": 306
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.3269230769230769e-05,
      "loss": 0.7345,
      "step": 307
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.3245192307692309e-05,
      "loss": 0.7543,
      "step": 308
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.3221153846153847e-05,
      "loss": 0.7948,
      "step": 309
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.3197115384615387e-05,
      "loss": 0.7262,
      "step": 310
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.3173076923076925e-05,
      "loss": 0.7293,
      "step": 311
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.3149038461538464e-05,
      "loss": 0.7145,
      "step": 312
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.3125e-05,
      "loss": 0.7774,
      "step": 313
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.3100961538461539e-05,
      "loss": 0.6981,
      "step": 314
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.3076923076923078e-05,
      "loss": 0.7584,
      "step": 315
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.3052884615384616e-05,
      "loss": 0.7331,
      "step": 316
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.3028846153846156e-05,
      "loss": 0.7757,
      "step": 317
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.3004807692307692e-05,
      "loss": 0.7141,
      "step": 318
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.2980769230769232e-05,
      "loss": 0.7132,
      "step": 319
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.295673076923077e-05,
      "loss": 0.7448,
      "step": 320
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.293269230769231e-05,
      "loss": 0.7303,
      "step": 321
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2908653846153848e-05,
      "loss": 0.7199,
      "step": 322
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2884615384615386e-05,
      "loss": 0.7516,
      "step": 323
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2860576923076924e-05,
      "loss": 0.751,
      "step": 324
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2836538461538463e-05,
      "loss": 0.7613,
      "step": 325
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2812500000000001e-05,
      "loss": 0.7393,
      "step": 326
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2788461538461538e-05,
      "loss": 0.7141,
      "step": 327
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2764423076923077e-05,
      "loss": 0.7178,
      "step": 328
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.2740384615384615e-05,
      "loss": 0.7639,
      "step": 329
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.2716346153846155e-05,
      "loss": 0.7608,
      "step": 330
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.2692307692307693e-05,
      "loss": 0.7455,
      "step": 331
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.2668269230769233e-05,
      "loss": 0.8251,
      "step": 332
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.264423076923077e-05,
      "loss": 0.7024,
      "step": 333
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.2620192307692309e-05,
      "loss": 0.705,
      "step": 334
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.2596153846153847e-05,
      "loss": 0.78,
      "step": 335
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.2572115384615387e-05,
      "loss": 0.7081,
      "step": 336
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.2548076923076925e-05,
      "loss": 0.7023,
      "step": 337
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.2524038461538464e-05,
      "loss": 0.6843,
      "step": 338
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.25e-05,
      "loss": 0.7252,
      "step": 339
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.2475961538461539e-05,
      "loss": 0.7692,
      "step": 340
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.2451923076923078e-05,
      "loss": 0.7538,
      "step": 341
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.2427884615384616e-05,
      "loss": 0.729,
      "step": 342
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.2403846153846156e-05,
      "loss": 0.7547,
      "step": 343
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.2379807692307692e-05,
      "loss": 0.7373,
      "step": 344
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.2355769230769232e-05,
      "loss": 0.7406,
      "step": 345
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.233173076923077e-05,
      "loss": 0.7349,
      "step": 346
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.230769230769231e-05,
      "loss": 0.7707,
      "step": 347
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2283653846153846e-05,
      "loss": 0.739,
      "step": 348
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2259615384615386e-05,
      "loss": 0.6808,
      "step": 349
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2235576923076924e-05,
      "loss": 0.7431,
      "step": 350
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.2211538461538463e-05,
      "loss": 0.7073,
      "step": 351
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.2187500000000001e-05,
      "loss": 0.7251,
      "step": 352
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.2163461538461538e-05,
      "loss": 0.7321,
      "step": 353
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.2139423076923077e-05,
      "loss": 0.7918,
      "step": 354
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.2115384615384615e-05,
      "loss": 0.7374,
      "step": 355
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.2091346153846155e-05,
      "loss": 0.7307,
      "step": 356
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.2067307692307693e-05,
      "loss": 0.7617,
      "step": 357
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.2043269230769233e-05,
      "loss": 0.7808,
      "step": 358
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.201923076923077e-05,
      "loss": 0.6914,
      "step": 359
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.1995192307692309e-05,
      "loss": 0.7304,
      "step": 360
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.1971153846153847e-05,
      "loss": 0.7732,
      "step": 361
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.1947115384615387e-05,
      "loss": 0.8037,
      "step": 362
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1923076923076925e-05,
      "loss": 0.7156,
      "step": 363
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1899038461538464e-05,
      "loss": 0.7605,
      "step": 364
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1875e-05,
      "loss": 0.7682,
      "step": 365
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1850961538461539e-05,
      "loss": 0.7285,
      "step": 366
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1826923076923078e-05,
      "loss": 0.7305,
      "step": 367
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1802884615384615e-05,
      "loss": 0.7585,
      "step": 368
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1778846153846154e-05,
      "loss": 0.7003,
      "step": 369
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1754807692307692e-05,
      "loss": 0.8018,
      "step": 370
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1730769230769232e-05,
      "loss": 0.7473,
      "step": 371
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.170673076923077e-05,
      "loss": 0.6937,
      "step": 372
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.168269230769231e-05,
      "loss": 0.7858,
      "step": 373
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.1658653846153846e-05,
      "loss": 0.7507,
      "step": 374
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.1634615384615386e-05,
      "loss": 0.7397,
      "step": 375
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1610576923076924e-05,
