{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988545246277205,
  "global_step": 436,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 1.946,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.908,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.090909090909091e-06,
      "loss": 2.1083,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 2.3218,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 1.8338,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 2.0202,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 2.1332,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 1.8593,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 1.5359,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 1.327,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7252,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.4351,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.939393939393939e-05,
      "loss": 1.2774,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.242424242424243e-05,
      "loss": 1.5145,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.1529,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.848484848484849e-05,
      "loss": 1.0047,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.151515151515152e-05,
      "loss": 1.3872,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.1229,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.757575757575758e-05,
      "loss": 1.3386,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.060606060606061e-05,
      "loss": 1.2493,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.363636363636364e-05,
      "loss": 1.1427,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.0895,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 6.96969696969697e-05,
      "loss": 1.1989,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.0438,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.575757575757576e-05,
      "loss": 1.176,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.878787878787879e-05,
      "loss": 1.1372,
      "step": 26
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.181818181818183e-05,
      "loss": 1.2983,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.484848484848486e-05,
      "loss": 0.9371,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.787878787878789e-05,
      "loss": 1.2299,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.9441,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.393939393939395e-05,
      "loss": 1.0011,
      "step": 31
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.696969696969698e-05,
      "loss": 1.1704,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.1193,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010303030303030303,
      "loss": 1.1559,
      "step": 34
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010606060606060606,
      "loss": 0.8677,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00010909090909090909,
      "loss": 1.0865,
      "step": 36
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00011212121212121212,
      "loss": 1.0922,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00011515151515151516,
      "loss": 0.9434,
      "step": 38
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001181818181818182,
      "loss": 0.9144,
      "step": 39
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012121212121212122,
      "loss": 0.9546,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00012424242424242425,
      "loss": 1.0654,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.8077,
      "step": 42
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001303030303030303,
      "loss": 1.0758,
      "step": 43
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.1512,
      "step": 44
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013636363636363637,
      "loss": 0.84,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001393939393939394,
      "loss": 1.0567,
      "step": 46
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014242424242424243,
      "loss": 1.0165,
      "step": 47
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.8678,
      "step": 48
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00014848484848484849,
      "loss": 1.055,
      "step": 49
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00015151515151515152,
      "loss": 1.0669,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015454545454545454,
      "loss": 0.9915,
      "step": 51
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00015757575757575757,
      "loss": 0.993,
      "step": 52
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001606060606060606,
      "loss": 1.1085,
      "step": 53
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9391,
      "step": 54
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.975,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00016969696969696972,
      "loss": 1.0697,
      "step": 56
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017272727272727275,
      "loss": 0.9462,
      "step": 57
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00017575757575757578,
      "loss": 1.1209,
      "step": 58
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001787878787878788,
      "loss": 1.0648,
      "step": 59
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9964,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00018484848484848484,
      "loss": 0.8451,
      "step": 61
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001878787878787879,
      "loss": 0.8437,
      "step": 62
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019090909090909092,
      "loss": 1.1271,
      "step": 63
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019393939393939395,
      "loss": 1.161,
      "step": 64
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019696969696969698,
      "loss": 1.0032,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002,
      "loss": 1.1258,
      "step": 66
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019999988957695886,
      "loss": 0.9543,
      "step": 67
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999955830807923,
      "loss": 1.0274,
      "step": 68
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999900619409279,
      "loss": 0.9334,
      "step": 69
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001999982332362188,
      "loss": 1.0398,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999723943616433,
      "loss": 0.9049,
      "step": 71
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019999602479612417,
      "loss": 0.7452,
      "step": 72
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999458931878073,
      "loss": 0.8762,
      "step": 73
