{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990627928772259,
  "eval_steps": 134,
  "global_step": 533,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.2302,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 3.179551601409912,
      "eval_runtime": 55.4081,
      "eval_samples_per_second": 24.329,
      "eval_steps_per_second": 1.029,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.1024,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 3.2198,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.0828,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 2.9847,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 2.7929,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.7878,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.6629,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 2.6465,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 2.5353,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.5154,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 2.498,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.4848,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.4794,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 2.4636,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.4932,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.4167,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.2e-05,
      "loss": 2.4665,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.6e-05,
      "loss": 2.3863,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 2.4089,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.4e-05,
      "loss": 2.4105,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.4187,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.3987,
      "step": 23
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.6e-05,
      "loss": 2.3898,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 2.4524,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010400000000000001,
      "loss": 2.4081,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010800000000000001,
      "loss": 2.4231,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011200000000000001,
      "loss": 2.3854,
      "step": 28
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000116,
      "loss": 2.4511,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012,
      "loss": 2.4137,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000124,
      "loss": 2.4189,
      "step": 31
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012800000000000002,
      "loss": 2.4123,
      "step": 32
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000132,
      "loss": 2.3896,
      "step": 33
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013600000000000003,
      "loss": 2.4448,
      "step": 34
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014,
      "loss": 2.3936,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000144,
      "loss": 2.4505,
      "step": 36
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000148,
      "loss": 2.4321,
      "step": 37
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000152,
      "loss": 2.4273,
      "step": 38
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00015600000000000002,
      "loss": 2.4394,
      "step": 39
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00016,
      "loss": 2.4661,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000164,
      "loss": 2.4693,
      "step": 41
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000168,
      "loss": 2.4416,
      "step": 42
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000172,
      "loss": 2.4219,
      "step": 43
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017600000000000002,
      "loss": 2.4929,
      "step": 44
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018,
      "loss": 2.5098,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018400000000000003,
      "loss": 2.5142,
      "step": 46
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000188,
      "loss": 2.4719,
      "step": 47
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000192,
      "loss": 2.4686,
      "step": 48
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000196,
      "loss": 2.4731,
      "step": 49
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 2.4735,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999788469031855,
      "loss": 2.5597,
      "step": 51
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999153885076487,
      "loss": 2.4634,
      "step": 52
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019998096274980728,
      "loss": 2.4727,
      "step": 53
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019996615683488039,
      "loss": 2.4603,
      "step": 54
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019994712173236604,
      "loss": 2.4999,
      "step": 55
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000199923858247567,
      "loss": 2.4886,
      "step": 56
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019989636736467278,
      "loss": 2.5067,
      "step": 57
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019986465024671794,
      "loss": 2.4929,
      "step": 58
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019982870823553308,
      "loss": 2.4504,
      "step": 59
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019978854285168784,
      "loss": 2.4733,
      "step": 60
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019974415579442675,
      "loss": 2.5515,
      "step": 61
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019969554894159723,
      "loss": 2.4798,
      "step": 62
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019964272434957022,
      "loss": 2.5098,
      "step": 63
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019958568425315314,
      "loss": 2.5603,
      "step": 64
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019952443106549533,
      "loss": 2.68,
      "step": 65
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019945896737798603,
      "loss": 2.7329,
      "step": 66
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001993892959601447,
      "loss": 2.5781,
      "step": 67
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019931541975950378,
      "loss": 2.5786,
      "step": 68
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019923734190148418,
      "loss": 2.5429,
      "step": 69
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001991550656892628,
      "loss": 2.4816,
      "step": 70
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019906859460363307,
      "loss": 2.5149,
      "step": 71
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019897793230285748,
      "loss": 2.5982,
      "step": 72
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019888308262251285,
      "loss": 2.5852,
      "step": 73
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019878404957532814,
      "loss": 2.5715,
      "step": 74
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019868083735101463,
      "loss": 2.52,
      "step": 75
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019857345031608868,
      "loss": 2.5562,
      "step": 76
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001984618930136869,
      "loss": 2.4902,
      "step": 77
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001983461701633742,
      "loss": 2.4734,
      "step": 78
