{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8665302683836803,
  "eval_steps": 500,
  "global_step": 450,
  "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": 0.6869,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8396,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 0.7489,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7252,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 0.6548,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 0.8022,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.6524,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.6981,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 0.7488,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 0.6368,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6891,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 0.7968,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.6912,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.8452,
      "step": 14
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 0.6989,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.6685,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.5469,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.2e-05,
      "loss": 0.7915,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.6e-05,
      "loss": 0.7744,
      "step": 19
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 0.6804,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.4e-05,
      "loss": 0.7796,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.706,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.6798,
      "step": 23
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.6e-05,
      "loss": 0.6333,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 0.6012,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.52,
      "step": 26
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.6583,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.7354,
      "step": 28
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000116,
      "loss": 0.6296,
      "step": 29
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012,
      "loss": 0.6352,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000124,
      "loss": 0.6007,
      "step": 31
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.5659,
      "step": 32
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000132,
      "loss": 0.5138,
      "step": 33
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.6639,
      "step": 34
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014,
      "loss": 0.5934,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000144,
      "loss": 0.5233,
      "step": 36
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000148,
      "loss": 0.5307,
      "step": 37
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000152,
      "loss": 0.5928,
      "step": 38
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.5908,
      "step": 39
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016,
      "loss": 0.6366,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000164,
      "loss": 0.5972,
      "step": 41
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000168,
      "loss": 0.4825,
      "step": 42
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000172,
      "loss": 0.6783,
      "step": 43
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.6082,
      "step": 44
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018,
      "loss": 0.7633,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.5988,
      "step": 46
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000188,
      "loss": 0.6658,
      "step": 47
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000192,
      "loss": 0.5945,
      "step": 48
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000196,
      "loss": 0.5984,
      "step": 49
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 0.6778,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00020400000000000003,
      "loss": 0.6057,
      "step": 51
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00020800000000000001,
      "loss": 0.601,
      "step": 52
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00021200000000000003,
      "loss": 0.5566,
      "step": 53
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00021600000000000002,
      "loss": 0.5911,
      "step": 54
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00022000000000000003,
      "loss": 0.7636,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00022400000000000002,
      "loss": 0.5537,
      "step": 56
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00022799999999999999,
      "loss": 0.6037,
      "step": 57
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000232,
      "loss": 0.6474,
      "step": 58
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000236,
      "loss": 0.6483,
      "step": 59
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00024,
      "loss": 0.5021,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000244,
      "loss": 0.5347,
      "step": 61
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000248,
      "loss": 0.5791,
      "step": 62
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000252,
      "loss": 0.5407,
      "step": 63
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00025600000000000004,
      "loss": 0.5298,
      "step": 64
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00026000000000000003,
      "loss": 0.5685,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000264,
      "loss": 0.5108,
      "step": 66
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000268,
      "loss": 0.526,
      "step": 67
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00027200000000000005,
      "loss": 0.6843,
      "step": 68
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000276,
      "loss": 0.6608,
      "step": 69
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00028,
      "loss": 0.5866,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000284,
      "loss": 0.6422,
      "step": 71
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000288,
      "loss": 0.449,
      "step": 72
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000292,
      "loss": 0.5319,
      "step": 73
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000296,
      "loss": 0.5977,
      "step": 74
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00030000000000000003,
      "loss": 0.5805,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000304,
      "loss": 0.5209,
      "step": 76
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000308,
      "loss": 0.6098,
      "step": 77
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00031200000000000005,
      "loss": 0.4665,
      "step": 78
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00031600000000000004,
      "loss": 0.6882,
      "step": 79
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00032,
