{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 465,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.6573,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.6856,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.6195,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.714285714285714e-05,
      "loss": 1.4941,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.3222,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.2348,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.2121,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011428571428571428,
      "loss": 1.1245,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012857142857142858,
      "loss": 1.1698,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.1782,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015714285714285716,
      "loss": 1.0427,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.0918,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018571428571428572,
      "loss": 1.0289,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 0.9759,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999757386529745,
      "loss": 0.9791,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999902955789124,
      "loss": 0.9935,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999781654940069,
      "loss": 0.9983,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019996118419916533,
      "loss": 0.9828,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999393525183659,
      "loss": 1.0053,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019991267151094053,
      "loss": 1.0188,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019988114247152363,
      "loss": 1.011,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019984476692998913,
      "loss": 0.9739,
      "step": 22
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019980354665137626,
      "loss": 0.9957,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019975748363580404,
      "loss": 0.942,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019970658011837404,
      "loss": 0.9644,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001996508385690621,
      "loss": 0.9272,
      "step": 26
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019959026169259834,
      "loss": 0.956,
      "step": 27
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000199524852428336,
      "loss": 0.9735,
      "step": 28
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019945461395010883,
      "loss": 1.0073,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019937954966607694,
      "loss": 0.9195,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001992996632185617,
      "loss": 0.9223,
      "step": 31
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019921495848386876,
      "loss": 0.9765,
      "step": 32
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001991254395721,
      "loss": 0.9753,
      "step": 33
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001990311108269542,
      "loss": 0.9585,
      "step": 34
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019893197682551624,
      "loss": 0.9614,
      "step": 35
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019882804237803488,
      "loss": 0.9492,
      "step": 36
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019871931252768955,
      "loss": 0.969,
      "step": 37
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001986057925503455,
      "loss": 0.9452,
      "step": 38
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019848748795429788,
      "loss": 0.9317,
      "step": 39
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001983644044800044,
      "loss": 0.8749,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019823654809980682,
      "loss": 0.8208,
      "step": 41
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019810392501764116,
      "loss": 0.8632,
      "step": 42
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019796654166873666,
      "loss": 0.9159,
      "step": 43
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019782440471930354,
      "loss": 0.9201,
      "step": 44
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001976775210662095,
      "loss": 0.957,
      "step": 45
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001975258978366451,
      "loss": 0.9268,
      "step": 46
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019736954238777792,
      "loss": 0.9516,
      "step": 47
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019720846230639557,
      "loss": 0.9008,
      "step": 48
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019704266540853752,
      "loss": 0.8722,
      "step": 49
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019687215973911599,
      "loss": 0.9384,
      "step": 50
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019669695357152537,
      "loss": 0.8853,
      "step": 51
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019651705540724092,
      "loss": 0.9246,
      "step": 52
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019633247397540625,
      "loss": 0.8659,
      "step": 53
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019614321823240968,
      "loss": 0.8708,
      "step": 54
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019594929736144976,
      "loss": 0.848,
      "step": 55
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019575072077208954,
      "loss": 0.8691,
      "step": 56
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019554749809980014,
      "loss": 0.8819,
      "step": 57
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019533963920549306,
      "loss": 0.9047,
      "step": 58
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001951271541750419,
      "loss": 0.8644,
      "step": 59
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019491005331879278,
      "loss": 0.8869,
      "step": 60
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019468834717106408,
      "loss": 0.8805,
      "step": 61
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001944620464896354,
      "loss": 0.9323,
      "step": 62
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019423116225522548,
      "loss": 0.9393,
      "step": 63
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019399570567095936,
      "loss": 0.9303,
      "step": 64
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019375568816182485,
      "loss": 0.8898,
      "step": 65
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019351112137411816,