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001982262866609439,
      "loss": 2.4944,
      "step": 79
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019810224757821064,
      "loss": 2.4315,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019797405816279585,
      "loss": 2.4392,
      "step": 81
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019784172383790582,
      "loss": 2.4658,
      "step": 82
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019770525020210204,
      "loss": 2.4779,
      "step": 83
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019756464302906465,
      "loss": 2.4132,
      "step": 84
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019741990826734794,
      "loss": 2.4443,
      "step": 85
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001972710520401287,
      "loss": 2.5367,
      "step": 86
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001971180806449473,
      "loss": 2.4563,
      "step": 87
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019696100055344124,
      "loss": 2.4693,
      "step": 88
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001967998184110713,
      "loss": 2.4599,
      "step": 89
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001966345410368404,
      "loss": 2.458,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019646517542300514,
      "loss": 2.4395,
      "step": 91
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019629172873477995,
      "loss": 2.453,
      "step": 92
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000196114208310034,
      "loss": 2.4638,
      "step": 93
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019593262165898076,
      "loss": 2.4314,
      "step": 94
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019574697646386027,
      "loss": 2.4776,
      "step": 95
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001955572805786141,
      "loss": 2.4625,
      "step": 96
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019536354202855308,
      "loss": 2.4451,
      "step": 97
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001951657690100178,
      "loss": 2.4473,
      "step": 98
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019496396989003193,
      "loss": 2.4928,
      "step": 99
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001947581532059481,
      "loss": 2.4132,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001945483276650868,
      "loss": 2.4591,
      "step": 101
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019433450214436797,
      "loss": 2.465,
      "step": 102
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001941166856899355,
      "loss": 2.3805,
      "step": 103
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001938948875167745,
      "loss": 2.4012,
      "step": 104
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019366911700832145,
      "loss": 2.3852,
      "step": 105
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019343938371606712,
      "loss": 2.3642,
      "step": 106
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019320569735915271,
      "loss": 2.39,
      "step": 107
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001929680678239585,
      "loss": 2.4373,
      "step": 108
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001927265051636856,
      "loss": 2.4666,
      "step": 109
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019248101959793066,
      "loss": 2.4267,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001922316215122536,
      "loss": 2.4158,
      "step": 111
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001919783214577381,
      "loss": 2.3634,
      "step": 112
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019172113015054532,
      "loss": 2.4179,
      "step": 113
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001914600584714605,
      "loss": 2.364,
      "step": 114
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019119511746543263,
      "loss": 2.3435,
      "step": 115
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019092631834110723,
      "loss": 2.2741,
      "step": 116
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019065367247035213,
      "loss": 2.3201,
      "step": 117
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019037719138777627,
      "loss": 2.4475,
      "step": 118
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001900968867902419,
      "loss": 2.3559,
      "step": 119
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001898127705363696,
      "loss": 2.3547,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018952485464603664,
      "loss": 2.2853,
      "step": 121
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018923315129986835,
      "loss": 2.4317,
      "step": 122
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018893767283872305,
      "loss": 2.3741,
      "step": 123
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001886384317631697,
      "loss": 2.2959,
      "step": 124
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018833544073295917,
      "loss": 2.3672,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018802871256648872,
      "loss": 2.3465,
      "step": 126
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018771826024025946,
      "loss": 2.2856,
      "step": 127
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018740409688832764,
      "loss": 2.28,
      "step": 128
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018708623580174889,
      "loss": 2.2592,
      "step": 129
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018676469042801588,
      "loss": 2.3545,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018643947437048944,
      "loss": 2.3505,
      "step": 131
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018611060138782305,
      "loss": 2.3164,
      "step": 132
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018577808539338087,
      "loss": 2.3547,
      "step": 133
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018544194045464886,
      "loss": 2.3772,
      "step": 134
    },
    {
      "epoch": 0.25,
      "eval_loss": 2.3696775436401367,
      "eval_runtime": 55.6786,
      "eval_samples_per_second": 24.21,
      "eval_steps_per_second": 1.024,
      "step": 134
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018510218079263995,
      "loss": 2.4287,
      "step": 135
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018475882078129212,
      "loss": 2.3653,
      "step": 136
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018441187494686053,
      "loss": 2.3392,
      "step": 137
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018406135796730287,
      "loss": 2.3177,
      "step": 138
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018370728467165828,
      "loss": 2.3777,
      "step": 139
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001833496700394202,
      "loss": 2.3158,
      "step": 140
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018298852919990252,
      "loss": 2.3367,
      "step": 141
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001826238774315995,
      "loss": 2.231,
      "step": 142
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018225573016153945,
      "loss": 2.2859,
      "step": 143
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001818841029646321,
      "loss": 2.2594,
      "step": 144