      "loss": 0.5427,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000324,
      "loss": 0.5345,
      "step": 81
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000328,
      "loss": 0.663,
      "step": 82
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000332,
      "loss": 0.5393,
      "step": 83
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000336,
      "loss": 0.5711,
      "step": 84
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00034,
      "loss": 0.5261,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000344,
      "loss": 0.5775,
      "step": 86
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000348,
      "loss": 0.6329,
      "step": 87
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00035200000000000005,
      "loss": 0.4425,
      "step": 88
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00035600000000000003,
      "loss": 0.6837,
      "step": 89
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00036,
      "loss": 0.615,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000364,
      "loss": 0.5615,
      "step": 91
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00036800000000000005,
      "loss": 0.5434,
      "step": 92
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00037200000000000004,
      "loss": 0.5864,
      "step": 93
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000376,
      "loss": 0.5583,
      "step": 94
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00038,
      "loss": 0.5299,
      "step": 95
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000384,
      "loss": 0.532,
      "step": 96
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000388,
      "loss": 0.5227,
      "step": 97
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000392,
      "loss": 0.5275,
      "step": 98
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00039600000000000003,
      "loss": 0.4541,
      "step": 99
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0004,
      "loss": 0.6485,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003999995350775973,
      "loss": 0.5438,
      "step": 101
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00039999814031255063,
      "loss": 0.5997,
      "step": 102
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00039999581571134455,
      "loss": 0.5322,
      "step": 103
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003999925612847867,
      "loss": 0.484,
      "step": 104
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00039998837704800766,
      "loss": 0.5961,
      "step": 105
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00039998326302046085,
      "loss": 0.7405,
      "step": 106
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00039997721922592255,
      "loss": 0.5802,
      "step": 107
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00039997024569249167,
      "loss": 0.769,
      "step": 108
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003999623424525898,
      "loss": 0.5598,
      "step": 109
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003999535095429608,
      "loss": 0.6143,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00039994374700467095,
      "loss": 0.5766,
      "step": 111
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00039993305488310836,
      "loss": 0.7695,
      "step": 112
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003999214332279831,
      "loss": 0.7153,
      "step": 113
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003999088820933269,
      "loss": 0.5835,
      "step": 114
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00039989540153749286,
      "loss": 0.6634,
      "step": 115
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000399880991623155,
      "loss": 0.6069,
      "step": 116
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003998656524173082,
      "loss": 0.7224,
      "step": 117
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000399849383991268,
      "loss": 0.5884,
      "step": 118
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003998321864206699,
      "loss": 0.5122,
      "step": 119
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00039981405978546924,
      "loss": 0.6453,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003997950041699408,
      "loss": 0.4665,
      "step": 121
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003997750196626785,
      "loss": 0.5428,
      "step": 122
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039975410635659464,
      "loss": 0.4365,
      "step": 123
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039973226434891995,
      "loss": 0.5978,
      "step": 124
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039970949374120286,
      "loss": 0.7729,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000399685794639309,
      "loss": 0.6212,
      "step": 126
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00039966116715342066,
      "loss": 0.5426,
      "step": 127
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00039963561139803676,
      "loss": 0.5782,
      "step": 128
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003996091274919716,
      "loss": 0.6701,
      "step": 129
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003995817155583548,
      "loss": 0.6314,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003995533757246307,
      "loss": 0.6662,
      "step": 131
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003995241081225573,
      "loss": 0.5192,
      "step": 132
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003994939128882065,
      "loss": 0.5591,
      "step": 133
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003994627901619625,
      "loss": 0.5809,
      "step": 134
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003994307400885219,
      "loss": 0.4871,
      "step": 135
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003993977628168928,
      "loss": 0.6666,
      "step": 136
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003993638585003938,
      "loss": 0.6469,
      "step": 137
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039932902729665357,
      "loss": 0.5727,
      "step": 138
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039929326936761036,
      "loss": 0.6715,
      "step": 139
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039925658487951067,
      "loss": 0.5686,
      "step": 140
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039921897400290894,
      "loss": 0.501,
      "step": 141
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00039918043691266665,
      "loss": 0.5795,
      "step": 142
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039914097378795124,
      "loss": 0.6287,
      "step": 143
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039910058481223564,
      "loss": 0.7016,
      "step": 144
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039905927017329726,