      "loss": 0.8466,
      "step": 66
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019326201717487863,
      "loss": 0.8526,
      "step": 67
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019300838765131314,
      "loss": 0.8938,
      "step": 68
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001927502451102095,
      "loss": 0.8712,
      "step": 69
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019248760207733919,
      "loss": 0.8522,
      "step": 70
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019222047129684974,
      "loss": 0.8797,
      "step": 71
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019194886573064635,
      "loss": 0.8753,
      "step": 72
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019167279855776274,
      "loss": 0.8703,
      "step": 73
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019139228317372194,
      "loss": 0.9131,
      "step": 74
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019110733318988604,
      "loss": 0.9136,
      "step": 75
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000190817962432796,
      "loss": 0.8971,
      "step": 76
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019052418494350048,
      "loss": 0.8285,
      "step": 77
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001902260149768747,
      "loss": 0.9126,
      "step": 78
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001899234670009288,
      "loss": 0.8018,
      "step": 79
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018961655569610557,
      "loss": 0.9147,
      "step": 80
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018930529595456838,
      "loss": 0.922,
      "step": 81
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018898970287947847,
      "loss": 0.8314,
      "step": 82
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018866979178426205,
      "loss": 0.8911,
      "step": 83
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018834557819186732,
      "loss": 0.7828,
      "step": 84
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018801707783401122,
      "loss": 0.8538,
      "step": 85
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001876843066504161,
      "loss": 0.8548,
      "step": 86
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001873472807880363,
      "loss": 0.8314,
      "step": 87
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018700601660027463,
      "loss": 0.8404,
      "step": 88
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018666053064618886,
      "loss": 0.8542,
      "step": 89
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018631083968968827,
      "loss": 0.8378,
      "step": 90
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018595696069872013,
      "loss": 0.8207,
      "step": 91
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018559891084444642,
      "loss": 0.8595,
      "step": 92
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018523670750041071,
      "loss": 0.8344,
      "step": 93
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018487036824169507,
      "loss": 0.8886,
      "step": 94
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001844999108440672,
      "loss": 0.8965,
      "step": 95
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018412535328311814,
      "loss": 0.9179,
      "step": 96
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018374671373338973,
      "loss": 0.8855,
      "step": 97
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001833640105674931,
      "loss": 0.8428,
      "step": 98
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018297726235521684,
      "loss": 0.8908,
      "step": 99
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001825864878626261,
      "loss": 0.8838,
      "step": 100
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018219170605115206,
      "loss": 0.839,
      "step": 101
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018179293607667178,
      "loss": 0.8641,
      "step": 102
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001813901972885787,
      "loss": 0.8761,
      "step": 103
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018098350922884384,
      "loss": 0.8309,
      "step": 104
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018057289163106747,
      "loss": 0.8708,
      "step": 105
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018015836441952172,
      "loss": 0.8735,
      "step": 106
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017973994770818357,
      "loss": 0.8488,
      "step": 107
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017931766179975914,
      "loss": 0.8311,
      "step": 108
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017889152718469835,
      "loss": 0.8416,
      "step": 109
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017846156454020076,
      "loss": 0.8871,
      "step": 110
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017802779472921222,
      "loss": 0.7938,
      "step": 111
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017759023879941258,
      "loss": 0.8236,
      "step": 112
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001771489179821943,
      "loss": 0.829,
      "step": 113
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017670385369163242,
      "loss": 0.8168,
      "step": 114
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001762550675234453,
      "loss": 0.8461,
      "step": 115
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017580258125394693,
      "loss": 0.8084,
      "step": 116
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017534641683899008,
      "loss": 0.9077,
      "step": 117
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001748865964129011,
      "loss": 0.8139,
      "step": 118
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017442314228740586,
      "loss": 0.8471,
      "step": 119
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001739560769505471,
      "loss": 0.8267,
      "step": 120
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017348542306559324,
      "loss": 0.7966,
      "step": 121
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017301120346993875,
      "loss": 0.9005,
      "step": 122
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000172533441173996,
      "loss": 0.8447,
      "step": 123
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001720521593600787,