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018150901156300956,
      "loss": 2.2945,
      "step": 145
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018113047182536127,
      "loss": 2.2277,
      "step": 146
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018074849976626274,
      "loss": 2.285,
      "step": 147
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018036311154549784,
      "loss": 2.287,
      "step": 148
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017997432346737524,
      "loss": 2.2308,
      "step": 149
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017958215198003865,
      "loss": 2.3425,
      "step": 150
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017918661367477098,
      "loss": 2.1763,
      "step": 151
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017878772528529232,
      "loss": 2.3044,
      "step": 152
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017838550368705217,
      "loss": 2.1648,
      "step": 153
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001779799658965153,
      "loss": 2.3134,
      "step": 154
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000177571129070442,
      "loss": 2.2027,
      "step": 155
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001771590105051622,
      "loss": 2.2242,
      "step": 156
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017674362763584375,
      "loss": 2.2897,
      "step": 157
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017632499803575474,
      "loss": 2.1541,
      "step": 158
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017590313941552002,
      "loss": 2.173,
      "step": 159
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001754780696223722,
      "loss": 2.2662,
      "step": 160
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017504980663939613,
      "loss": 2.2121,
      "step": 161
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017461836858476856,
      "loss": 2.2703,
      "step": 162
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017418377371099136,
      "loss": 2.2875,
      "step": 163
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017374604040411935,
      "loss": 2.2159,
      "step": 164
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017330518718298264,
      "loss": 2.2517,
      "step": 165
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017286123269840293,
      "loss": 2.2079,
      "step": 166
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017241419573240462,
      "loss": 2.1622,
      "step": 167
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001719640951974202,
      "loss": 2.2229,
      "step": 168
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017151095013548994,
      "loss": 2.2151,
      "step": 169
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017105477971745666,
      "loss": 2.232,
      "step": 170
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017059560324215436,
      "loss": 2.2971,
      "step": 171
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017013344013559197,
      "loss": 2.1772,
      "step": 172
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016966830995013133,
      "loss": 2.2384,
      "step": 173
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016920023236366002,
      "loss": 2.1376,
      "step": 174
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016872922717875923,
      "loss": 2.1521,
      "step": 175
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016825531432186543,
      "loss": 2.2222,
      "step": 176
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016777851384242766,
      "loss": 2.1104,
      "step": 177
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001672988459120594,
      "loss": 2.2398,
      "step": 178
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016681633082368498,
      "loss": 2.1505,
      "step": 179
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001663309889906811,
      "loss": 2.1549,
      "step": 180
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001658428409460134,
      "loss": 2.2301,
      "step": 181
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001653519073413675,
      "loss": 2.1479,
      "step": 182
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001648582089462756,
      "loss": 2.1095,
      "step": 183
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001643617666472376,
      "loss": 2.1487,
      "step": 184
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016386260144683745,
      "loss": 2.1334,
      "step": 185
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016336073446285485,
      "loss": 2.0953,
      "step": 186
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016285618692737157,
      "loss": 2.1386,
      "step": 187
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016234898018587337,
      "loss": 2.1415,
      "step": 188
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001618391356963468,
      "loss": 2.0492,
      "step": 189
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016132667502837165,
      "loss": 2.056,
      "step": 190
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016081161986220807,
      "loss": 2.2249,
      "step": 191
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016029399198787974,
      "loss": 2.1115,
      "step": 192
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00015977381330425163,
      "loss": 2.1275,
      "step": 193
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00015925110581810394,
      "loss": 1.9615,
      "step": 194
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015872589164320078,
      "loss": 2.1591,
      "step": 195
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001581981929993547,
      "loss": 2.1233,
      "step": 196
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015766803221148673,
      "loss": 2.2147,
      "step": 197
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001571354317086818,
      "loss": 2.1625,
      "step": 198
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001566004140232399,
      "loss": 2.0565,
      "step": 199
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015606300178972287,
      "loss": 2.1389,
      "step": 200
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015552321774399666,
      "loss": 2.126,
      "step": 201
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015498108472226964,
      "loss": 2.1251,
      "step": 202
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015443662566012645,
      "loss": 2.0343,
      "step": 203
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015388986359155758,
      "loss": 2.076,
      "step": 204
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00015334082164798489,
      "loss": 1.9876,
      "step": 205
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015278952305728324,
      "loss": 2.1316,
      "step": 206
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015223599114279755,
      "loss": 2.06,
      "step": 207
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015168024932235617,
      "loss": 2.0479,
      "step": 208
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015112232110728015,
      "loss": 1.9749,
      "step": 209
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015056223010138857,
      "loss": 2.1165,
      "step": 210