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999293300730427,
      "loss": 1.0941,
      "step": 74
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999105586535268,
      "loss": 0.7713,
      "step": 75
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019998895789707154,
      "loss": 0.9233,
      "step": 76
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019998663910709416,
      "loss": 0.8634,
      "step": 77
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019998409950054146,
      "loss": 0.9697,
      "step": 78
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019998133908302209,
      "loss": 1.0816,
      "step": 79
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999783578606323,
      "loss": 0.9659,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019997515583995603,
      "loss": 0.9644,
      "step": 81
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019997173302806478,
      "loss": 0.8561,
      "step": 82
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019996808943251773,
      "loss": 1.0016,
      "step": 83
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001999642250613616,
      "loss": 0.8951,
      "step": 84
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019996013992313073,
      "loss": 1.0157,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019995583402684694,
      "loss": 0.9414,
      "step": 86
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019995130738201966,
      "loss": 0.8097,
      "step": 87
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019994655999864582,
      "loss": 0.8606,
      "step": 88
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001999415918872098,
      "loss": 1.0427,
      "step": 89
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019993640305868352,
      "loss": 0.9578,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019993099352452623,
      "loss": 1.1097,
      "step": 91
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019992536329668478,
      "loss": 0.8119,
      "step": 92
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019991951238759325,
      "loss": 0.9915,
      "step": 93
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001999134408101731,
      "loss": 0.838,
      "step": 94
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019990714857783326,
      "loss": 0.8935,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019990063570446984,
      "loss": 0.7914,
      "step": 96
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019989390220446622,
      "loss": 0.8724,
      "step": 97
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019988694809269314,
      "loss": 1.0374,
      "step": 98
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019987977338450845,
      "loss": 0.9028,
      "step": 99
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019987237809575723,
      "loss": 0.9986,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019986476224277165,
      "loss": 1.113,
      "step": 101
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019985692584237108,
      "loss": 0.8395,
      "step": 102
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019984886891186184,
      "loss": 1.0134,
      "step": 103
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001998405914690374,
      "loss": 0.8845,
      "step": 104
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019983209353217812,
      "loss": 0.7507,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019982337512005138,
      "loss": 0.9073,
      "step": 106
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019981443625191148,
      "loss": 0.9973,
      "step": 107
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019980527694749952,
      "loss": 1.0733,
      "step": 108
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019979589722704346,
      "loss": 0.9148,
      "step": 109
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019978629711125812,
      "loss": 0.8385,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019977647662134488,
      "loss": 0.75,
      "step": 111
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019976643577899195,
      "loss": 0.9002,
      "step": 112
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019975617460637416,
      "loss": 0.8754,
      "step": 113
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001997456931261529,
      "loss": 0.8886,
      "step": 114
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019973499136147606,
      "loss": 1.0058,
      "step": 115
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019972406933597812,
      "loss": 0.9276,
      "step": 116
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019971292707377991,
      "loss": 0.9922,
      "step": 117
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019970156459948873,
      "loss": 0.9507,
      "step": 118
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001996899819381981,
      "loss": 0.9619,
      "step": 119
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019967817911548794,
      "loss": 0.8163,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019966615615742424,
      "loss": 1.0647,
      "step": 121
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001996539130905593,
      "loss": 0.9348,
      "step": 122
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019964144994193142,
      "loss": 1.0523,
      "step": 123
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000199628766739065,
      "loss": 0.9063,
      "step": 124
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019961586350997033,
      "loss": 1.0227,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001996027402831438,
      "loss": 1.006,
      "step": 126
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019958939708756746,
      "loss": 0.9082,
      "step": 127
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019957583395270923,
      "loss": 0.8756,
      "step": 128
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001995620509085228,
      "loss": 0.8311,
      "step": 129
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019954804798544745,
      "loss": 1.0332,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019953382521440815,
      "loss": 0.9427,
      "step": 131
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019951938262681527,
      "loss": 0.838,
      "step": 132
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001995047202545647,
      "loss": 0.8509,
      "step": 133
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019948983813003774,
      "loss": 0.8944,
      "step": 134
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019947473628610099,
      "loss": 0.9569,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019945941475610623,