      "loss": 0.8722,
      "step": 124
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017156738138127706,
      "loss": 0.8462,
      "step": 125
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001710791307603246,
      "loss": 0.8249,
      "step": 126
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017058743118845686,
      "loss": 0.8764,
      "step": 127
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017009230652426173,
      "loss": 0.7816,
      "step": 128
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016959378079252176,
      "loss": 0.804,
      "step": 129
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016909187818304854,
      "loss": 0.8169,
      "step": 130
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016858662304950885,
      "loss": 0.8389,
      "step": 131
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016807803990824294,
      "loss": 0.879,
      "step": 132
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016756615343707494,
      "loss": 0.7998,
      "step": 133
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016705098847411552,
      "loss": 0.8218,
      "step": 134
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016653257001655652,
      "loss": 0.7729,
      "step": 135
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001660109232194582,
      "loss": 0.8509,
      "step": 136
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016548607339452853,
      "loss": 0.809,
      "step": 137
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016495804600889487,
      "loss": 0.8388,
      "step": 138
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001644268666838686,
      "loss": 0.8096,
      "step": 139
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016389256119370154,
      "loss": 0.8099,
      "step": 140
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016335515546433553,
      "loss": 0.8121,
      "step": 141
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016281467557214437,
      "loss": 0.8371,
      "step": 142
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016227114774266854,
      "loss": 0.8633,
      "step": 143
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016172459834934254,
      "loss": 0.8851,
      "step": 144
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016117505391221543,
      "loss": 0.7979,
      "step": 145
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001606225410966638,
      "loss": 0.8057,
      "step": 146
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016006708671209794,
      "loss": 0.8623,
      "step": 147
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000159508717710661,
      "loss": 0.85,
      "step": 148
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015894746118592123,
      "loss": 0.8645,
      "step": 149
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001583833443715572,
      "loss": 0.8464,
      "step": 150
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001578163946400366,
      "loss": 0.7715,
      "step": 151
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015724663950128775,
      "loss": 0.8274,
      "step": 152
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015667410660136487,
      "loss": 0.9138,
      "step": 153
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015609882372110684,
      "loss": 0.7879,
      "step": 154
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001555208187747887,
      "loss": 0.8327,
      "step": 155
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001549401198087677,
      "loss": 0.8274,
      "step": 156
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015435675500012212,
      "loss": 0.8606,
      "step": 157
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015377075265528406,
      "loss": 0.8739,
      "step": 158
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000153182141208666,
      "loss": 0.8834,
      "step": 159
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015259094922128109,
      "loss": 0.8255,
      "step": 160
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015199720537935725,
      "loss": 0.8356,
      "step": 161
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001514009384929453,
      "loss": 0.8171,
      "step": 162
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015080217749452094,
      "loss": 0.8538,
      "step": 163
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015020095143758084,
      "loss": 0.828,
      "step": 164
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014959728949523305,
      "loss": 0.8258,
      "step": 165
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014899122095878137,
      "loss": 0.8689,
      "step": 166
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014838277523630388,
      "loss": 0.8654,
      "step": 167
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001477719818512263,
      "loss": 0.8278,
      "step": 168
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014715887044088912,
      "loss": 0.833,
      "step": 169
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014654347075510974,
      "loss": 0.7702,
      "step": 170
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014592581265473884,
      "loss": 0.7773,
      "step": 171
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014530592611021145,
      "loss": 0.7538,
      "step": 172
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014468384120009273,
      "loss": 0.8864,
      "step": 173
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014405958810961842,
      "loss": 0.7691,
      "step": 174
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014343319712923025,
      "loss": 0.8287,
      "step": 175
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014280469865310614,
      "loss": 0.8333,
      "step": 176
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001421741231776853,
      "loss": 0.7896,
      "step": 177
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014154150130018866,
      "loss": 0.8755,
      "step": 178
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014090686371713402,
      "loss": 0.8675,
      "step": 179
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001402702412228466,
      "loss": 0.798,
      "step": 180
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000139631664707965,
      "loss": 0.8112,
      "step": 181
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013899116515794205,
      "loss": 0.878,