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.0656,
      "step": 211
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014943565458893,
      "loss": 2.0241,
      "step": 212
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014886921774348472,
      "loss": 2.0393,
      "step": 213
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014830071342745112,
      "loss": 2.0376,
      "step": 214
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014773016569208283,
      "loss": 2.0739,
      "step": 215
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001471575986750828,
      "loss": 2.0254,
      "step": 216
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001465830365995821,
      "loss": 2.0989,
      "step": 217
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014600650377311522,
      "loss": 2.1056,
      "step": 218
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014542802458659152,
      "loss": 2.0197,
      "step": 219
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014484762351326343,
      "loss": 2.055,
      "step": 220
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001442653251076912,
      "loss": 2.058,
      "step": 221
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014368115400470392,
      "loss": 1.9918,
      "step": 222
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014309513491835734,
      "loss": 2.0102,
      "step": 223
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014250729264088843,
      "loss": 2.0356,
      "step": 224
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014191765204166643,
      "loss": 2.0166,
      "step": 225
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014132623806614063,
      "loss": 1.9309,
      "step": 226
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014073307573478526,
      "loss": 2.0886,
      "step": 227
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014013819014204075,
      "loss": 1.973,
      "step": 228
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013954160645525217,
      "loss": 1.9996,
      "step": 229
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013894334991360448,
      "loss": 1.9444,
      "step": 230
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013834344582705474,
      "loss": 2.0583,
      "step": 231
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00013774191957526143,
      "loss": 1.9805,
      "step": 232
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013713879660651068,
      "loss": 2.0694,
      "step": 233
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013653410243663952,
      "loss": 2.0294,
      "step": 234
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013592786264795658,
      "loss": 1.966,
      "step": 235
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001353201028881598,
      "loss": 1.8961,
      "step": 236
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013471084886925122,
      "loss": 2.0144,
      "step": 237
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013410012636644935,
      "loss": 1.9803,
      "step": 238
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013348796121709862,
      "loss": 1.984,
      "step": 239
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001328743793195764,
      "loss": 2.011,
      "step": 240
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013225940663219726,
      "loss": 1.9768,
      "step": 241
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013164306917211476,
      "loss": 1.9221,
      "step": 242
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013102539301422086,
      "loss": 1.9793,
      "step": 243
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013040640429004267,
      "loss": 1.944,
      "step": 244
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000129786129186637,
      "loss": 1.8944,
      "step": 245
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001291645939454825,
      "loss": 2.0456,
      "step": 246
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012854182486136942,
      "loss": 1.992,
      "step": 247
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012791784828128724,
      "loss": 1.9942,
      "step": 248
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012729269060330999,
      "loss": 1.9879,
      "step": 249
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012666637827547932,
      "loss": 1.9231,
      "step": 250
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012603893779468604,
      "loss": 1.9368,
      "step": 251
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001254103957055485,
      "loss": 1.856,
      "step": 252
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012478077859929,
      "loss": 1.9358,
      "step": 253
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001241501131126138,
      "loss": 1.995,
      "step": 254
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012351842592657613,
      "loss": 1.8455,
      "step": 255
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012288574376545733,
      "loss": 1.8912,
      "step": 256
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012225209339563145,
      "loss": 1.9491,
      "step": 257
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012161750162443371,
      "loss": 1.8341,
      "step": 258
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012098199529902648,
      "loss": 1.8941,
      "step": 259
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001203456013052634,
      "loss": 1.8808,
      "step": 260
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00011970834656655199,
      "loss": 1.8794,
      "step": 261
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00011907025804271461,
      "loss": 1.8828,
      "step": 262
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00011843136272884794,
      "loss": 1.818,
      "step": 263
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00011779168765418079,
      "loss": 1.847,
      "step": 264
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011715125988093074,
      "loss": 1.8181,
      "step": 265
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011651010650315923,
      "loss": 1.8297,
      "step": 266
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011586825464562514,
      "loss": 1.9047,
      "step": 267
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011522573146263744,
      "loss": 1.8538,
      "step": 268
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.8599034547805786,
      "eval_runtime": 55.6724,
      "eval_samples_per_second": 24.213,
      "eval_steps_per_second": 1.024,
      "step": 268
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011458256413690633,
      "loss": 2.0143,
      "step": 269
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011393877987839327,
      "loss": 1.7532,
      "step": 270
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011329440592315971,
      "loss": 1.825,
      "step": 271
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011264946953221496,
      "loss": 1.7548,
      "step": 272
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011200399799036288,
      "loss": 1.8505,
      "step": 273
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011135801860504749,
      "loss": 1.8608,
      "step": 274
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011071155870519777,
      "loss": 1.8352,
      "step": 275