      "loss": 0.7805,
      "step": 136
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019944387357389052,
      "loss": 0.9337,
      "step": 137
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001994281127737759,
      "loss": 0.8712,
      "step": 138
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001994121323905695,
      "loss": 0.9264,
      "step": 139
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001993959324595634,
      "loss": 0.9323,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019937951301653444,
      "loss": 0.8331,
      "step": 141
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001993628740977444,
      "loss": 0.902,
      "step": 142
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001993460157399396,
      "loss": 0.8676,
      "step": 143
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019932893798035116,
      "loss": 0.8525,
      "step": 144
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019931164085669456,
      "loss": 0.8571,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019929412440716985,
      "loss": 1.0006,
      "step": 146
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019927638867046142,
      "loss": 0.9849,
      "step": 147
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019925843368573794,
      "loss": 0.9064,
      "step": 148
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001992402594926523,
      "loss": 0.9716,
      "step": 149
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001992218661313415,
      "loss": 0.7553,
      "step": 150
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019920325364242654,
      "loss": 0.7921,
      "step": 151
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019918442206701245,
      "loss": 0.7994,
      "step": 152
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001991653714466879,
      "loss": 0.8296,
      "step": 153
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019914610182352548,
      "loss": 0.8116,
      "step": 154
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019912661324008148,
      "loss": 0.9844,
      "step": 155
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019910690573939557,
      "loss": 0.865,
      "step": 156
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019908697936499103,
      "loss": 0.959,
      "step": 157
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019906683416087448,
      "loss": 0.7727,
      "step": 158
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019904647017153582,
      "loss": 0.707,
      "step": 159
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019902588744194813,
      "loss": 0.8597,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019900508601756756,
      "loss": 0.9146,
      "step": 161
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001989840659443332,
      "loss": 0.9571,
      "step": 162
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001989628272686671,
      "loss": 0.8537,
      "step": 163
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019894137003747403,
      "loss": 0.828,
      "step": 164
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019891969429814145,
      "loss": 0.8055,
      "step": 165
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001988978000985394,
      "loss": 0.8432,
      "step": 166
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001988756874870203,
      "loss": 0.8101,
      "step": 167
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019885335651241903,
      "loss": 0.9072,
      "step": 168
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001988308072240527,
      "loss": 0.7862,
      "step": 169
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019880803967172047,
      "loss": 0.8303,
      "step": 170
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019878505390570362,
      "loss": 0.9489,
      "step": 171
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001987618499767653,
      "loss": 1.0125,
      "step": 172
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001987384279361505,
      "loss": 0.809,
      "step": 173
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019871478783558587,
      "loss": 0.9488,
      "step": 174
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001986909297272796,
      "loss": 0.9664,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001986668536639215,
      "loss": 0.9657,
      "step": 176
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001986425596986825,
      "loss": 0.8123,
      "step": 177
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019861804788521493,
      "loss": 0.9482,
      "step": 178
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019859331827765212,
      "loss": 0.879,
      "step": 179
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019856837093060848,
      "loss": 0.896,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019854320589917927,
      "loss": 1.0729,
      "step": 181
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019851782323894042,
      "loss": 0.9844,
      "step": 182
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001984922230059486,
      "loss": 0.9131,
      "step": 183
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019846640525674082,
      "loss": 0.9417,
      "step": 184
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019844037004833473,
      "loss": 0.9633,
      "step": 185
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001984141174382279,
      "loss": 0.968,
      "step": 186
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019838764748439827,
      "loss": 0.8447,
      "step": 187
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019836096024530373,
      "loss": 0.8638,
      "step": 188
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019833405577988195,
      "loss": 0.9346,
      "step": 189
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001983069341475504,
      "loss": 0.8969,
      "step": 190
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019827959540820613,
      "loss": 0.8499,
      "step": 191
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019825203962222572,
      "loss": 0.8041,
      "step": 192
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019822426685046497,
      "loss": 0.9216,
      "step": 193
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019819627715425903,
      "loss": 0.906,
      "step": 194
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000198168070595422,
      "loss": 0.8969,
      "step": 195
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000198139647236247,
      "loss": 0.7949,
      "step": 196
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019811100713950587,