      "loss": 0.7126,
      "step": 376
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1586538461538464e-05,
      "loss": 0.7559,
      "step": 377
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1562500000000002e-05,
      "loss": 0.7407,
      "step": 378
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1538461538461538e-05,
      "loss": 0.723,
      "step": 379
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.1514423076923078e-05,
      "loss": 0.7441,
      "step": 380
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1490384615384616e-05,
      "loss": 0.7533,
      "step": 381
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1466346153846155e-05,
      "loss": 0.7113,
      "step": 382
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1442307692307693e-05,
      "loss": 0.7529,
      "step": 383
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.1418269230769233e-05,
      "loss": 0.7574,
      "step": 384
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.139423076923077e-05,
      "loss": 0.7354,
      "step": 385
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.1370192307692309e-05,
      "loss": 0.7783,
      "step": 386
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.1346153846153847e-05,
      "loss": 0.751,
      "step": 387
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.1322115384615387e-05,
      "loss": 0.7101,
      "step": 388
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.1298076923076923e-05,
      "loss": 0.7462,
      "step": 389
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.1274038461538463e-05,
      "loss": 0.7701,
      "step": 390
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.125e-05,
      "loss": 0.6807,
      "step": 391
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.1225961538461539e-05,
      "loss": 0.7603,
      "step": 392
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.1201923076923078e-05,
      "loss": 0.8018,
      "step": 393
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.1177884615384615e-05,
      "loss": 0.74,
      "step": 394
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.1153846153846154e-05,
      "loss": 0.7039,
      "step": 395
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.1129807692307692e-05,
      "loss": 0.7858,
      "step": 396
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.1105769230769232e-05,
      "loss": 0.7536,
      "step": 397
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.108173076923077e-05,
      "loss": 0.7586,
      "step": 398
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.105769230769231e-05,
      "loss": 0.7555,
      "step": 399
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.1033653846153846e-05,
      "loss": 0.7849,
      "step": 400
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.1009615384615386e-05,
      "loss": 0.7513,
      "step": 401
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.0985576923076924e-05,
      "loss": 0.65,
      "step": 402
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.0961538461538464e-05,
      "loss": 0.7416,
      "step": 403
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.0937500000000002e-05,
      "loss": 0.756,
      "step": 404
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.0913461538461538e-05,
      "loss": 0.7542,
      "step": 405
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0889423076923078e-05,
      "loss": 0.7342,
      "step": 406
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0865384615384616e-05,
      "loss": 0.7155,
      "step": 407
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0841346153846155e-05,
      "loss": 0.7369,
      "step": 408
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0817307692307693e-05,
      "loss": 0.7184,
      "step": 409
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0793269230769231e-05,
      "loss": 0.7084,
      "step": 410
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.076923076923077e-05,
      "loss": 0.7391,
      "step": 411
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0745192307692309e-05,
      "loss": 0.7178,
      "step": 412
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0721153846153847e-05,
      "loss": 0.7261,
      "step": 413
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0697115384615387e-05,
      "loss": 0.7537,
      "step": 414
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.0673076923076923e-05,
      "loss": 0.7419,
      "step": 415
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.0649038461538463e-05,
      "loss": 0.7358,
      "step": 416
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.0625e-05,
      "loss": 0.739,
      "step": 417
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.0600961538461539e-05,
      "loss": 0.7373,
      "step": 418
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0576923076923078e-05,
      "loss": 0.7703,
      "step": 419
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0552884615384615e-05,
      "loss": 0.7557,
      "step": 420
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0528846153846154e-05,
      "loss": 0.7366,
      "step": 421
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0504807692307692e-05,
      "loss": 0.6743,
      "step": 422
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.0480769230769232e-05,
      "loss": 0.7874,
      "step": 423
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.045673076923077e-05,
      "loss": 0.7811,
      "step": 424
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.043269230769231e-05,
      "loss": 0.7395,
      "step": 425
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0408653846153846e-05,
      "loss": 0.7401,
      "step": 426
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0384615384615386e-05,
      "loss": 0.7722,
      "step": 427
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0360576923076924e-05,
      "loss": 0.7654,
      "step": 428
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0336538461538464e-05,
      "loss": 0.7651,
      "step": 429
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0312500000000002e-05,
      "loss": 0.73,
      "step": 430
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0288461538461538e-05,
      "loss": 0.7567,
      "step": 431
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.0264423076923078e-05,
      "loss": 0.7413,
      "step": 432
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.0240384615384616e-05,
      "loss": 0.7285,
      "step": 433
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.0216346153846155e-05,
      "loss": 0.69,
      "step": 434
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.0192307692307692e-05,
      "loss": 0.7651,
      "step": 435
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.0168269230769231e-05,
      "loss": 0.7404,
      "step": 436
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.014423076923077e-05,
      "loss": 0.7434,
      "step": 437
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.0120192307692309e-05,
      "loss": 0.6984,
      "step": 438
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.0096153846153847e-05,
      "loss": 0.7156,
      "step": 439
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.0072115384615387e-05,
      "loss": 0.7799,
      "step": 440
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.0048076923076923e-05,
      "loss": 0.7473,
      "step": 441
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.0024038461538463e-05,
      "loss": 0.7358,
      "step": 442
    },
    {
      "epoch": 1.03,
      "learning_rate": 1e-05,
      "loss": 0.7247,
      "step": 443
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.975961538461539e-06,
      "loss": 0.7319,
      "step": 444
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.951923076923079e-06,
      "loss": 0.6721,
      "step": 445