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011006464564007138,
      "loss": 1.9602,
      "step": 276
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010941730677809772,
      "loss": 1.7833,
      "step": 277
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010876956950572006,
      "loss": 1.8567,
      "step": 278
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010812146122623683,
      "loss": 1.8606,
      "step": 279
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010747300935864243,
      "loss": 1.7611,
      "step": 280
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001068242413364671,
      "loss": 1.8188,
      "step": 281
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010617518460661644,
      "loss": 1.7576,
      "step": 282
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010552586662821009,
      "loss": 1.8525,
      "step": 283
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010487631487142017,
      "loss": 1.7134,
      "step": 284
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010422655681630917,
      "loss": 1.8414,
      "step": 285
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010357661995166705,
      "loss": 1.815,
      "step": 286
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010292653177384876,
      "loss": 1.7789,
      "step": 287
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010227631978561056,
      "loss": 1.82,
      "step": 288
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010162601149494676,
      "loss": 1.8095,
      "step": 289
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010097563441392581,
      "loss": 1.7666,
      "step": 290
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010032521605752646,
      "loss": 1.8287,
      "step": 291
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.967478394247357e-05,
      "loss": 1.8818,
      "step": 292
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.90243655860742e-05,
      "loss": 1.7085,
      "step": 293
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.837398850505324e-05,
      "loss": 1.7111,
      "step": 294
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.772368021438943e-05,
      "loss": 1.7282,
      "step": 295
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.707346822615128e-05,
      "loss": 1.8105,
      "step": 296
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.642338004833295e-05,
      "loss": 1.7592,
      "step": 297
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.577344318369084e-05,
      "loss": 1.6769,
      "step": 298
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.512368512857984e-05,
      "loss": 1.721,
      "step": 299
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.447413337178995e-05,
      "loss": 1.6353,
      "step": 300
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.38248153933836e-05,
      "loss": 1.654,
      "step": 301
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.317575866353292e-05,
      "loss": 1.7222,
      "step": 302
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.252699064135758e-05,
      "loss": 1.7727,
      "step": 303
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.187853877376318e-05,
      "loss": 1.8161,
      "step": 304
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.123043049427995e-05,
      "loss": 1.7088,
      "step": 305
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.058269322190228e-05,
      "loss": 1.7274,
      "step": 306
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.993535435992867e-05,
      "loss": 1.6949,
      "step": 307
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.928844129480227e-05,
      "loss": 1.7429,
      "step": 308
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.86419813949525e-05,
      "loss": 1.7443,
      "step": 309
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.799600200963716e-05,
      "loss": 1.5959,
      "step": 310
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.735053046778506e-05,
      "loss": 1.6557,
      "step": 311
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.670559407684034e-05,
      "loss": 1.6743,
      "step": 312
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.606122012160676e-05,
      "loss": 1.7672,
      "step": 313
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.541743586309365e-05,
      "loss": 1.6774,
      "step": 314
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.477426853736257e-05,
      "loss": 1.6597,
      "step": 315
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.413174535437487e-05,
      "loss": 1.7112,
      "step": 316
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.348989349684076e-05,
      "loss": 1.6499,
      "step": 317
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.284874011906927e-05,
      "loss": 1.625,
      "step": 318
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.220831234581922e-05,
      "loss": 1.6922,
      "step": 319
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.156863727115211e-05,
      "loss": 1.6797,
      "step": 320
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.092974195728542e-05,
      "loss": 1.6772,
      "step": 321
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.029165343344805e-05,
      "loss": 1.6439,
      "step": 322
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.965439869473664e-05,
      "loss": 1.6358,
      "step": 323
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.901800470097355e-05,
      "loss": 1.6808,
      "step": 324
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.838249837556629e-05,
      "loss": 1.6013,
      "step": 325
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.774790660436858e-05,
      "loss": 1.6607,
      "step": 326
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.711425623454267e-05,
      "loss": 1.7424,
      "step": 327
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.648157407342386e-05,
      "loss": 1.6395,
      "step": 328
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.584988688738622e-05,
      "loss": 1.7159,
      "step": 329
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.521922140071002e-05,
      "loss": 1.57,
      "step": 330
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.458960429445157e-05,
      "loss": 1.6616,
      "step": 331
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.396106220531398e-05,
      "loss": 1.6996,
      "step": 332
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.333362172452065e-05,
      "loss": 1.6087,
      "step": 333
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.270730939669006e-05,
      "loss": 1.6516,
      "step": 334
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.208215171871277e-05,
      "loss": 1.6155,
      "step": 335
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.145817513863057e-05,
      "loss": 1.7189,
      "step": 336
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.08354060545175e-05,
      "loss": 1.6217,
      "step": 337
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.021387081336301e-05,
      "loss": 1.6072,
      "step": 338
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.959359570995738e-05,
      "loss": 1.6163,
      "step": 339
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.897460698577918e-05,
      "loss": 1.5596,
      "step": 340
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.835693082788525e-05,