      "loss": 0.6232,
      "step": 145
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039901703006321715,
      "loss": 0.5291,
      "step": 146
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039897386467837903,
      "loss": 0.5297,
      "step": 147
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00039892977421946844,
      "loss": 0.5784,
      "step": 148
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003988847588914718,
      "loss": 0.5714,
      "step": 149
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003988388189036754,
      "loss": 0.5044,
      "step": 150
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003987919544696646,
      "loss": 0.8246,
      "step": 151
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003987441658073226,
      "loss": 0.5048,
      "step": 152
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003986954531388297,
      "loss": 0.5433,
      "step": 153
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00039864581669066186,
      "loss": 0.5251,
      "step": 154
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003985952566935902,
      "loss": 0.5708,
      "step": 155
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00039854377338267936,
      "loss": 0.6276,
      "step": 156
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00039849136699728684,
      "loss": 0.4915,
      "step": 157
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003984380377810617,
      "loss": 0.6389,
      "step": 158
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00039838378598194325,
      "loss": 0.6067,
      "step": 159
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00039832861185216045,
      "loss": 0.6136,
      "step": 160
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003982725156482301,
      "loss": 0.5597,
      "step": 161
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.000398215497630956,
      "loss": 0.5957,
      "step": 162
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003981575580654278,
      "loss": 0.5853,
      "step": 163
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003980986972210194,
      "loss": 0.5462,
      "step": 164
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003980389153713881,
      "loss": 0.5302,
      "step": 165
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00039797821279447307,
      "loss": 0.5395,
      "step": 166
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00039791658977249425,
      "loss": 0.7004,
      "step": 167
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00039785404659195084,
      "loss": 0.5622,
      "step": 168
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00039779058354362013,
      "loss": 0.5759,
      "step": 169
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000397726200922556,
      "loss": 0.6184,
      "step": 170
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003976608990280877,
      "loss": 0.5488,
      "step": 171
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003975946781638183,
      "loss": 0.6162,
      "step": 172
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003975275386376236,
      "loss": 0.558,
      "step": 173
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003974594807616502,
      "loss": 0.519,
      "step": 174
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003973905048523144,
      "loss": 0.6195,
      "step": 175
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00039732061123030064,
      "loss": 0.5991,
      "step": 176
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003972498002205601,
      "loss": 0.5428,
      "step": 177
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00039717807215230896,
      "loss": 0.5323,
      "step": 178
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00039710542735902705,
      "loss": 0.5307,
      "step": 179
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003970318661784564,
      "loss": 0.5783,
      "step": 180
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003969573889525993,
      "loss": 0.5924,
      "step": 181
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00039688199602771714,
      "loss": 0.5902,
      "step": 182
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00039680568775432855,
      "loss": 0.6291,
      "step": 183
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003967284644872077,
      "loss": 0.5942,
      "step": 184
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003966503265853829,
      "loss": 0.4878,
      "step": 185
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003965712744121347,
      "loss": 0.6487,
      "step": 186
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003964913083349945,
      "loss": 0.6111,
      "step": 187
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00039641042872574233,
      "loss": 0.6072,
      "step": 188
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00039632863596040575,
      "loss": 0.716,
      "step": 189
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00039624593041925763,
      "loss": 0.6178,
      "step": 190
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003961623124868145,
      "loss": 0.6323,
      "step": 191
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00039607778255183485,
      "loss": 0.5821,
      "step": 192
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003959923410073174,
      "loss": 0.6738,
      "step": 193
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003959059882504989,
      "loss": 0.6203,
      "step": 194
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00039581872468285277,
      "loss": 0.632,
      "step": 195
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003957305507100868,
      "loss": 0.5857,
      "step": 196
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00039564146674214164,
      "loss": 0.6311,
      "step": 197
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003955514731931885,
      "loss": 0.5889,
      "step": 198
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00039546057048162763,
      "loss": 0.5201,
      "step": 199
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039536875903008607,
      "loss": 0.5581,
      "step": 200
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039527603926541586,
      "loss": 0.5104,
      "step": 201
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039518241161869193,
      "loss": 0.5978,
      "step": 202
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039508787652521013,
      "loss": 0.6244,
      "step": 203
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00039499243442448536,
      "loss": 0.589,
      "step": 204
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003948960857602493,
      "loss": 0.575,
      "step": 205
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003947988309804485,
      "loss": 0.5494,