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.927884615384617e-06,
      "loss": 0.8221,
      "step": 446
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.903846153846155e-06,
      "loss": 0.72,
      "step": 447
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.879807692307694e-06,
      "loss": 0.7089,
      "step": 448
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.855769230769232e-06,
      "loss": 0.7289,
      "step": 449
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.83173076923077e-06,
      "loss": 0.7794,
      "step": 450
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.807692307692308e-06,
      "loss": 0.7308,
      "step": 451
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.783653846153846e-06,
      "loss": 0.7457,
      "step": 452
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.759615384615386e-06,
      "loss": 0.7448,
      "step": 453
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.735576923076924e-06,
      "loss": 0.7417,
      "step": 454
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.711538461538462e-06,
      "loss": 0.7325,
      "step": 455
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.6875e-06,
      "loss": 0.7704,
      "step": 456
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.66346153846154e-06,
      "loss": 0.6973,
      "step": 457
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.639423076923078e-06,
      "loss": 0.7703,
      "step": 458
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.615384615384616e-06,
      "loss": 0.7423,
      "step": 459
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.591346153846155e-06,
      "loss": 0.7002,
      "step": 460
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.567307692307693e-06,
      "loss": 0.7644,
      "step": 461
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.543269230769231e-06,
      "loss": 0.7497,
      "step": 462
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.51923076923077e-06,
      "loss": 0.7316,
      "step": 463
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.495192307692307e-06,
      "loss": 0.6952,
      "step": 464
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.471153846153847e-06,
      "loss": 0.775,
      "step": 465
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.447115384615385e-06,
      "loss": 0.7371,
      "step": 466
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.423076923076923e-06,
      "loss": 0.7166,
      "step": 467
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.399038461538463e-06,
      "loss": 0.7809,
      "step": 468
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.375000000000001e-06,
      "loss": 0.7148,
      "step": 469
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.350961538461539e-06,
      "loss": 0.7366,
      "step": 470
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.326923076923079e-06,
      "loss": 0.7409,
      "step": 471
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.302884615384617e-06,
      "loss": 0.7558,
      "step": 472
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.278846153846155e-06,
      "loss": 0.7338,
      "step": 473
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.254807692307694e-06,
      "loss": 0.7505,
      "step": 474
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.230769230769232e-06,
      "loss": 0.7089,
      "step": 475
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.20673076923077e-06,
      "loss": 0.7557,
      "step": 476
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.182692307692308e-06,
      "loss": 0.8059,
      "step": 477
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.158653846153846e-06,
      "loss": 0.7504,
      "step": 478
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.134615384615384e-06,
      "loss": 0.7513,
      "step": 479
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.110576923076924e-06,
      "loss": 0.7469,
      "step": 480
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.086538461538462e-06,
      "loss": 0.7118,
      "step": 481
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.0625e-06,
      "loss": 0.7009,
      "step": 482
    },
    {
      "epoch": 1.12,
      "learning_rate": 9.03846153846154e-06,
      "loss": 0.7326,
      "step": 483
    },
    {
      "epoch": 1.13,
      "learning_rate": 9.014423076923078e-06,
      "loss": 0.6924,
      "step": 484
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.990384615384616e-06,
      "loss": 0.7207,
      "step": 485
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.966346153846155e-06,
      "loss": 0.7436,
      "step": 486
    },
    {
      "epoch": 1.13,
      "learning_rate": 8.942307692307693e-06,
      "loss": 0.6856,
      "step": 487
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.918269230769231e-06,
      "loss": 0.7208,
      "step": 488
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.89423076923077e-06,
      "loss": 0.7459,
      "step": 489
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.870192307692308e-06,
      "loss": 0.7393,
      "step": 490
    },
    {
      "epoch": 1.14,
      "learning_rate": 8.846153846153847e-06,
      "loss": 0.8019,
      "step": 491
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.822115384615385e-06,
      "loss": 0.7082,
      "step": 492
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.798076923076923e-06,
      "loss": 0.7403,
      "step": 493
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.774038461538463e-06,
      "loss": 0.7694,
      "step": 494
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.750000000000001e-06,
      "loss": 0.7232,
      "step": 495
    },
    {
      "epoch": 1.15,
      "learning_rate": 8.725961538461539e-06,
      "loss": 0.7255,
      "step": 496
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.701923076923079e-06,
      "loss": 0.7256,
      "step": 497
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.677884615384617e-06,
      "loss": 0.7222,
      "step": 498
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.653846153846155e-06,
      "loss": 0.7491,
      "step": 499
    },
    {
      "epoch": 1.16,
      "learning_rate": 8.629807692307693e-06,
      "loss": 0.7845,
      "step": 500
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.605769230769232e-06,
      "loss": 0.7759,
      "step": 501
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.581730769230769e-06,
      "loss": 0.7304,
      "step": 502
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.557692307692308e-06,
      "loss": 0.6939,
      "step": 503
    },
    {
      "epoch": 1.17,
      "learning_rate": 8.533653846153846e-06,
      "loss": 0.7838,
      "step": 504
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.509615384615384e-06,
      "loss": 0.6693,
      "step": 505
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.485576923076924e-06,
      "loss": 0.727,
      "step": 506
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.461538461538462e-06,
      "loss": 0.7153,
      "step": 507
    },
    {
      "epoch": 1.18,
      "learning_rate": 8.4375e-06,
      "loss": 0.8066,
      "step": 508
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.41346153846154e-06,
      "loss": 0.7349,
      "step": 509
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.389423076923078e-06,
      "loss": 0.6531,
      "step": 510
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.365384615384616e-06,
      "loss": 0.7391,
      "step": 511
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.341346153846156e-06,
      "loss": 0.7599,
      "step": 512
    },
    {
      "epoch": 1.19,
      "learning_rate": 8.317307692307694e-06,
      "loss": 0.7264,
      "step": 513
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.293269230769232e-06,
      "loss": 0.7751,
      "step": 514
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.26923076923077e-06,