      "step": 182
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013834877365154143,
      "loss": 0.8426,
      "step": 183
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013770452135932967,
      "loss": 0.7863,
      "step": 184
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013705843954216367,
      "loss": 0.7532,
      "step": 185
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013641055954967377,
      "loss": 0.7935,
      "step": 186
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013576091281874256,
      "loss": 0.7937,
      "step": 187
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013510953087197974,
      "loss": 0.803,
      "step": 188
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001344564453161921,
      "loss": 0.781,
      "step": 189
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013380168784085027,
      "loss": 0.785,
      "step": 190
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013314529021655097,
      "loss": 0.8305,
      "step": 191
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013248728429347524,
      "loss": 0.8081,
      "step": 192
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001318277019998432,
      "loss": 0.8432,
      "step": 193
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013116657534036468,
      "loss": 0.86,
      "step": 194
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013050393639468629,
      "loss": 0.8163,
      "step": 195
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012983981731583486,
      "loss": 0.7691,
      "step": 196
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001291742503286573,
      "loss": 0.82,
      "step": 197
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012850726772825686,
      "loss": 0.857,
      "step": 198
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012783890187842618,
      "loss": 0.8442,
      "step": 199
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012716918521007696,
      "loss": 0.8234,
      "step": 200
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001264981502196662,
      "loss": 0.7953,
      "step": 201
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012582582946761938,
      "loss": 0.8526,
      "step": 202
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001251522555767507,
      "loss": 0.7855,
      "step": 203
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012447746123067996,
      "loss": 0.7828,
      "step": 204
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001238014791722468,
      "loss": 0.7819,
      "step": 205
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012312434220192178,
      "loss": 0.8025,
      "step": 206
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000122446083176215,
      "loss": 0.7783,
      "step": 207
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012176673500608155,
      "loss": 0.7921,
      "step": 208
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012108633065532498,
      "loss": 0.8183,
      "step": 209
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012040490313899735,
      "loss": 0.835,
      "step": 210
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011972248552179755,
      "loss": 0.7651,
      "step": 211
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011903911091646684,
      "loss": 0.839,
      "step": 212
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011835481248218215,
      "loss": 0.8393,
      "step": 213
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000117669623422947,
      "loss": 0.8009,
      "step": 214
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011698357698598052,
      "loss": 0.7651,
      "step": 215
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011629670646010407,
      "loss": 0.7803,
      "step": 216
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011560904517412598,
      "loss": 0.8199,
      "step": 217
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001149206264952245,
      "loss": 0.7937,
      "step": 218
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011423148382732853,
      "loss": 0.7851,
      "step": 219
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001135416506094969,
      "loss": 0.7896,
      "step": 220
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011285116031429584,
      "loss": 0.7636,
      "step": 221
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011216004644617462,
      "loss": 0.814,
      "step": 222
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011146834253984006,
      "loss": 0.7922,
      "step": 223
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011077608215862914,
      "loss": 0.7879,
      "step": 224
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001100832988928806,
      "loss": 0.7597,
      "step": 225
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010939002635830484,
      "loss": 0.7908,
      "step": 226
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010869629819435296,
      "loss": 0.8218,
      "step": 227
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010800214806258444,
      "loss": 0.7939,
      "step": 228
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001073076096450337,
      "loss": 0.8615,
      "step": 229
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010661271664257593,
      "loss": 0.8111,
      "step": 230
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010591750277329166,
      "loss": 0.7829,
      "step": 231
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010522200177083077,
      "loss": 0.7753,
      "step": 232
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010452624738277564,
      "loss": 0.725,
      "step": 233
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010383027336900355,
      "loss": 0.7834,
      "step": 234
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010313411350004863,
      "loss": 0.7676,
      "step": 235
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010243780155546323,
      "loss": 0.8096,
      "step": 236
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010174137132217883,
      "loss": 0.7363,
      "step": 237
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010104485659286647,
      "loss": 0.7526,
      "step": 238
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010034829116429738,
      "loss": 0.7667,
      "step": 239
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.965170883570266e-05,
      "loss": 0.7648,
      "step": 240