      "step": 206
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003947006705372422,
      "loss": 0.4895,
      "step": 207
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00039460160488700036,
      "loss": 0.5479,
      "step": 208
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00039450163449030124,
      "loss": 0.5893,
      "step": 209
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003944007598119297,
      "loss": 0.5451,
      "step": 210
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003942989813208747,
      "loss": 0.5582,
      "step": 211
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003941962994903273,
      "loss": 0.5121,
      "step": 212
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00039409271479767826,
      "loss": 0.6324,
      "step": 213
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000393988227724516,
      "loss": 0.6118,
      "step": 214
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003938828387566244,
      "loss": 0.6303,
      "step": 215
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003937765483839804,
      "loss": 0.7705,
      "step": 216
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003936693571007517,
      "loss": 0.6224,
      "step": 217
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003935612654052946,
      "loss": 0.5664,
      "step": 218
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00039345227380015163,
      "loss": 0.66,
      "step": 219
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00039334238279204906,
      "loss": 0.5582,
      "step": 220
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039323159289189505,
      "loss": 0.6087,
      "step": 221
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003931199046147764,
      "loss": 0.5566,
      "step": 222
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039300731847995716,
      "loss": 0.5775,
      "step": 223
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039289383501087534,
      "loss": 0.5081,
      "step": 224
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00039277945473514104,
      "loss": 0.5218,
      "step": 225
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003926641781845338,
      "loss": 0.6655,
      "step": 226
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003925480058950002,
      "loss": 0.5735,
      "step": 227
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039243093840665114,
      "loss": 0.6609,
      "step": 228
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003923129762637596,
      "loss": 0.7323,
      "step": 229
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000392194120014758,
      "loss": 0.5703,
      "step": 230
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00039207437021223583,
      "loss": 0.6545,
      "step": 231
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003919537274129366,
      "loss": 0.521,
      "step": 232
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039183219217775564,
      "loss": 0.5257,
      "step": 233
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003917097650717377,
      "loss": 0.5487,
      "step": 234
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039158644666407365,
      "loss": 0.4861,
      "step": 235
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00039146223752809845,
      "loss": 0.4928,
      "step": 236
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003913371382412883,
      "loss": 0.5253,
      "step": 237
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039121114938525756,
      "loss": 0.6155,
      "step": 238
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039108427154575684,
      "loss": 0.55,
      "step": 239
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039095650531266967,
      "loss": 0.6617,
      "step": 240
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00039082785128000976,
      "loss": 0.5198,
      "step": 241
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00039069831004591866,
      "loss": 0.5302,
      "step": 242
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003905678822126625,
      "loss": 0.5347,
      "step": 243
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00039043656838662946,
      "loss": 0.531,
      "step": 244
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00039030436917832697,
      "loss": 0.4884,
      "step": 245
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00039017128520237883,
      "loss": 0.6027,
      "step": 246
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003900373170775222,
      "loss": 0.5537,
      "step": 247
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038990246542660494,
      "loss": 0.5753,
      "step": 248
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038976673087658256,
      "loss": 0.5059,
      "step": 249
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038963011405851537,
      "loss": 0.5118,
      "step": 250
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00038949261560756565,
      "loss": 0.5645,
      "step": 251
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003893542361629944,
      "loss": 0.5623,
      "step": 252
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00038921497636815866,
      "loss": 0.5216,
      "step": 253
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003890748368705085,
      "loss": 0.4501,
      "step": 254
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003889338183215838,
      "loss": 0.48,
      "step": 255
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00038879192137701135,
      "loss": 0.5218,
      "step": 256
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003886491466965018,
      "loss": 0.5858,
      "step": 257
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038850549494384685,
      "loss": 0.6124,
      "step": 258
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038836096678691536,
      "loss": 0.4645,
      "step": 259
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038821556289765136,
      "loss": 0.474,
      "step": 260
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038806928395207003,
      "loss": 0.4364,
      "step": 261
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00038792213063025484,
      "loss": 0.5821,
      "step": 262
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003877741036163547,
      "loss": 0.5393,
      "step": 263
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003876252035985804,
      "loss": 0.5373,
      "step": 264
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003874754312692013,
      "loss": 0.6021,
      "step": 265
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003873247873245426,
      "loss": 0.4549,
      "step": 266
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003871732724649817,
      "loss": 0.5994,
      "step": 267
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003870208873949453,