      "loss": 0.7816,
      "step": 515
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.245192307692308e-06,
      "loss": 0.6606,
      "step": 516
    },
    {
      "epoch": 1.2,
      "learning_rate": 8.221153846153847e-06,
      "loss": 0.7694,
      "step": 517
    },
    {
      "epoch": 1.21,
      "learning_rate": 8.197115384615385e-06,
      "loss": 0.7568,
      "step": 518
    },
    {
      "epoch": 1.21,
      "learning_rate": 8.173076923076923e-06,
      "loss": 0.746,
      "step": 519
    },
    {
      "epoch": 1.21,
      "learning_rate": 8.149038461538461e-06,
      "loss": 0.6413,
      "step": 520
    },
    {
      "epoch": 1.21,
      "learning_rate": 8.125000000000001e-06,
      "loss": 0.7307,
      "step": 521
    },
    {
      "epoch": 1.22,
      "learning_rate": 8.100961538461539e-06,
      "loss": 0.6971,
      "step": 522
    },
    {
      "epoch": 1.22,
      "learning_rate": 8.076923076923077e-06,
      "loss": 0.7328,
      "step": 523
    },
    {
      "epoch": 1.22,
      "learning_rate": 8.052884615384617e-06,
      "loss": 0.6639,
      "step": 524
    },
    {
      "epoch": 1.22,
      "learning_rate": 8.028846153846155e-06,
      "loss": 0.7407,
      "step": 525
    },
    {
      "epoch": 1.22,
      "learning_rate": 8.004807692307693e-06,
      "loss": 0.7541,
      "step": 526
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.980769230769232e-06,
      "loss": 0.7097,
      "step": 527
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.956730769230769e-06,
      "loss": 0.7716,
      "step": 528
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.932692307692308e-06,
      "loss": 0.7859,
      "step": 529
    },
    {
      "epoch": 1.23,
      "learning_rate": 7.908653846153846e-06,
      "loss": 0.7683,
      "step": 530
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.884615384615384e-06,
      "loss": 0.8176,
      "step": 531
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.860576923076924e-06,
      "loss": 0.8056,
      "step": 532
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.836538461538462e-06,
      "loss": 0.6425,
      "step": 533
    },
    {
      "epoch": 1.24,
      "learning_rate": 7.8125e-06,
      "loss": 0.7543,
      "step": 534
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.78846153846154e-06,
      "loss": 0.8141,
      "step": 535
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.764423076923078e-06,
      "loss": 0.7276,
      "step": 536
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.740384615384616e-06,
      "loss": 0.7059,
      "step": 537
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.716346153846156e-06,
      "loss": 0.7562,
      "step": 538
    },
    {
      "epoch": 1.25,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.7004,
      "step": 539
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.668269230769232e-06,
      "loss": 0.7087,
      "step": 540
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.64423076923077e-06,
      "loss": 0.7128,
      "step": 541
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.620192307692308e-06,
      "loss": 0.7745,
      "step": 542
    },
    {
      "epoch": 1.26,
      "learning_rate": 7.5961538461538465e-06,
      "loss": 0.7134,
      "step": 543
    },
    {
      "epoch": 1.27,
      "learning_rate": 7.572115384615385e-06,
      "loss": 0.7305,
      "step": 544
    },
    {
      "epoch": 1.27,
      "learning_rate": 7.548076923076923e-06,
      "loss": 0.7197,
      "step": 545
    },
    {
      "epoch": 1.27,
      "learning_rate": 7.524038461538462e-06,
      "loss": 0.6959,
      "step": 546
    },
    {
      "epoch": 1.27,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.7369,
      "step": 547
    },
    {
      "epoch": 1.28,
      "learning_rate": 7.475961538461539e-06,
      "loss": 0.7657,
      "step": 548
    },
    {
      "epoch": 1.28,
      "learning_rate": 7.451923076923078e-06,
      "loss": 0.704,
      "step": 549
    },
    {
      "epoch": 1.28,
      "learning_rate": 7.427884615384616e-06,
      "loss": 0.7452,
      "step": 550
    },
    {
      "epoch": 1.28,
      "learning_rate": 7.403846153846155e-06,
      "loss": 0.8127,
      "step": 551
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.379807692307694e-06,
      "loss": 0.7347,
      "step": 552
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.355769230769232e-06,
      "loss": 0.765,
      "step": 553
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.33173076923077e-06,
      "loss": 0.7523,
      "step": 554
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.307692307692308e-06,
      "loss": 0.7356,
      "step": 555
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.2836538461538465e-06,
      "loss": 0.7551,
      "step": 556
    },
    {
      "epoch": 1.3,
      "learning_rate": 7.259615384615385e-06,
      "loss": 0.7478,
      "step": 557
    },
    {
      "epoch": 1.3,
      "learning_rate": 7.235576923076923e-06,
      "loss": 0.764,
      "step": 558
    },
    {
      "epoch": 1.3,
      "learning_rate": 7.211538461538462e-06,
      "loss": 0.7545,
      "step": 559
    },
    {
      "epoch": 1.3,
      "learning_rate": 7.1875e-06,
      "loss": 0.7908,
      "step": 560
    },
    {
      "epoch": 1.31,
      "learning_rate": 7.163461538461539e-06,
      "loss": 0.6474,
      "step": 561
    },
    {
      "epoch": 1.31,
      "learning_rate": 7.139423076923078e-06,
      "loss": 0.7521,
      "step": 562
    },
    {
      "epoch": 1.31,
      "learning_rate": 7.115384615384616e-06,
      "loss": 0.6777,
      "step": 563
    },
    {
      "epoch": 1.31,
      "learning_rate": 7.091346153846155e-06,
      "loss": 0.7018,
      "step": 564
    },
    {
      "epoch": 1.32,
      "learning_rate": 7.067307692307694e-06,
      "loss": 0.6937,
      "step": 565
    },
    {
      "epoch": 1.32,
      "learning_rate": 7.043269230769232e-06,
      "loss": 0.7547,
      "step": 566
    },
    {
      "epoch": 1.32,
      "learning_rate": 7.01923076923077e-06,
      "loss": 0.6753,
      "step": 567
    },
    {
      "epoch": 1.32,
      "learning_rate": 6.995192307692308e-06,
      "loss": 0.7114,
      "step": 568
    },
    {
      "epoch": 1.32,
      "learning_rate": 6.9711538461538465e-06,
      "loss": 0.7267,
      "step": 569
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.9471153846153845e-06,
      "loss": 0.7327,
      "step": 570
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.923076923076923e-06,
      "loss": 0.8159,
      "step": 571
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.899038461538462e-06,
      "loss": 0.7367,
      "step": 572
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.875e-06,
      "loss": 0.7001,
      "step": 573
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.850961538461539e-06,
      "loss": 0.7023,
      "step": 574
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.826923076923078e-06,
      "loss": 0.7887,
      "step": 575
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.802884615384616e-06,
      "loss": 0.7033,
      "step": 576
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.778846153846155e-06,
      "loss": 0.7066,
      "step": 577
    },
    {
      "epoch": 1.35,
      "learning_rate": 6.754807692307694e-06,
      "loss": 0.7609,
      "step": 578
    },
    {
      "epoch": 1.35,
      "learning_rate": 6.730769230769232e-06,
      "loss": 0.772,
      "step": 579
    },
    {
      "epoch": 1.35,
      "learning_rate": 6.70673076923077e-06,
      "loss": 0.7014,
      "step": 580
    },
    {
      "epoch": 1.35,
      "learning_rate": 6.682692307692308e-06,
      "loss": 0.7289,
      "step": 581
    },
    {
      "epoch": 1.36,
      "learning_rate": 6.6586538461538465e-06,
      "loss": 0.7272,
      "step": 582
    },
    {
      "epoch": 1.36,
      "learning_rate": 6.6346153846153846e-06,
      "loss": 0.7183,
      "step": 583
    },