      "loss": 0.8996,
      "step": 197
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019808215036844917,
      "loss": 0.9118,
      "step": 198
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001980530769868059,
      "loss": 0.7355,
      "step": 199
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019802378705878354,
      "loss": 0.8344,
      "step": 200
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019799428064906774,
      "loss": 0.9639,
      "step": 201
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001979645578228222,
      "loss": 0.852,
      "step": 202
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001979346186456887,
      "loss": 0.8493,
      "step": 203
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019790446318378665,
      "loss": 0.851,
      "step": 204
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019787409150371328,
      "loss": 0.7161,
      "step": 205
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019784350367254322,
      "loss": 0.9846,
      "step": 206
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001978126997578285,
      "loss": 0.7883,
      "step": 207
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019778167982759833,
      "loss": 0.8691,
      "step": 208
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019775044395035907,
      "loss": 0.928,
      "step": 209
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001977189921950939,
      "loss": 0.8244,
      "step": 210
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001976873246312628,
      "loss": 1.0413,
      "step": 211
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001976554413288023,
      "loss": 0.8261,
      "step": 212
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001976233423581255,
      "loss": 0.823,
      "step": 213
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019759102779012166,
      "loss": 0.9386,
      "step": 214
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019755849769615628,
      "loss": 0.8156,
      "step": 215
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019752575214807076,
      "loss": 0.8556,
      "step": 216
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.7769,
      "step": 217
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019745961497928406,
      "loss": 1.0772,
      "step": 218
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019742622350464418,
      "loss": 0.8147,
      "step": 219
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001973926168680066,
      "loss": 0.9529,
      "step": 220
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019735879514359018,
      "loss": 0.8688,
      "step": 221
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019732475840608888,
      "loss": 0.9647,
      "step": 222
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019729050673067156,
      "loss": 0.837,
      "step": 223
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019725604019298163,
      "loss": 0.9211,
      "step": 224
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019722135886913715,
      "loss": 0.9434,
      "step": 225
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001971864628357304,
      "loss": 0.6506,
      "step": 226
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019715135216982798,
      "loss": 0.8052,
      "step": 227
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019711602694897037,
      "loss": 0.7852,
      "step": 228
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019708048725117192,
      "loss": 0.9283,
      "step": 229
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001970447331549207,
      "loss": 0.9081,
      "step": 230
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019700876473917824,
      "loss": 0.9036,
      "step": 231
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019697258208337934,
      "loss": 0.716,
      "step": 232
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019693618526743197,
      "loss": 0.8192,
      "step": 233
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001968995743717171,
      "loss": 0.9773,
      "step": 234
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019686274947708848,
      "loss": 0.8698,
      "step": 235
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001968257106648724,
      "loss": 0.9062,
      "step": 236
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019678845801686764,
      "loss": 0.8984,
      "step": 237
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019675099161534521,
      "loss": 0.8087,
      "step": 238
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019671331154304822,
      "loss": 0.8272,
      "step": 239
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019667541788319162,
      "loss": 0.784,
      "step": 240
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019663731071946206,
      "loss": 0.8777,
      "step": 241
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019659899013601772,
      "loss": 0.8534,
      "step": 242
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019656045621748808,
      "loss": 0.9645,
      "step": 243
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019652170904897387,
      "loss": 0.9692,
      "step": 244
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019648274871604662,
      "loss": 0.838,
      "step": 245
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019644357530474872,
      "loss": 0.7445,
      "step": 246
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001964041889015931,
      "loss": 0.9065,
      "step": 247
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019636458959356316,
      "loss": 0.7806,
      "step": 248
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019632477746811232,
      "loss": 0.7971,
      "step": 249
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019628475261316417,
      "loss": 0.8409,
      "step": 250
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019624451511711198,
      "loss": 0.7432,
      "step": 251
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019620406506881875,
      "loss": 0.9096,
      "step": 252
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019616340255761676,
      "loss": 0.8004,
      "step": 253
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019612252767330763,
      "loss": 0.7978,
      "step": 254
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001960814405061619,
      "loss": 0.9535,
      "step": 255
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000196040141146919,
      "loss": 0.9945,
      "step": 256
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001959986296867869,
      "loss": 0.9703,