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.895514340713354e-05,
      "loss": 0.7525,
      "step": 241
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.825862867782123e-05,
      "loss": 0.809,
      "step": 242
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.756219844453676e-05,
      "loss": 0.7872,
      "step": 243
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.686588649995137e-05,
      "loss": 0.8715,
      "step": 244
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.616972663099647e-05,
      "loss": 0.8001,
      "step": 245
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.547375261722437e-05,
      "loss": 0.7999,
      "step": 246
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.477799822916924e-05,
      "loss": 0.8099,
      "step": 247
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.408249722670837e-05,
      "loss": 0.6896,
      "step": 248
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.338728335742406e-05,
      "loss": 0.7653,
      "step": 249
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.26923903549663e-05,
      "loss": 0.8662,
      "step": 250
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.199785193741559e-05,
      "loss": 0.7762,
      "step": 251
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.130370180564706e-05,
      "loss": 0.7992,
      "step": 252
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.06099736416952e-05,
      "loss": 0.747,
      "step": 253
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.991670110711943e-05,
      "loss": 0.8737,
      "step": 254
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.922391784137086e-05,
      "loss": 0.8148,
      "step": 255
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.853165746015997e-05,
      "loss": 0.7463,
      "step": 256
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.78399535538254e-05,
      "loss": 0.7471,
      "step": 257
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.714883968570417e-05,
      "loss": 0.7916,
      "step": 258
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.64583493905031e-05,
      "loss": 0.7884,
      "step": 259
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.57685161726715e-05,
      "loss": 0.7891,
      "step": 260
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.507937350477553e-05,
      "loss": 0.7395,
      "step": 261
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.439095482587403e-05,
      "loss": 0.8222,
      "step": 262
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.370329353989597e-05,
      "loss": 0.8021,
      "step": 263
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.301642301401949e-05,
      "loss": 0.7854,
      "step": 264
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.233037657705302e-05,
      "loss": 0.7797,
      "step": 265
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.164518751781789e-05,
      "loss": 0.7943,
      "step": 266
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.096088908353315e-05,
      "loss": 0.8402,
      "step": 267
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.027751447820246e-05,
      "loss": 0.8083,
      "step": 268
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.959509686100267e-05,
      "loss": 0.7724,
      "step": 269
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.891366934467503e-05,
      "loss": 0.7647,
      "step": 270
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.823326499391846e-05,
      "loss": 0.7342,
      "step": 271
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.755391682378506e-05,
      "loss": 0.7705,
      "step": 272
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.687565779807824e-05,
      "loss": 0.8154,
      "step": 273
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.619852082775323e-05,
      "loss": 0.7415,
      "step": 274
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.552253876932006e-05,
      "loss": 0.8267,
      "step": 275
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.484774442324932e-05,
      "loss": 0.8021,
      "step": 276
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.417417053238065e-05,
      "loss": 0.7901,
      "step": 277
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.350184978033386e-05,
      "loss": 0.8075,
      "step": 278
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.283081478992308e-05,
      "loss": 0.8005,
      "step": 279
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.216109812157382e-05,
      "loss": 0.7494,
      "step": 280
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.149273227174317e-05,
      "loss": 0.7529,
      "step": 281
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.082574967134274e-05,
      "loss": 0.706,
      "step": 282
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.016018268416518e-05,
      "loss": 0.7667,
      "step": 283
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.949606360531375e-05,
      "loss": 0.7019,
      "step": 284
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.883342465963537e-05,
      "loss": 0.7613,
      "step": 285
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.817229800015682e-05,
      "loss": 0.8472,
      "step": 286
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.751271570652477e-05,
      "loss": 0.7839,
      "step": 287
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.685470978344905e-05,
      "loss": 0.7967,
      "step": 288
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.619831215914974e-05,
      "loss": 0.7803,
      "step": 289
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.554355468380795e-05,
      "loss": 0.7655,
      "step": 290
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.489046912802031e-05,
      "loss": 0.7805,
      "step": 291
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.423908718125742e-05,
      "loss": 0.8139,
      "step": 292
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.358944045032627e-05,
      "loss": 0.8033,
      "step": 293
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.294156045783634e-05,
      "loss": 0.8466,
      "step": 294
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.229547864067034e-05,
      "loss": 0.8037,
      "step": 295
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.16512263484586e-05,
      "loss": 0.8241,
      "step": 296
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.1008834842057995e-05,
      "loss": 0.8096,
      "step": 297