      "loss": 1.5035,
      "step": 341
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.774059336780277e-05,
      "loss": 1.5525,
      "step": 342
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.712562068042361e-05,
      "loss": 1.578,
      "step": 343
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.651203878290139e-05,
      "loss": 1.5724,
      "step": 344
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.589987363355068e-05,
      "loss": 1.6454,
      "step": 345
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.528915113074879e-05,
      "loss": 1.5945,
      "step": 346
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.46798971118402e-05,
      "loss": 1.5424,
      "step": 347
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.407213735204343e-05,
      "loss": 1.6592,
      "step": 348
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.34658975633605e-05,
      "loss": 1.6077,
      "step": 349
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.286120339348935e-05,
      "loss": 1.5977,
      "step": 350
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.225808042473858e-05,
      "loss": 1.6713,
      "step": 351
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.165655417294527e-05,
      "loss": 1.4955,
      "step": 352
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.105665008639557e-05,
      "loss": 1.5353,
      "step": 353
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.045839354474786e-05,
      "loss": 1.4601,
      "step": 354
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.986180985795926e-05,
      "loss": 1.5212,
      "step": 355
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.926692426521474e-05,
      "loss": 1.5534,
      "step": 356
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.867376193385936e-05,
      "loss": 1.5822,
      "step": 357
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.8082347958333625e-05,
      "loss": 1.583,
      "step": 358
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.749270735911158e-05,
      "loss": 1.484,
      "step": 359
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.6904865081642676e-05,
      "loss": 1.404,
      "step": 360
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.631884599529611e-05,
      "loss": 1.4449,
      "step": 361
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.573467489230879e-05,
      "loss": 1.553,
      "step": 362
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.515237648673656e-05,
      "loss": 1.4247,
      "step": 363
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.457197541340853e-05,
      "loss": 1.4967,
      "step": 364
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.399349622688479e-05,
      "loss": 1.5317,
      "step": 365
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.3416963400417905e-05,
      "loss": 1.5611,
      "step": 366
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.284240132491727e-05,
      "loss": 1.588,
      "step": 367
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.226983430791722e-05,
      "loss": 1.5095,
      "step": 368
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.16992865725489e-05,
      "loss": 1.4771,
      "step": 369
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.113078225651529e-05,
      "loss": 1.4928,
      "step": 370
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.0564345411070025e-05,
      "loss": 1.5018,
      "step": 371
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.4768,
      "step": 372
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.943776989861145e-05,
      "loss": 1.5867,
      "step": 373
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.8877678892719866e-05,
      "loss": 1.4886,
      "step": 374
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.831975067764387e-05,
      "loss": 1.5394,
      "step": 375
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.7764008857202425e-05,
      "loss": 1.4141,
      "step": 376
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.721047694271676e-05,
      "loss": 1.4668,
      "step": 377
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.665917835201512e-05,
      "loss": 1.507,
      "step": 378
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.611013640844245e-05,
      "loss": 1.4728,
      "step": 379
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.556337433987359e-05,
      "loss": 1.4566,
      "step": 380
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.501891527773038e-05,
      "loss": 1.4617,
      "step": 381
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.447678225600337e-05,
      "loss": 1.4384,
      "step": 382
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.393699821027716e-05,
      "loss": 1.5093,
      "step": 383
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.3399585976760105e-05,
      "loss": 1.4602,
      "step": 384
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.286456829131821e-05,
      "loss": 1.3591,
      "step": 385
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.2331967788513295e-05,
      "loss": 1.4804,
      "step": 386
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.180180700064531e-05,
      "loss": 1.4427,
      "step": 387
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.127410835679926e-05,
      "loss": 1.3901,
      "step": 388
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.074889418189608e-05,
      "loss": 1.4564,
      "step": 389
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.022618669574839e-05,
      "loss": 1.4548,
      "step": 390
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.97060080121203e-05,
      "loss": 1.4485,
      "step": 391
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.9188380137791936e-05,
      "loss": 1.418,
      "step": 392
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.8673324971628357e-05,
      "loss": 1.4664,
      "step": 393
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.816086430365321e-05,
      "loss": 1.4593,
      "step": 394
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 1.4556,
      "step": 395
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.7143813072628465e-05,
      "loss": 1.3472,
      "step": 396
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.663926553714518e-05,
      "loss": 1.2962,
      "step": 397
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.613739855316257e-05,
      "loss": 1.4875,
      "step": 398
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.563823335276244e-05,
      "loss": 1.382,
      "step": 399
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.5141791053724405e-05,
      "loss": 1.3698,
      "step": 400
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.46480926586325e-05,
      "loss": 1.4564,
      "step": 401
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.415715905398664e-05,
      "loss": 1.5117,
      "step": 402
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.422906517982483,
      "eval_runtime": 55.7451,
      "eval_samples_per_second": 24.182,
      "eval_steps_per_second": 1.023,
      "step": 402
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.366901100931892e-05,
      "loss": 1.407,
      "step": 403
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.3183669176315045e-05,
      "loss": 1.3833,
      "step": 404