      "step": 257
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019595690621744208,
      "loss": 0.9639,
      "step": 258
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019591497083102914,
      "loss": 0.9312,
      "step": 259
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019587282362016083,
      "loss": 0.7709,
      "step": 260
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001958304646779175,
      "loss": 0.8547,
      "step": 261
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019578789409784727,
      "loss": 0.8081,
      "step": 262
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019574511197396563,
      "loss": 0.8476,
      "step": 263
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019570211840075517,
      "loss": 0.9658,
      "step": 264
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019565891347316552,
      "loss": 0.7778,
      "step": 265
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001956154972866131,
      "loss": 0.9926,
      "step": 266
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001955718699369808,
      "loss": 0.957,
      "step": 267
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000195528031520618,
      "loss": 0.9396,
      "step": 268
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019548398213434007,
      "loss": 0.9049,
      "step": 269
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019543972187542833,
      "loss": 0.9683,
      "step": 270
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019539525084162992,
      "loss": 0.8555,
      "step": 271
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019535056913115725,
      "loss": 0.8489,
      "step": 272
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001953056768426882,
      "loss": 0.8728,
      "step": 273
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019526057407536564,
      "loss": 0.9443,
      "step": 274
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019521526092879725,
      "loss": 0.8161,
      "step": 275
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019516973750305532,
      "loss": 0.8936,
      "step": 276
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019512400389867657,
      "loss": 0.8315,
      "step": 277
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019507806021666188,
      "loss": 0.9298,
      "step": 278
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019503190655847604,
      "loss": 0.8235,
      "step": 279
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019498554302604766,
      "loss": 0.9245,
      "step": 280
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001949389697217687,
      "loss": 0.8302,
      "step": 281
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019489218674849455,
      "loss": 0.8488,
      "step": 282
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019484519420954354,
      "loss": 0.8177,
      "step": 283
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019479799220869682,
      "loss": 1.0039,
      "step": 284
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019475058085019825,
      "loss": 0.7685,
      "step": 285
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019470296023875387,
      "loss": 0.9174,
      "step": 286
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.000194655130479532,
      "loss": 1.0997,
      "step": 287
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019460709167816274,
      "loss": 0.9759,
      "step": 288
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001945588439407379,
      "loss": 0.9397,
      "step": 289
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019451038737381077,
      "loss": 1.0367,
      "step": 290
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019446172208439574,
      "loss": 0.8298,
      "step": 291
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001944128481799682,
      "loss": 0.9094,
      "step": 292
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019436376576846423,
      "loss": 1.1234,
      "step": 293
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019431447495828045,
      "loss": 0.9103,
      "step": 294
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001942649758582737,
      "loss": 0.7841,
      "step": 295
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019421526857776072,
      "loss": 0.8817,
      "step": 296
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019416535322651818,
      "loss": 1.0682,
      "step": 297
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019411522991478214,
      "loss": 0.9201,
      "step": 298
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.000194064898753248,
      "loss": 4.1834,
      "step": 299
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019401435985307012,
      "loss": 1.0391,
      "step": 300
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019396361332586166,
      "loss": 2.5015,
      "step": 301
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001939126592836944,
      "loss": 0.7927,
      "step": 302
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001938614978390983,
      "loss": 2.2345,
      "step": 303
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019381012910506146,
      "loss": 0.9311,
      "step": 304
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019375855319502962,
      "loss": 0.9713,
      "step": 305
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019370677022290624,
      "loss": 0.8967,
      "step": 306
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019365478030305196,
      "loss": 3.095,
      "step": 307
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001936025835502845,
      "loss": 1.1008,
      "step": 308
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001935501800798783,
      "loss": 1.5409,
      "step": 309
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019349757000756444,
      "loss": 1.02,
      "step": 310
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019344475344953012,
      "loss": 1.0101,
      "step": 311
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001933917305224187,
      "loss": 0.7686,
      "step": 312
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001933385013433292,
      "loss": 1.1061,
      "step": 313
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001932850660298162,
      "loss": 0.8083,
      "step": 314
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001932314246998895,
      "loss": 1.1942,
      "step": 315
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019317757747201384,
      "loss": 0.8551,
      "step": 316
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019312352446510878,
      "loss": 0.9049,
      "step": 317