      "loss": 0.4764,
      "step": 268
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00038686763282290556,
      "loss": 0.4311,
      "step": 269
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003867135094613774,
      "loss": 0.5462,
      "step": 270
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003865585180269148,
      "loss": 0.5006,
      "step": 271
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003864026592401076,
      "loss": 0.5347,
      "step": 272
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00038624593382557835,
      "loss": 0.5242,
      "step": 273
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00038608834251197856,
      "loss": 0.5005,
      "step": 274
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00038592988603198554,
      "loss": 0.5436,
      "step": 275
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000385770565122299,
      "loss": 0.4658,
      "step": 276
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003856103805236375,
      "loss": 0.5273,
      "step": 277
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038544933298073516,
      "loss": 0.436,
      "step": 278
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038528742324233804,
      "loss": 0.4785,
      "step": 279
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038512465206120086,
      "loss": 0.5366,
      "step": 280
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038496102019408324,
      "loss": 0.4448,
      "step": 281
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038479652840174637,
      "loss": 0.5132,
      "step": 282
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00038463117744894955,
      "loss": 0.7918,
      "step": 283
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038446496810444627,
      "loss": 0.5309,
      "step": 284
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038429790114098114,
      "loss": 0.5316,
      "step": 285
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038412997733528576,
      "loss": 0.4611,
      "step": 286
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038396119746807563,
      "loss": 0.4609,
      "step": 287
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00038379156232404613,
      "loss": 0.5821,
      "step": 288
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003836210726918691,
      "loss": 0.5883,
      "step": 289
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003834497293641889,
      "loss": 0.5012,
      "step": 290
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00038327753313761913,
      "loss": 0.4457,
      "step": 291
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00038310448481273867,
      "loss": 0.4851,
      "step": 292
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00038293058519408787,
      "loss": 0.5622,
      "step": 293
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00038275583509016507,
      "loss": 0.5703,
      "step": 294
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00038258023531342265,
      "loss": 0.5718,
      "step": 295
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003824037866802632,
      "loss": 0.5183,
      "step": 296
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00038222649001103614,
      "loss": 0.5085,
      "step": 297
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00038204834613003323,
      "loss": 0.5388,
      "step": 298
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00038186935586548537,
      "loss": 0.5425,
      "step": 299
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003816895200495584,
      "loss": 0.447,
      "step": 300
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003815088395183493,
      "loss": 0.5541,
      "step": 301
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00038132731511188227,
      "loss": 0.5518,
      "step": 302
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.000381144947674105,
      "loss": 0.5074,
      "step": 303
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003809617380528847,
      "loss": 0.5134,
      "step": 304
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003807776871000037,
      "loss": 0.4599,
      "step": 305
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003805927956711562,
      "loss": 0.5838,
      "step": 306
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00038040706462594395,
      "loss": 0.5216,
      "step": 307
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00038022049482787216,
      "loss": 0.5323,
      "step": 308
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003800330871443456,
      "loss": 0.5681,
      "step": 309
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00037984484244666446,
      "loss": 0.4172,
      "step": 310
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003796557616100207,
      "loss": 0.4958,
      "step": 311
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003794658455134934,
      "loss": 0.662,
      "step": 312
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003792750950400451,
      "loss": 0.5832,
      "step": 313
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003790835110765174,
      "loss": 0.4271,
      "step": 314
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003788910945136271,
      "loss": 0.4842,
      "step": 315
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00037869784624596186,
      "loss": 0.4656,
      "step": 316
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00037850376717197626,
      "loss": 0.4981,
      "step": 317
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00037830885819398733,
      "loss": 0.5162,
      "step": 318
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00037811312021817067,
      "loss": 0.652,
      "step": 319
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003779165541545558,
      "loss": 0.5104,
      "step": 320
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003777191609170225,
      "loss": 0.4971,
      "step": 321
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003775209414232962,
      "loss": 0.4871,
      "step": 322
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003773218965949436,
      "loss": 0.5226,
      "step": 323
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00037712202735736884,
      "loss": 0.4823,
      "step": 324
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003769213346398087,
      "loss": 0.497,
      "step": 325
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003767198193753286,
      "loss": 0.5976,
      "step": 326
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003765174825008181,
      "loss": 0.4532,
      "step": 327
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003763143249569868,
      "loss": 0.5236,
      "step": 328
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00037611034768835947,
      "loss": 0.6513,