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.0368335292035e-05,
      "loss": 0.7818,
      "step": 298
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.972975877715339e-05,
      "loss": 0.7422,
      "step": 299
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.909313628286601e-05,
      "loss": 0.7525,
      "step": 300
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.845849869981137e-05,
      "loss": 0.7912,
      "step": 301
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.782587682231473e-05,
      "loss": 0.7835,
      "step": 302
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.71953013468939e-05,
      "loss": 0.7513,
      "step": 303
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6566802870769766e-05,
      "loss": 0.8177,
      "step": 304
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.5940411890381573e-05,
      "loss": 0.7986,
      "step": 305
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.531615879990729e-05,
      "loss": 0.8016,
      "step": 306
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.469407388978854e-05,
      "loss": 0.7473,
      "step": 307
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.407418734526118e-05,
      "loss": 0.8324,
      "step": 308
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.3456529244890274e-05,
      "loss": 0.7647,
      "step": 309
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.2841129559110894e-05,
      "loss": 0.7477,
      "step": 310
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.222801814877369e-05,
      "loss": 0.7838,
      "step": 311
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1617224763696123e-05,
      "loss": 0.7668,
      "step": 312
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1008779041218644e-05,
      "loss": 0.7891,
      "step": 313
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.040271050476697e-05,
      "loss": 0.8267,
      "step": 314
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9799048562419204e-05,
      "loss": 0.7796,
      "step": 315
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.919782250547911e-05,
      "loss": 0.7924,
      "step": 316
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.859906150705471e-05,
      "loss": 0.7837,
      "step": 317
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8002794620642776e-05,
      "loss": 0.811,
      "step": 318
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7409050778718944e-05,
      "loss": 0.7875,
      "step": 319
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.681785879133402e-05,
      "loss": 0.8032,
      "step": 320
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6229247344715985e-05,
      "loss": 0.8237,
      "step": 321
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.56432449998779e-05,
      "loss": 0.758,
      "step": 322
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.505988019123228e-05,
      "loss": 0.777,
      "step": 323
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.447918122521129e-05,
      "loss": 0.816,
      "step": 324
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3901176278893194e-05,
      "loss": 0.7499,
      "step": 325
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.332589339863512e-05,
      "loss": 0.7624,
      "step": 326
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.2753360498712305e-05,
      "loss": 0.7827,
      "step": 327
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.218360535996338e-05,
      "loss": 0.8106,
      "step": 328
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.16166556284428e-05,
      "loss": 0.8423,
      "step": 329
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.105253881407879e-05,
      "loss": 0.809,
      "step": 330
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.049128228933903e-05,
      "loss": 0.7933,
      "step": 331
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.993291328790209e-05,
      "loss": 0.7756,
      "step": 332
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.937745890333623e-05,
      "loss": 0.7669,
      "step": 333
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8824946087784544e-05,
      "loss": 0.8394,
      "step": 334
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.827540165065746e-05,
      "loss": 0.7931,
      "step": 335
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.772885225733147e-05,
      "loss": 0.7199,
      "step": 336
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.718532442785565e-05,
      "loss": 0.8122,
      "step": 337
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.664484453566449e-05,
      "loss": 0.7875,
      "step": 338
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.6107438806298486e-05,
      "loss": 0.7569,
      "step": 339
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.557313331613145e-05,
      "loss": 0.7351,
      "step": 340
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.504195399110516e-05,
      "loss": 0.7618,
      "step": 341
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.45139266054715e-05,
      "loss": 0.8037,
      "step": 342
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.398907678054177e-05,
      "loss": 0.776,
      "step": 343
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.346742998344348e-05,
      "loss": 0.7853,
      "step": 344
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.29490115258845e-05,
      "loss": 0.7861,
      "step": 345
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.243384656292511e-05,
      "loss": 0.7843,
      "step": 346
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.1921960091757074e-05,
      "loss": 0.7517,
      "step": 347
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.141337695049117e-05,
      "loss": 0.7762,
      "step": 348
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.090812181695146e-05,
      "loss": 0.8029,
      "step": 349
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.040621920747827e-05,
      "loss": 0.7374,
      "step": 350
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.9907693475738307e-05,
      "loss": 0.7354,
      "step": 351
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9412568811543174e-05,
      "loss": 0.7213,
      "step": 352
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8920869239675387e-05,
      "loss": 0.815,
      "step": 353
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.843261861872296e-05,
      "loss": 0.8181,
      "step": 354