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019306926579854821,
      "loss": 0.7072,
      "step": 318
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019301480159216028,
      "loss": 0.8552,
      "step": 319
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019296013196622706,
      "loss": 0.8414,
      "step": 320
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001929052570414843,
      "loss": 0.9198,
      "step": 321
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019285017693912107,
      "loss": 2.1953,
      "step": 322
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019279489178077969,
      "loss": 0.851,
      "step": 323
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019273940168855518,
      "loss": 1.0239,
      "step": 324
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019268370678499533,
      "loss": 1.5125,
      "step": 325
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019262780719310008,
      "loss": 0.9171,
      "step": 326
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019257170303632148,
      "loss": 0.9794,
      "step": 327
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019251539443856344,
      "loss": 0.9023,
      "step": 328
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019245888152418124,
      "loss": 1.058,
      "step": 329
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019240216441798142,
      "loss": 0.9411,
      "step": 330
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001923452432452215,
      "loss": 1.197,
      "step": 331
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001922881181316097,
      "loss": 0.9253,
      "step": 332
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001922307892033046,
      "loss": 1.156,
      "step": 333
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019217325658691482,
      "loss": 0.9424,
      "step": 334
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019211552040949891,
      "loss": 1.1147,
      "step": 335
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019205758079856498,
      "loss": 0.8528,
      "step": 336
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001919994378820704,
      "loss": 0.8105,
      "step": 337
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019194109178842153,
      "loss": 0.9279,
      "step": 338
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019188254264647337,
      "loss": 0.9231,
      "step": 339
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019182379058552948,
      "loss": 1.0425,
      "step": 340
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019176483573534142,
      "loss": 0.8794,
      "step": 341
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019170567822610873,
      "loss": 0.9873,
      "step": 342
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001916463181884784,
      "loss": 0.8146,
      "step": 343
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019158675575354478,
      "loss": 1.027,
      "step": 344
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019152699105284913,
      "loss": 0.8093,
      "step": 345
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001914670242183795,
      "loss": 0.951,
      "step": 346
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019140685538257028,
      "loss": 0.9268,
      "step": 347
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019134648467830198,
      "loss": 1.0205,
      "step": 348
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019128591223890092,
      "loss": 0.9043,
      "step": 349
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019122513819813902,
      "loss": 0.7387,
      "step": 350
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001911641626902333,
      "loss": 0.9422,
      "step": 351
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019110298584984578,
      "loss": 0.9015,
      "step": 352
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001910416078120832,
      "loss": 0.7522,
      "step": 353
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019098002871249646,
      "loss": 0.9722,
      "step": 354
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001909182486870806,
      "loss": 0.8358,
      "step": 355
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019085626787227443,
      "loss": 0.9859,
      "step": 356
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019079408640496013,
      "loss": 0.7796,
      "step": 357
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019073170442246302,
      "loss": 0.8617,
      "step": 358
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001906691220625513,
      "loss": 0.7727,
      "step": 359
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001906063394634356,
      "loss": 0.8786,
      "step": 360
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001905433567637689,
      "loss": 0.9117,
      "step": 361
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000190480174102646,
      "loss": 0.9182,
      "step": 362
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001904167916196033,
      "loss": 0.9706,
      "step": 363
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001903532094546186,
      "loss": 0.8036,
      "step": 364
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001902894277481105,
      "loss": 0.902,
      "step": 365
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019022544664093854,
      "loss": 0.9231,
      "step": 366
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019016126627440237,
      "loss": 0.9751,
      "step": 367
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.8373,
      "step": 368
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001900323083306367,
      "loss": 0.8695,
      "step": 369
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001899675310382057,
      "loss": 0.8654,
      "step": 370
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018990255505600706,
      "loss": 0.98,
      "step": 371
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018983738052753767,
      "loss": 0.7454,
      "step": 372
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00018977200759673295,
      "loss": 0.829,
      "step": 373
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018970643640796642,
      "loss": 0.8262,
      "step": 374
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001896406671060495,
      "loss": 1.0659,
      "step": 375
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018957469983623112,
      "loss": 0.8551,
      "step": 376
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018950853474419742,
      "loss": 0.7991,
      "step": 377
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001894421719760714,