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.27011540879406e-05,
      "loss": 1.4071,
      "step": 405
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.2221486157572324e-05,
      "loss": 1.439,
      "step": 406
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.174468567813461e-05,
      "loss": 1.4009,
      "step": 407
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.1270772821240776e-05,
      "loss": 1.417,
      "step": 408
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.079976763633996e-05,
      "loss": 1.2888,
      "step": 409
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.033169004986873e-05,
      "loss": 1.475,
      "step": 410
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.986655986440805e-05,
      "loss": 1.3512,
      "step": 411
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.940439675784563e-05,
      "loss": 1.2825,
      "step": 412
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.894522028254334e-05,
      "loss": 1.3424,
      "step": 413
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.8489049864510054e-05,
      "loss": 1.391,
      "step": 414
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.803590480257985e-05,
      "loss": 1.2999,
      "step": 415
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.7585804267595384e-05,
      "loss": 1.39,
      "step": 416
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.7138767301597067e-05,
      "loss": 1.3686,
      "step": 417
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.669481281701739e-05,
      "loss": 1.3871,
      "step": 418
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.6253959595880673e-05,
      "loss": 1.3755,
      "step": 419
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.581622628900868e-05,
      "loss": 1.4435,
      "step": 420
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5381631415231454e-05,
      "loss": 1.3808,
      "step": 421
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.495019336060387e-05,
      "loss": 1.4653,
      "step": 422
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.4521930377627812e-05,
      "loss": 1.3653,
      "step": 423
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.4096860584479974e-05,
      "loss": 1.4224,
      "step": 424
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.367500196424529e-05,
      "loss": 1.3416,
      "step": 425
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.3256372364156286e-05,
      "loss": 1.3177,
      "step": 426
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.2840989494837793e-05,
      "loss": 1.403,
      "step": 427
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.242887092955801e-05,
      "loss": 1.4582,
      "step": 428
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.202003410348473e-05,
      "loss": 1.4202,
      "step": 429
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1614496312947852e-05,
      "loss": 1.3492,
      "step": 430
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.121227471470768e-05,
      "loss": 1.201,
      "step": 431
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0813386325229055e-05,
      "loss": 1.3131,
      "step": 432
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0417848019961372e-05,
      "loss": 1.3579,
      "step": 433
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.002567653262479e-05,
      "loss": 1.3943,
      "step": 434
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9636888454502178e-05,
      "loss": 1.4777,
      "step": 435
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.925150023373726e-05,
      "loss": 1.4449,
      "step": 436
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.8869528174638752e-05,
      "loss": 1.3711,
      "step": 437
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.8490988436990488e-05,
      "loss": 1.2473,
      "step": 438
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.8115897035367934e-05,
      "loss": 1.4266,
      "step": 439
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.774426983846058e-05,
      "loss": 1.3646,
      "step": 440
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7376122568400532e-05,
      "loss": 1.2857,
      "step": 441
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7011470800097496e-05,
      "loss": 1.3349,
      "step": 442
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6650329960579792e-05,
      "loss": 1.3196,
      "step": 443
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6292715328341712e-05,
      "loss": 1.3533,
      "step": 444
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.593864203269716e-05,
      "loss": 1.3276,
      "step": 445
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5588125053139468e-05,
      "loss": 1.434,
      "step": 446
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5241179218707891e-05,
      "loss": 1.4045,
      "step": 447
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4897819207360098e-05,
      "loss": 1.4106,
      "step": 448
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4558059545351143e-05,
      "loss": 1.3125,
      "step": 449
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4221914606619135e-05,
      "loss": 1.2878,
      "step": 450
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3889398612176941e-05,
      "loss": 1.3981,
      "step": 451
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3560525629510568e-05,
      "loss": 1.2914,
      "step": 452
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3235309571984156e-05,
      "loss": 1.2669,
      "step": 453
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2913764198251132e-05,
      "loss": 1.405,
      "step": 454
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.259590311167238e-05,
      "loss": 1.3743,
      "step": 455
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2281739759740574e-05,
      "loss": 1.2633,
      "step": 456
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1971287433511313e-05,
      "loss": 1.2473,
      "step": 457
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.166455926704082e-05,
      "loss": 1.366,
      "step": 458
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1361568236830323e-05,
      "loss": 1.286,
      "step": 459
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1062327161276963e-05,
      "loss": 1.3363,
      "step": 460
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0766848700131648e-05,
      "loss": 1.3854,
      "step": 461
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0475145353963389e-05,
      "loss": 1.4039,
      "step": 462
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.01872294636304e-05,
      "loss": 1.446,
      "step": 463
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.903113209758096e-06,
      "loss": 1.3371,
      "step": 464
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.62280861222372e-06,
      "loss": 1.3936,
      "step": 465
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.346327529647868e-06,
      "loss": 1.2979,
      "step": 466
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.073681658892775e-06,
      "loss": 1.3019,
      "step": 467
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.804882534567382e-06,
      "loss": 1.3869,
      "step": 468
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.53994152853952e-06,
      "loss": 1.3959,
      "step": 469