    {
      "epoch": 1.36,
      "learning_rate": 6.610576923076923e-06,
      "loss": 0.7195,
      "step": 584
    },
    {
      "epoch": 1.36,
      "learning_rate": 6.586538461538462e-06,
      "loss": 0.7047,
      "step": 585
    },
    {
      "epoch": 1.36,
      "learning_rate": 6.5625e-06,
      "loss": 0.7635,
      "step": 586
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.538461538461539e-06,
      "loss": 0.7532,
      "step": 587
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.514423076923078e-06,
      "loss": 0.7432,
      "step": 588
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.490384615384616e-06,
      "loss": 0.7372,
      "step": 589
    },
    {
      "epoch": 1.37,
      "learning_rate": 6.466346153846155e-06,
      "loss": 0.7202,
      "step": 590
    },
    {
      "epoch": 1.38,
      "learning_rate": 6.442307692307693e-06,
      "loss": 0.6896,
      "step": 591
    },
    {
      "epoch": 1.38,
      "learning_rate": 6.418269230769232e-06,
      "loss": 0.7469,
      "step": 592
    },
    {
      "epoch": 1.38,
      "learning_rate": 6.394230769230769e-06,
      "loss": 0.663,
      "step": 593
    },
    {
      "epoch": 1.38,
      "learning_rate": 6.370192307692308e-06,
      "loss": 0.707,
      "step": 594
    },
    {
      "epoch": 1.39,
      "learning_rate": 6.3461538461538466e-06,
      "loss": 0.8043,
      "step": 595
    },
    {
      "epoch": 1.39,
      "learning_rate": 6.322115384615385e-06,
      "loss": 0.7627,
      "step": 596
    },
    {
      "epoch": 1.39,
      "learning_rate": 6.2980769230769234e-06,
      "loss": 0.7414,
      "step": 597
    },
    {
      "epoch": 1.39,
      "learning_rate": 6.274038461538462e-06,
      "loss": 0.7033,
      "step": 598
    },
    {
      "epoch": 1.39,
      "learning_rate": 6.25e-06,
      "loss": 0.6933,
      "step": 599
    },
    {
      "epoch": 1.4,
      "learning_rate": 6.225961538461539e-06,
      "loss": 0.6782,
      "step": 600
    },
    {
      "epoch": 1.4,
      "learning_rate": 6.201923076923078e-06,
      "loss": 0.7487,
      "step": 601
    },
    {
      "epoch": 1.4,
      "learning_rate": 6.177884615384616e-06,
      "loss": 0.7744,
      "step": 602
    },
    {
      "epoch": 1.4,
      "learning_rate": 6.153846153846155e-06,
      "loss": 0.7049,
      "step": 603
    },
    {
      "epoch": 1.41,
      "learning_rate": 6.129807692307693e-06,
      "loss": 0.7783,
      "step": 604
    },
    {
      "epoch": 1.41,
      "learning_rate": 6.105769230769232e-06,
      "loss": 0.7084,
      "step": 605
    },
    {
      "epoch": 1.41,
      "learning_rate": 6.081730769230769e-06,
      "loss": 0.7595,
      "step": 606
    },
    {
      "epoch": 1.41,
      "learning_rate": 6.057692307692308e-06,
      "loss": 0.702,
      "step": 607
    },
    {
      "epoch": 1.42,
      "learning_rate": 6.033653846153847e-06,
      "loss": 0.7654,
      "step": 608
    },
    {
      "epoch": 1.42,
      "learning_rate": 6.009615384615385e-06,
      "loss": 0.7016,
      "step": 609
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.9855769230769235e-06,
      "loss": 0.7886,
      "step": 610
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.961538461538462e-06,
      "loss": 0.7261,
      "step": 611
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.9375e-06,
      "loss": 0.712,
      "step": 612
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.913461538461539e-06,
      "loss": 0.768,
      "step": 613
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.889423076923077e-06,
      "loss": 0.7186,
      "step": 614
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.865384615384616e-06,
      "loss": 0.7065,
      "step": 615
    },
    {
      "epoch": 1.43,
      "learning_rate": 5.841346153846155e-06,
      "loss": 0.7522,
      "step": 616
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.817307692307693e-06,
      "loss": 0.7611,
      "step": 617
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.793269230769232e-06,
      "loss": 0.7253,
      "step": 618
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.769230769230769e-06,
      "loss": 0.834,
      "step": 619
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.745192307692308e-06,
      "loss": 0.7598,
      "step": 620
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.721153846153847e-06,
      "loss": 0.7296,
      "step": 621
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.697115384615385e-06,
      "loss": 0.7471,
      "step": 622
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.6730769230769235e-06,
      "loss": 0.7268,
      "step": 623
    },
    {
      "epoch": 1.45,
      "learning_rate": 5.6490384615384615e-06,
      "loss": 0.7534,
      "step": 624
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.625e-06,
      "loss": 0.7715,
      "step": 625
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.600961538461539e-06,
      "loss": 0.6664,
      "step": 626
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.576923076923077e-06,
      "loss": 0.747,
      "step": 627
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.552884615384616e-06,
      "loss": 0.8049,
      "step": 628
    },
    {
      "epoch": 1.46,
      "learning_rate": 5.528846153846155e-06,
      "loss": 0.7335,
      "step": 629
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.504807692307693e-06,
      "loss": 0.6928,
      "step": 630
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.480769230769232e-06,
      "loss": 0.7788,
      "step": 631
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.456730769230769e-06,
      "loss": 0.6739,
      "step": 632
    },
    {
      "epoch": 1.47,
      "learning_rate": 5.432692307692308e-06,
      "loss": 0.7819,
      "step": 633
    },
    {
      "epoch": 1.48,
      "learning_rate": 5.408653846153847e-06,
      "loss": 0.7333,
      "step": 634
    },
    {
      "epoch": 1.48,
      "learning_rate": 5.384615384615385e-06,
      "loss": 0.7469,
      "step": 635
    },
    {
      "epoch": 1.48,
      "learning_rate": 5.3605769230769235e-06,
      "loss": 0.7061,
      "step": 636
    },
    {
      "epoch": 1.48,
      "learning_rate": 5.3365384615384615e-06,
      "loss": 0.7084,
      "step": 637
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.3125e-06,
      "loss": 0.6951,
      "step": 638
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.288461538461539e-06,
      "loss": 0.7814,
      "step": 639
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.264423076923077e-06,
      "loss": 0.7085,
      "step": 640
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.240384615384616e-06,
      "loss": 0.7496,
      "step": 641
    },
    {
      "epoch": 1.49,
      "learning_rate": 5.216346153846155e-06,
      "loss": 0.7385,
      "step": 642
    },
    {
      "epoch": 1.5,
      "learning_rate": 5.192307692307693e-06,
      "loss": 0.7093,
      "step": 643
    },
    {
      "epoch": 1.5,
      "learning_rate": 5.168269230769232e-06,
      "loss": 0.6752,
      "step": 644
    },
    {
      "epoch": 1.5,
      "learning_rate": 5.144230769230769e-06,
      "loss": 0.7053,
      "step": 645
    },
    {
      "epoch": 1.5,
      "learning_rate": 5.120192307692308e-06,
      "loss": 0.7715,
      "step": 646
    },
    {
      "epoch": 1.51,
      "learning_rate": 5.096153846153846e-06,
      "loss": 0.7235,
      "step": 647
    },
    {
      "epoch": 1.51,
      "learning_rate": 5.072115384615385e-06,
      "loss": 0.7547,
      "step": 648
    },
    {
      "epoch": 1.51,
      "learning_rate": 5.0480769230769235e-06,
      "loss": 0.7393,
      "step": 649
    },
    {
      "epoch": 1.51,
      "learning_rate": 5.0240384615384616e-06,
      "loss": 0.7762,
      "step": 650
    },
    {
      "epoch": 1.52,
      "learning_rate": 5e-06,
      "loss": 0.6762,
      "step": 651
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.975961538461539e-06,