      "loss": 0.8662,
      "step": 378
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018937561167841263,
      "loss": 0.8817,
      "step": 379
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018930885399821693,
      "loss": 1.0894,
      "step": 380
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.000189241899082916,
      "loss": 0.8225,
      "step": 381
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018917474708037718,
      "loss": 0.9065,
      "step": 382
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018910739813890302,
      "loss": 0.8779,
      "step": 383
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018903985240723104,
      "loss": 0.7909,
      "step": 384
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018897211003453328,
      "loss": 0.7649,
      "step": 385
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00018890417117041619,
      "loss": 0.9788,
      "step": 386
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018883603596492004,
      "loss": 0.938,
      "step": 387
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018876770456851877,
      "loss": 0.9032,
      "step": 388
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018869917713211964,
      "loss": 0.9059,
      "step": 389
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00018863045380706274,
      "loss": 0.8896,
      "step": 390
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001885615347451209,
      "loss": 0.7614,
      "step": 391
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001884924200984991,
      "loss": 0.978,
      "step": 392
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001884231100198344,
      "loss": 0.9406,
      "step": 393
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00018835360466219533,
      "loss": 0.7555,
      "step": 394
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001882839041790818,
      "loss": 0.9049,
      "step": 395
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018821400872442458,
      "loss": 0.7041,
      "step": 396
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018814391845258505,
      "loss": 0.8995,
      "step": 397
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001880736335183548,
      "loss": 0.7461,
      "step": 398
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00018800315407695539,
      "loss": 0.9954,
      "step": 399
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018793248028403788,
      "loss": 0.9035,
      "step": 400
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001878616122956826,
      "loss": 0.9083,
      "step": 401
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00018779055026839868,
      "loss": 0.7286,
      "step": 402
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001877192943591239,
      "loss": 0.8001,
      "step": 403
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018764784472522403,
      "loss": 0.8795,
      "step": 404
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001875762015244929,
      "loss": 0.8912,
      "step": 405
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018750436491515163,
      "loss": 0.8848,
      "step": 406
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018743233505584862,
      "loss": 0.8512,
      "step": 407
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00018736011210565898,
      "loss": 0.8537,
      "step": 408
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018728769622408423,
      "loss": 0.8777,
      "step": 409
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018721508757105202,
      "loss": 0.7849,
      "step": 410
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00018714228630691576,
      "loss": 0.9669,
      "step": 411
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001870692925924541,
      "loss": 0.9299,
      "step": 412
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018699610658887088,
      "loss": 1.0188,
      "step": 413
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018692272845779448,
      "loss": 0.8388,
      "step": 414
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018684915836127765,
      "loss": 0.7904,
      "step": 415
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00018677539646179707,
      "loss": 0.9689,
      "step": 416
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018670144292225297,
      "loss": 0.7339,
      "step": 417
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018662729790596888,
      "loss": 0.7894,
      "step": 418
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018655296157669117,
      "loss": 0.7163,
      "step": 419
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018647843409858869,
      "loss": 0.8642,
      "step": 420
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00018640371563625246,
      "loss": 0.9281,
      "step": 421
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018632880635469526,
      "loss": 0.834,
      "step": 422
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018625370641935129,
      "loss": 0.7316,
      "step": 423
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018617841599607586,
      "loss": 0.8504,
      "step": 424
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018610293525114492,
      "loss": 0.8731,
      "step": 425
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018602726435125474,
      "loss": 0.8803,
      "step": 426
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001859514034635215,
      "loss": 0.8417,
      "step": 427
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000185875352755481,
      "loss": 0.8947,
      "step": 428
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00018579911239508827,
      "loss": 0.8368,
      "step": 429
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018572268255071718,
      "loss": 0.8231,
      "step": 430
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018564606339116,
      "loss": 0.8576,
      "step": 431
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001855692550856272,
      "loss": 0.8753,
      "step": 432
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018549225780374685,
      "loss": 0.7778,
      "step": 433
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00018541507171556445,
      "loss": 0.7516,
      "step": 434
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001853376969915425,
      "loss": 0.7466,
      "step": 435
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00018526013380255999,
      "loss": 0.917,
      "step": 436
    }
  ],
  "max_steps": 2180,
  "num_train_epochs": 5,
  "total_flos": 140002887892992.0,
  "trial_name": null,
  "trial_params": null
}