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.278869849454718e-06,
      "loss": 1.2561,
      "step": 470
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.021678542261924e-06,
      "loss": 1.3396,
      "step": 471
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.76837848774642e-06,
      "loss": 1.3443,
      "step": 472
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.5189804020693536e-06,
      "loss": 1.3167,
      "step": 473
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.2734948363144206e-06,
      "loss": 1.2964,
      "step": 474
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.031932176041523e-06,
      "loss": 1.3125,
      "step": 475
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.794302640847294e-06,
      "loss": 1.2952,
      "step": 476
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.560616283932897e-06,
      "loss": 1.2655,
      "step": 477
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.330882991678577e-06,
      "loss": 1.3877,
      "step": 478
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.1051124832254944e-06,
      "loss": 1.33,
      "step": 479
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.883314310064492e-06,
      "loss": 1.3948,
      "step": 480
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.6654978556320405e-06,
      "loss": 1.3569,
      "step": 481
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.451672334913216e-06,
      "loss": 1.2655,
      "step": 482
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.2418467940519185e-06,
      "loss": 1.3639,
      "step": 483
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.036030109968082e-06,
      "loss": 1.427,
      "step": 484
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.834230989982213e-06,
      "loss": 1.3306,
      "step": 485
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.63645797144695e-06,
      "loss": 1.3196,
      "step": 486
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.442719421385922e-06,
      "loss": 1.2518,
      "step": 487
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.253023536139733e-06,
      "loss": 1.2918,
      "step": 488
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.067378341019257e-06,
      "loss": 1.3128,
      "step": 489
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.885791689966023e-06,
      "loss": 1.3452,
      "step": 490
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.7082712652200867e-06,
      "loss": 1.4055,
      "step": 491
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5348245769948773e-06,
      "loss": 1.2194,
      "step": 492
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.3654589631595955e-06,
      "loss": 1.338,
      "step": 493
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.2001815889286856e-06,
      "loss": 1.158,
      "step": 494
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.0389994465587545e-06,
      "loss": 1.3595,
      "step": 495
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.881919355052709e-06,
      "loss": 1.2421,
      "step": 496
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.728947959871353e-06,
      "loss": 1.3172,
      "step": 497
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.580091732652101e-06,
      "loss": 1.2558,
      "step": 498
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.435356970935354e-06,
      "loss": 1.2086,
      "step": 499
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.294749797897955e-06,
      "loss": 1.3303,
      "step": 500
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.158276162094197e-06,
      "loss": 1.3262,
      "step": 501
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0259418372041485e-06,
      "loss": 1.3066,
      "step": 502
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8977524217893783e-06,
      "loss": 1.3071,
      "step": 503
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7737133390561046e-06,
      "loss": 1.338,
      "step": 504
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6538298366257976e-06,
      "loss": 1.3407,
      "step": 505
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5381069863131037e-06,
      "loss": 1.4355,
      "step": 506
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.426549683911349e-06,
      "loss": 1.341,
      "step": 507
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3191626489853615e-06,
      "loss": 1.3546,
      "step": 508
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2159504246718522e-06,
      "loss": 1.3322,
      "step": 509
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.1169173774871478e-06,
      "loss": 1.3374,
      "step": 510
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0220676971425257e-06,
      "loss": 1.3706,
      "step": 511
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.314053963669245e-07,
      "loss": 1.3249,
      "step": 512
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.44934310737211e-07,
      "loss": 1.4235,
      "step": 513
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.62658098515856e-07,
      "loss": 1.2759,
      "step": 514
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.845802404962243e-07,
      "loss": 1.342,
      "step": 515
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.107040398553144e-07,
      "loss": 1.4004,
      "step": 516
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.410326220139705e-07,
      "loss": 1.3671,
      "step": 517
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.7556893450466653e-07,
      "loss": 1.2746,
      "step": 518
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.143157468468717e-07,
      "loss": 1.3585,
      "step": 519
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.5727565042978915e-07,
      "loss": 1.3258,
      "step": 520
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.044510584027771e-07,
      "loss": 1.2909,
      "step": 521
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.558442055732524e-07,
      "loss": 1.2929,
      "step": 522
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.1145714831216634e-07,
      "loss": 1.389,
      "step": 523
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.7129176446692984e-07,
      "loss": 1.4132,
      "step": 524
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3534975328205467e-07,
      "loss": 1.2848,
      "step": 525
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0363263532724432e-07,
      "loss": 1.3483,
      "step": 526
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.614175243301213e-08,
      "loss": 1.3588,
      "step": 527
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.287826763398229e-08,
      "loss": 1.3012,
      "step": 528
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.384316511964025e-08,
      "loss": 1.3524,
      "step": 529
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9037250192732726e-08,
      "loss": 1.3232,
      "step": 530
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.46114923513941e-09,
      "loss": 1.3092,
      "step": 531
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.1153096814607865e-09,
      "loss": 1.2231,
      "step": 532
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.4531,
      "step": 533
    }
  ],
  "logging_steps": 1,
  "max_steps": 533,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 4.023661144257331e+17,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}