      "loss": 0.6965,
      "step": 652
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.951923076923077e-06,
      "loss": 0.7459,
      "step": 653
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.927884615384616e-06,
      "loss": 0.7735,
      "step": 654
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.903846153846154e-06,
      "loss": 0.7614,
      "step": 655
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.879807692307693e-06,
      "loss": 0.7235,
      "step": 656
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.855769230769231e-06,
      "loss": 0.7244,
      "step": 657
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.83173076923077e-06,
      "loss": 0.6837,
      "step": 658
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.807692307692308e-06,
      "loss": 0.7142,
      "step": 659
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.783653846153847e-06,
      "loss": 0.7137,
      "step": 660
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.759615384615385e-06,
      "loss": 0.793,
      "step": 661
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.7355769230769236e-06,
      "loss": 0.7491,
      "step": 662
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.711538461538462e-06,
      "loss": 0.7208,
      "step": 663
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.6875000000000004e-06,
      "loss": 0.7695,
      "step": 664
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.663461538461539e-06,
      "loss": 0.7025,
      "step": 665
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.639423076923077e-06,
      "loss": 0.7709,
      "step": 666
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.7231,
      "step": 667
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.591346153846154e-06,
      "loss": 0.7089,
      "step": 668
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.567307692307692e-06,
      "loss": 0.7847,
      "step": 669
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.543269230769231e-06,
      "loss": 0.7278,
      "step": 670
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.51923076923077e-06,
      "loss": 0.7408,
      "step": 671
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.495192307692308e-06,
      "loss": 0.6999,
      "step": 672
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.471153846153847e-06,
      "loss": 0.7176,
      "step": 673
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.447115384615385e-06,
      "loss": 0.7011,
      "step": 674
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.423076923076924e-06,
      "loss": 0.7319,
      "step": 675
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.399038461538462e-06,
      "loss": 0.7415,
      "step": 676
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.3750000000000005e-06,
      "loss": 0.6948,
      "step": 677
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.350961538461539e-06,
      "loss": 0.6702,
      "step": 678
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.326923076923077e-06,
      "loss": 0.6973,
      "step": 679
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.302884615384616e-06,
      "loss": 0.712,
      "step": 680
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.278846153846154e-06,
      "loss": 0.7413,
      "step": 681
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.254807692307692e-06,
      "loss": 0.6852,
      "step": 682
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.230769230769231e-06,
      "loss": 0.7531,
      "step": 683
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.20673076923077e-06,
      "loss": 0.6617,
      "step": 684
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.182692307692308e-06,
      "loss": 0.7335,
      "step": 685
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.158653846153847e-06,
      "loss": 0.7174,
      "step": 686
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.134615384615385e-06,
      "loss": 0.6879,
      "step": 687
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.110576923076924e-06,
      "loss": 0.7348,
      "step": 688
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.086538461538462e-06,
      "loss": 0.7413,
      "step": 689
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.0625000000000005e-06,
      "loss": 0.7522,
      "step": 690
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.0384615384615385e-06,
      "loss": 0.7668,
      "step": 691
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.014423076923077e-06,
      "loss": 0.8087,
      "step": 692
    },
    {
      "epoch": 1.61,
      "learning_rate": 3.990384615384616e-06,
      "loss": 0.6655,
      "step": 693
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.966346153846154e-06,
      "loss": 0.6891,
      "step": 694
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.942307692307692e-06,
      "loss": 0.7042,
      "step": 695
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.918269230769231e-06,
      "loss": 0.7726,
      "step": 696
    },
    {
      "epoch": 1.62,
      "learning_rate": 3.89423076923077e-06,
      "loss": 0.7435,
      "step": 697
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.870192307692308e-06,
      "loss": 0.7504,
      "step": 698
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.7441,
      "step": 699
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.822115384615385e-06,
      "loss": 0.7076,
      "step": 700
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.7980769230769232e-06,
      "loss": 0.7128,
      "step": 701
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.7740384615384617e-06,
      "loss": 0.728,
      "step": 702
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.7769,
      "step": 703
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.725961538461539e-06,
      "loss": 0.7213,
      "step": 704
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.7019230769230774e-06,
      "loss": 0.7045,
      "step": 705
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.677884615384616e-06,
      "loss": 0.7975,
      "step": 706
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.653846153846154e-06,
      "loss": 0.7291,
      "step": 707
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.6298076923076927e-06,
      "loss": 0.7165,
      "step": 708
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.605769230769231e-06,
      "loss": 0.7053,
      "step": 709
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.5817307692307695e-06,
      "loss": 0.726,
      "step": 710
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.557692307692308e-06,
      "loss": 0.6997,
      "step": 711
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.533653846153847e-06,
      "loss": 0.7519,
      "step": 712
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.509615384615385e-06,
      "loss": 0.7029,
      "step": 713
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.4855769230769233e-06,
      "loss": 0.7855,
      "step": 714
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.4615384615384617e-06,
      "loss": 0.7331,
      "step": 715
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.4375e-06,
      "loss": 0.7491,
      "step": 716
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.413461538461539e-06,
      "loss": 0.7336,
      "step": 717
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.3894230769230774e-06,
      "loss": 0.6901,
      "step": 718
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.365384615384616e-06,
      "loss": 0.7543,
      "step": 719
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.341346153846154e-06,
      "loss": 0.7013,
      "step": 720
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.3173076923076923e-06,
      "loss": 0.7916,
      "step": 721
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.293269230769231e-06,
      "loss": 0.6932,
      "step": 722