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.794784063992131e-05,
      "loss": 0.8089,
      "step": 355
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7466558826003996e-05,
      "loss": 0.8126,
      "step": 356
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6988796530061266e-05,
      "loss": 0.739,
      "step": 357
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6514576934406777e-05,
      "loss": 0.7688,
      "step": 358
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6043923049452913e-05,
      "loss": 0.6952,
      "step": 359
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.557685771259414e-05,
      "loss": 0.7665,
      "step": 360
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5113403587098916e-05,
      "loss": 0.7898,
      "step": 361
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4653583161009942e-05,
      "loss": 0.7712,
      "step": 362
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4197418746053104e-05,
      "loss": 0.8119,
      "step": 363
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3744932476554717e-05,
      "loss": 0.7542,
      "step": 364
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3296146308367594e-05,
      "loss": 0.7718,
      "step": 365
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2851082017805703e-05,
      "loss": 0.7335,
      "step": 366
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2409761200587455e-05,
      "loss": 0.8223,
      "step": 367
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1972205270787783e-05,
      "loss": 0.8132,
      "step": 368
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1538435459799268e-05,
      "loss": 0.7725,
      "step": 369
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.1108472815301673e-05,
      "loss": 0.7681,
      "step": 370
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.068233820024088e-05,
      "loss": 0.7569,
      "step": 371
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0260052291816445e-05,
      "loss": 0.7739,
      "step": 372
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9841635580478325e-05,
      "loss": 0.7866,
      "step": 373
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9427108368932533e-05,
      "loss": 0.7849,
      "step": 374
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.901649077115617e-05,
      "loss": 0.7662,
      "step": 375
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.860980271142133e-05,
      "loss": 0.6951,
      "step": 376
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8207063923328237e-05,
      "loss": 0.7999,
      "step": 377
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7808293948847942e-05,
      "loss": 0.7626,
      "step": 378
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.74135121373739e-05,
      "loss": 0.7663,
      "step": 379
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.702273764478318e-05,
      "loss": 0.7274,
      "step": 380
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6635989432506903e-05,
      "loss": 0.7396,
      "step": 381
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.625328626661028e-05,
      "loss": 0.7429,
      "step": 382
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.587464671688187e-05,
      "loss": 0.7384,
      "step": 383
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5500089155932807e-05,
      "loss": 0.7554,
      "step": 384
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5129631758304941e-05,
      "loss": 0.7523,
      "step": 385
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4763292499589298e-05,
      "loss": 0.7054,
      "step": 386
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4401089155553582e-05,
      "loss": 0.6719,
      "step": 387
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4043039301279903e-05,
      "loss": 0.7845,
      "step": 388
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3689160310311721e-05,
      "loss": 0.7605,
      "step": 389
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.333946935381114e-05,
      "loss": 0.8225,
      "step": 390
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2993983399725373e-05,
      "loss": 0.6951,
      "step": 391
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2652719211963726e-05,
      "loss": 0.7516,
      "step": 392
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2315693349583923e-05,
      "loss": 0.8173,
      "step": 393
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1982922165988808e-05,
      "loss": 0.7253,
      "step": 394
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1654421808132687e-05,
      "loss": 0.8076,
      "step": 395
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1330208215737937e-05,
      "loss": 0.8309,
      "step": 396
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1010297120521528e-05,
      "loss": 0.7405,
      "step": 397
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0694704045431604e-05,
      "loss": 0.7937,
      "step": 398
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0383444303894452e-05,
      "loss": 0.7316,
      "step": 399
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.007653299907122e-05,
      "loss": 0.756,
      "step": 400
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.77398502312531e-06,
      "loss": 0.7262,
      "step": 401
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.475815056499526e-06,
      "loss": 0.7558,
      "step": 402
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.182037567204016e-06,
      "loss": 0.7594,
      "step": 403
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.892666810113958e-06,
      "loss": 0.7306,
      "step": 404
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.60771682627809e-06,
      "loss": 0.7518,
      "step": 405
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.327201442237276e-06,
      "loss": 0.763,
      "step": 406
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.051134269353688e-06,
      "loss": 0.7824,
      "step": 407
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.779528703150263e-06,
      "loss": 0.7717,
      "step": 408
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.512397922660852e-06,
      "loss": 0.7227,
      "step": 409
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.249754889790539e-06,
      "loss": 0.7398,
      "step": 410
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.99161234868686e-06,
      "loss": 0.8,
      "step": 411