      "step": 329
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00037590555164327224,
      "loss": 0.5686,
      "step": 330
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00037569993777386774,
      "loss": 0.456,
      "step": 331
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003754935070360909,
      "loss": 0.5181,
      "step": 332
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003752862603896846,
      "loss": 0.4765,
      "step": 333
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00037507819879818477,
      "loss": 0.5363,
      "step": 334
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00037486932322891646,
      "loss": 0.4584,
      "step": 335
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00037465963465298886,
      "loss": 0.5428,
      "step": 336
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003744491340452913,
      "loss": 0.3927,
      "step": 337
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003742378223844882,
      "loss": 0.5478,
      "step": 338
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003740257006530147,
      "loss": 0.469,
      "step": 339
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00037381276983707246,
      "loss": 0.5169,
      "step": 340
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00037359903092662434,
      "loss": 0.4797,
      "step": 341
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00037338448491539054,
      "loss": 0.5315,
      "step": 342
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00037316913280084353,
      "loss": 0.4422,
      "step": 343
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003729529755842035,
      "loss": 0.4426,
      "step": 344
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003727360142704337,
      "loss": 0.4718,
      "step": 345
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003725182498682361,
      "loss": 0.5585,
      "step": 346
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003722996833900459,
      "loss": 0.4775,
      "step": 347
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003720803158520279,
      "loss": 0.6014,
      "step": 348
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00037186014827407076,
      "loss": 0.5117,
      "step": 349
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003716391816797829,
      "loss": 0.5404,
      "step": 350
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003714174170964876,
      "loss": 0.527,
      "step": 351
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00037119485555521796,
      "loss": 0.4555,
      "step": 352
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00037097149809071255,
      "loss": 0.5372,
      "step": 353
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00037074734574141016,
      "loss": 0.5377,
      "step": 354
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003705223995494454,
      "loss": 0.4925,
      "step": 355
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00037029666056064345,
      "loss": 0.482,
      "step": 356
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00037007012982451546,
      "loss": 0.5235,
      "step": 357
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00036984280839425356,
      "loss": 0.4957,
      "step": 358
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000369614697326726,
      "loss": 0.5379,
      "step": 359
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003693857976824721,
      "loss": 0.4653,
      "step": 360
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00036915611052569785,
      "loss": 0.469,
      "step": 361
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003689256369242702,
      "loss": 0.5618,
      "step": 362
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003686943779497124,
      "loss": 0.4459,
      "step": 363
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003684623346771995,
      "loss": 0.5606,
      "step": 364
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003682295081855524,
      "loss": 0.4368,
      "step": 365
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00036799589955723375,
      "loss": 0.4168,
      "step": 366
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00036776150987834243,
      "loss": 0.4664,
      "step": 367
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00036752634023860846,
      "loss": 0.4737,
      "step": 368
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003672903917313883,
      "loss": 0.4247,
      "step": 369
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00036705366545365935,
      "loss": 0.5677,
      "step": 370
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00036681616250601505,
      "loss": 0.5441,
      "step": 371
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003665778839926599,
      "loss": 0.6247,
      "step": 372
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00036633883102140405,
      "loss": 0.5217,
      "step": 373
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003660990047036584,
      "loss": 0.4651,
      "step": 374
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003658584061544291,
      "loss": 0.4648,
      "step": 375
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003656170364923128,
      "loss": 0.6048,
      "step": 376
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036537489683949114,
      "loss": 0.4515,
      "step": 377
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003651319883217255,
      "loss": 0.5096,
      "step": 378
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036488831206835207,
      "loss": 0.4231,
      "step": 379
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036464386921227637,
      "loss": 0.4903,
      "step": 380
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00036439866088996796,
      "loss": 0.5131,
      "step": 381
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003641526882414553,
      "loss": 0.5986,
      "step": 382
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003639059524103203,
      "loss": 0.6,
      "step": 383
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003636584545436931,
      "loss": 0.5216,
      "step": 384
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003634101957922468,
      "loss": 0.5144,
      "step": 385
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00036316117731019184,
      "loss": 0.4963,
      "step": 386
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003629114002552711,
      "loss": 0.5657,
      "step": 387
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00036266086578875384,
      "loss": 0.5028,
      "step": 388
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003624095750754311,
      "loss": 0.573,
      "step": 389
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00036215752928360967,
      "loss": 0.5199,
      "step": 390