    },
    {
      "epoch": 1.68,
      "learning_rate": 3.2692307692307696e-06,
      "loss": 0.7266,
      "step": 723
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.245192307692308e-06,
      "loss": 0.7365,
      "step": 724
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.2211538461538464e-06,
      "loss": 0.7516,
      "step": 725
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.1971153846153844e-06,
      "loss": 0.7308,
      "step": 726
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.1730769230769233e-06,
      "loss": 0.7482,
      "step": 727
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.1490384615384617e-06,
      "loss": 0.7247,
      "step": 728
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.125e-06,
      "loss": 0.7203,
      "step": 729
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.100961538461539e-06,
      "loss": 0.7611,
      "step": 730
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 0.7104,
      "step": 731
    },
    {
      "epoch": 1.7,
      "learning_rate": 3.052884615384616e-06,
      "loss": 0.704,
      "step": 732
    },
    {
      "epoch": 1.71,
      "learning_rate": 3.028846153846154e-06,
      "loss": 0.7557,
      "step": 733
    },
    {
      "epoch": 1.71,
      "learning_rate": 3.0048076923076923e-06,
      "loss": 0.7174,
      "step": 734
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.980769230769231e-06,
      "loss": 0.7241,
      "step": 735
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.9567307692307696e-06,
      "loss": 0.7018,
      "step": 736
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.932692307692308e-06,
      "loss": 0.7,
      "step": 737
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.9086538461538465e-06,
      "loss": 0.7544,
      "step": 738
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.8846153846153845e-06,
      "loss": 0.6733,
      "step": 739
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.8605769230769233e-06,
      "loss": 0.668,
      "step": 740
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.8365384615384617e-06,
      "loss": 0.7321,
      "step": 741
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.8125e-06,
      "loss": 0.7008,
      "step": 742
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.7884615384615386e-06,
      "loss": 0.7344,
      "step": 743
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.7644230769230775e-06,
      "loss": 0.782,
      "step": 744
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.740384615384616e-06,
      "loss": 0.7277,
      "step": 745
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.716346153846154e-06,
      "loss": 0.7396,
      "step": 746
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.6923076923076923e-06,
      "loss": 0.7626,
      "step": 747
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.6682692307692308e-06,
      "loss": 0.7108,
      "step": 748
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.6442307692307696e-06,
      "loss": 0.7246,
      "step": 749
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.620192307692308e-06,
      "loss": 0.6997,
      "step": 750
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.5961538461538465e-06,
      "loss": 0.6956,
      "step": 751
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.5721153846153845e-06,
      "loss": 0.6799,
      "step": 752
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.548076923076923e-06,
      "loss": 0.7581,
      "step": 753
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.5240384615384618e-06,
      "loss": 0.6765,
      "step": 754
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.5e-06,
      "loss": 0.7695,
      "step": 755
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.4759615384615386e-06,
      "loss": 0.6721,
      "step": 756
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.451923076923077e-06,
      "loss": 0.6641,
      "step": 757
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.4278846153846155e-06,
      "loss": 0.7327,
      "step": 758
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.403846153846154e-06,
      "loss": 0.7459,
      "step": 759
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.3798076923076924e-06,
      "loss": 0.7117,
      "step": 760
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.355769230769231e-06,
      "loss": 0.7001,
      "step": 761
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.3317307692307696e-06,
      "loss": 0.7134,
      "step": 762
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.307692307692308e-06,
      "loss": 0.725,
      "step": 763
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.283653846153846e-06,
      "loss": 0.7492,
      "step": 764
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.259615384615385e-06,
      "loss": 0.7317,
      "step": 765
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.2355769230769234e-06,
      "loss": 0.7042,
      "step": 766
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.211538461538462e-06,
      "loss": 0.7401,
      "step": 767
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.1875000000000002e-06,
      "loss": 0.7896,
      "step": 768
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.1634615384615387e-06,
      "loss": 0.7735,
      "step": 769
    },
    {
      "epoch": 1.79,
      "learning_rate": 2.139423076923077e-06,
      "loss": 0.755,
      "step": 770
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.1153846153846155e-06,
      "loss": 0.6535,
      "step": 771
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.091346153846154e-06,
      "loss": 0.7115,
      "step": 772
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.0673076923076924e-06,
      "loss": 0.738,
      "step": 773
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.043269230769231e-06,
      "loss": 0.7527,
      "step": 774
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.0192307692307692e-06,
      "loss": 0.6896,
      "step": 775
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.995192307692308e-06,
      "loss": 0.6956,
      "step": 776
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.971153846153846e-06,
      "loss": 0.7307,
      "step": 777
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.947115384615385e-06,
      "loss": 0.6916,
      "step": 778
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 0.7192,
      "step": 779
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.8990384615384616e-06,
      "loss": 0.731,
      "step": 780
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.8750000000000003e-06,
      "loss": 0.6862,
      "step": 781
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.8509615384615387e-06,
      "loss": 0.6842,
      "step": 782
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.826923076923077e-06,
      "loss": 0.7115,
      "step": 783
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.8028846153846156e-06,
      "loss": 0.7259,
      "step": 784
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.778846153846154e-06,
      "loss": 0.7035,
      "step": 785
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.7548076923076924e-06,
      "loss": 0.7665,
      "step": 786
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.7307692307692308e-06,
      "loss": 0.7068,
      "step": 787
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.7067307692307695e-06,
      "loss": 0.7142,
      "step": 788
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.682692307692308e-06,
      "loss": 0.7128,
      "step": 789
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.6586538461538461e-06,
      "loss": 0.811,
      "step": 790
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.6346153846153848e-06,
      "loss": 0.7538,
      "step": 791
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.6105769230769232e-06,
      "loss": 0.7396,
      "step": 792