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.737982825121392e-06,
      "loss": 0.7839,
      "step": 412
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.488878625881867e-06,
      "loss": 0.7311,
      "step": 413
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.244311838175143e-06,
      "loss": 0.7871,
      "step": 414
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.0042943290406384e-06,
      "loss": 0.8087,
      "step": 415
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.768837744774547e-06,
      "loss": 0.7269,
      "step": 416
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.537953510364613e-06,
      "loss": 0.6742,
      "step": 417
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.3116528289359425e-06,
      "loss": 0.752,
      "step": 418
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.089946681207247e-06,
      "loss": 0.7432,
      "step": 419
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.872845824958106e-06,
      "loss": 0.7794,
      "step": 420
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.660360794506946e-06,
      "loss": 0.7081,
      "step": 421
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.452501900199901e-06,
      "loss": 0.7495,
      "step": 422
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.249279227910485e-06,
      "loss": 0.7318,
      "step": 423
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.050702638550275e-06,
      "loss": 0.7864,
      "step": 424
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.856781767590334e-06,
      "loss": 0.7636,
      "step": 425
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.667526024593759e-06,
      "loss": 0.7483,
      "step": 426
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4829445927590852e-06,
      "loss": 0.717,
      "step": 427
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.303046428474643e-06,
      "loss": 0.7798,
      "step": 428
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.1278402608840185e-06,
      "loss": 0.7522,
      "step": 429
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.9573345914624794e-06,
      "loss": 0.8183,
      "step": 430
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7915376936044623e-06,
      "loss": 0.7446,
      "step": 431
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6304576122221035e-06,
      "loss": 0.7461,
      "step": 432
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4741021633549077e-06,
      "loss": 0.7495,
      "step": 433
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.322478933790506e-06,
      "loss": 0.7334,
      "step": 434
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.175595280696463e-06,
      "loss": 0.8137,
      "step": 435
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.033458331263338e-06,
      "loss": 0.7179,
      "step": 436
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8960749823588532e-06,
      "loss": 0.7921,
      "step": 437
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7634519001931914e-06,
      "loss": 0.8521,
      "step": 438
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6355955199956142e-06,
      "loss": 0.671,
      "step": 439
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5125120457021303e-06,
      "loss": 0.7294,
      "step": 440
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3942074496545165e-06,
      "loss": 0.8334,
      "step": 441
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2806874723104822e-06,
      "loss": 0.7709,
      "step": 442
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1719576219651585e-06,
      "loss": 0.7273,
      "step": 443
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0680231744837898e-06,
      "loss": 0.7483,
      "step": 444
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.68889173045806e-07,
      "loss": 0.7046,
      "step": 445
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.745604279000175e-07,
      "loss": 0.8129,
      "step": 446
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.850415161312463e-07,
      "loss": 0.7924,
      "step": 447
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.003367814382933e-07,
      "loss": 0.7779,
      "step": 448
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.204503339230505e-07,
      "loss": 0.714,
      "step": 449
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.453860498911945e-07,
      "loss": 0.8237,
      "step": 450
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.7514757166400304e-07,
      "loss": 0.7992,
      "step": 451
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.097383074016636e-07,
      "loss": 0.779,
      "step": 452
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.4916143093790543e-07,
      "loss": 0.7296,
      "step": 453
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.934198816259559e-07,
      "loss": 0.7767,
      "step": 454
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.42516364195966e-07,
      "loss": 0.7701,
      "step": 455
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9645334862373744e-07,
      "loss": 0.755,
      "step": 456
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5523307001088505e-07,
      "loss": 0.7407,
      "step": 457
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.1885752847637932e-07,
      "loss": 0.7914,
      "step": 458
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.732848905947943e-08,
      "loss": 0.7358,
      "step": 459
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.064748163413514e-08,
      "loss": 0.7522,
      "step": 460
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.881580083469061e-08,
      "loss": 0.7588,
      "step": 461
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.1834505993134634e-08,
      "loss": 0.7715,
      "step": 462
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.704421087619597e-09,
      "loss": 0.8239,
      "step": 463
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.4261347025489323e-09,
      "loss": 0.7666,
      "step": 464
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.7757,
      "step": 465
    },
    {
      "epoch": 1.0,
      "step": 465,
      "total_flos": 53904513761280.0,
      "train_loss": 0.8270689119574844,
      "train_runtime": 4897.453,
      "train_samples_per_second": 6.069,
      "train_steps_per_second": 0.095
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 465,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 53904513761280.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}