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003619047295851068,
      "loss": 0.656,
      "step": 391
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00036165117715524506,
      "loss": 0.5129,
      "step": 392
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00036139687317284647,
      "loss": 0.3945,
      "step": 393
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003611418188202271,
      "loss": 0.5318,
      "step": 394
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00036088601528319196,
      "loss": 0.5344,
      "step": 395
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00036062946375102885,
      "loss": 0.5407,
      "step": 396
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003603721654165034,
      "loss": 0.5364,
      "step": 397
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00036011412147585306,
      "loss": 0.5407,
      "step": 398
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003598553331287821,
      "loss": 0.5999,
      "step": 399
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003595958015784555,
      "loss": 0.624,
      "step": 400
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00035933552803149354,
      "loss": 0.5351,
      "step": 401
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003590745136979662,
      "loss": 0.5196,
      "step": 402
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00035881275979138765,
      "loss": 0.5447,
      "step": 403
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003585502675287104,
      "loss": 0.4908,
      "step": 404
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00035828703813031986,
      "loss": 0.5172,
      "step": 405
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00035802307282002834,
      "loss": 0.5923,
      "step": 406
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003577583728250699,
      "loss": 0.568,
      "step": 407
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00035749293937609395,
      "loss": 0.4618,
      "step": 408
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003572267737071601,
      "loss": 0.5351,
      "step": 409
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003569598770557322,
      "loss": 0.5285,
      "step": 410
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00035669225066267256,
      "loss": 0.4571,
      "step": 411
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00035642389577223625,
      "loss": 0.4214,
      "step": 412
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003561548136320653,
      "loss": 0.5393,
      "step": 413
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003558850054931828,
      "loss": 0.549,
      "step": 414
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00035561447260998714,
      "loss": 0.4824,
      "step": 415
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00035534321624024656,
      "loss": 0.6244,
      "step": 416
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00035507123764509245,
      "loss": 0.5436,
      "step": 417
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003547985380890144,
      "loss": 0.5198,
      "step": 418
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00035452511883985366,
      "loss": 0.5979,
      "step": 419
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00035425098116879754,
      "loss": 0.4158,
      "step": 420
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00035397612635037356,
      "loss": 0.5125,
      "step": 421
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00035370055566244334,
      "loss": 0.4699,
      "step": 422
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003534242703861966,
      "loss": 0.5553,
      "step": 423
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00035314727180614573,
      "loss": 0.5969,
      "step": 424
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00035286956121011897,
      "loss": 0.456,
      "step": 425
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003525911398892552,
      "loss": 0.5195,
      "step": 426
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003523120091379975,
      "loss": 0.5187,
      "step": 427
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00035203217025408726,
      "loss": 0.5443,
      "step": 428
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003517516245385582,
      "loss": 0.4476,
      "step": 429
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003514703732957301,
      "loss": 0.5757,
      "step": 430
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00035118841783320304,
      "loss": 0.5129,
      "step": 431
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00035090575946185114,
      "loss": 0.6354,
      "step": 432
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00035062239949581645,
      "loss": 0.4065,
      "step": 433
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000350338339252503,
      "loss": 0.5472,
      "step": 434
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00035005358005257045,
      "loss": 0.5424,
      "step": 435
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00034976812321992816,
      "loss": 0.6127,
      "step": 436
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00034948197008172877,
      "loss": 0.63,
      "step": 437
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003491951219683625,
      "loss": 0.413,
      "step": 438
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034890758021345034,
      "loss": 0.5435,
      "step": 439
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034861934615383844,
      "loss": 0.5433,
      "step": 440
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034833042112959153,
      "loss": 0.4763,
      "step": 441
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034804080648398667,
      "loss": 0.5727,
      "step": 442
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034775050356350727,
      "loss": 0.5392,
      "step": 443
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00034745951371783666,
      "loss": 0.4981,
      "step": 444
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003471678382998518,
      "loss": 0.5516,
      "step": 445
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00034687547866561703,
      "loss": 0.4965,
      "step": 446
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003465824361743779,
      "loss": 0.4982,
      "step": 447
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003462887121885544,
      "loss": 0.5619,
      "step": 448
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003459943080737353,
      "loss": 0.5273,
      "step": 449
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00034569922519867133,
      "loss": 0.517,
      "step": 450
    }
  ],
  "logging_steps": 1,
  "max_steps": 1557,
  "num_train_epochs": 3,
  "save_steps": 50,
  "total_flos": 6.020058348017418e+17,
  "trial_name": null,
  "trial_params": null
}