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.5865384615384616e-06,
      "loss": 0.7484,
      "step": 793
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.5625e-06,
      "loss": 0.7008,
      "step": 794
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.7069,
      "step": 795
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.514423076923077e-06,
      "loss": 0.7385,
      "step": 796
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.4903846153846156e-06,
      "loss": 0.7283,
      "step": 797
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.466346153846154e-06,
      "loss": 0.7702,
      "step": 798
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.4423076923076922e-06,
      "loss": 0.6993,
      "step": 799
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.4182692307692309e-06,
      "loss": 0.7355,
      "step": 800
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.3942307692307693e-06,
      "loss": 0.7598,
      "step": 801
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.370192307692308e-06,
      "loss": 0.7578,
      "step": 802
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.3461538461538462e-06,
      "loss": 0.6848,
      "step": 803
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.3221153846153848e-06,
      "loss": 0.7129,
      "step": 804
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.2980769230769232e-06,
      "loss": 0.7557,
      "step": 805
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.2740384615384615e-06,
      "loss": 0.718,
      "step": 806
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.25e-06,
      "loss": 0.7332,
      "step": 807
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.2259615384615385e-06,
      "loss": 0.6985,
      "step": 808
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.201923076923077e-06,
      "loss": 0.7342,
      "step": 809
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.1778846153846154e-06,
      "loss": 0.7681,
      "step": 810
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.153846153846154e-06,
      "loss": 0.6903,
      "step": 811
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.1298076923076925e-06,
      "loss": 0.6801,
      "step": 812
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.105769230769231e-06,
      "loss": 0.7243,
      "step": 813
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.0817307692307693e-06,
      "loss": 0.6756,
      "step": 814
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.0576923076923078e-06,
      "loss": 0.6777,
      "step": 815
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.0336538461538462e-06,
      "loss": 0.7568,
      "step": 816
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.0096153846153846e-06,
      "loss": 0.7401,
      "step": 817
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.85576923076923e-07,
      "loss": 0.6894,
      "step": 818
    },
    {
      "epoch": 1.91,
      "learning_rate": 9.615384615384617e-07,
      "loss": 0.8246,
      "step": 819
    },
    {
      "epoch": 1.91,
      "learning_rate": 9.375000000000001e-07,
      "loss": 0.699,
      "step": 820
    },
    {
      "epoch": 1.91,
      "learning_rate": 9.134615384615385e-07,
      "loss": 0.7872,
      "step": 821
    },
    {
      "epoch": 1.91,
      "learning_rate": 8.89423076923077e-07,
      "loss": 0.6746,
      "step": 822
    },
    {
      "epoch": 1.92,
      "learning_rate": 8.653846153846154e-07,
      "loss": 0.7123,
      "step": 823
    },
    {
      "epoch": 1.92,
      "learning_rate": 8.41346153846154e-07,
      "loss": 0.6976,
      "step": 824
    },
    {
      "epoch": 1.92,
      "learning_rate": 8.173076923076924e-07,
      "loss": 0.7299,
      "step": 825
    },
    {
      "epoch": 1.92,
      "learning_rate": 7.932692307692308e-07,
      "loss": 0.7014,
      "step": 826
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.692307692307694e-07,
      "loss": 0.7378,
      "step": 827
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.451923076923078e-07,
      "loss": 0.7206,
      "step": 828
    },
    {
      "epoch": 1.93,
      "learning_rate": 7.211538461538461e-07,
      "loss": 0.6853,
      "step": 829
    },
    {
      "epoch": 1.93,
      "learning_rate": 6.971153846153847e-07,
      "loss": 0.7227,
      "step": 830
    },
    {
      "epoch": 1.93,
      "learning_rate": 6.730769230769231e-07,
      "loss": 0.7564,
      "step": 831
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.490384615384616e-07,
      "loss": 0.7167,
      "step": 832
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.25e-07,
      "loss": 0.7206,
      "step": 833
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.009615384615385e-07,
      "loss": 0.6948,
      "step": 834
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.76923076923077e-07,
      "loss": 0.7189,
      "step": 835
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.528846153846155e-07,
      "loss": 0.7095,
      "step": 836
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.288461538461539e-07,
      "loss": 0.7361,
      "step": 837
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.048076923076923e-07,
      "loss": 0.6983,
      "step": 838
    },
    {
      "epoch": 1.95,
      "learning_rate": 4.807692307692308e-07,
      "loss": 0.7802,
      "step": 839
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.5673076923076923e-07,
      "loss": 0.7157,
      "step": 840
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.326923076923077e-07,
      "loss": 0.7349,
      "step": 841
    },
    {
      "epoch": 1.96,
      "learning_rate": 4.086538461538462e-07,
      "loss": 0.7576,
      "step": 842
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.846153846153847e-07,
      "loss": 0.713,
      "step": 843
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.6057692307692306e-07,
      "loss": 0.6931,
      "step": 844
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.3653846153846154e-07,
      "loss": 0.7504,
      "step": 845
    },
    {
      "epoch": 1.97,
      "learning_rate": 3.125e-07,
      "loss": 0.7984,
      "step": 846
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.884615384615385e-07,
      "loss": 0.7518,
      "step": 847
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.6442307692307694e-07,
      "loss": 0.6893,
      "step": 848
    },
    {
      "epoch": 1.98,
      "learning_rate": 2.403846153846154e-07,
      "loss": 0.6848,
      "step": 849
    },
    {
      "epoch": 1.98,
      "learning_rate": 2.1634615384615386e-07,
      "loss": 0.7338,
      "step": 850
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.9230769230769234e-07,
      "loss": 0.6898,
      "step": 851
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.6826923076923077e-07,
      "loss": 0.7097,
      "step": 852
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.4423076923076925e-07,
      "loss": 0.7671,
      "step": 853
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.201923076923077e-07,
      "loss": 0.7528,
      "step": 854
    },
    {
      "epoch": 1.99,
      "learning_rate": 9.615384615384617e-08,
      "loss": 0.7427,
      "step": 855
    },
    {
      "epoch": 1.99,
      "learning_rate": 7.211538461538463e-08,
      "loss": 0.7086,
      "step": 856
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8076923076923085e-08,
      "loss": 0.7835,
      "step": 857
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.4038461538461542e-08,
      "loss": 0.7139,
      "step": 858
    },
    {
      "epoch": 2.0,
      "step": 858,
      "total_flos": 2.9325289200979804e+18,
      "train_loss": 0.7660849066603156,
      "train_runtime": 11277.6545,
      "train_samples_per_second": 9.749,
      "train_steps_per_second": 0.076
    }
  ],
  "max_steps": 858,
  "num_train_epochs": 2,
  "total_flos": 2.9325289200979804e+18,
  "trial_name": null,
  "trial_params": null
}