{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.38512456372608017,
  "eval_steps": 500,
  "global_step": 200,
  "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
    }
  ],
  "logging_steps": 1,
  "max_steps": 1557,
  "num_train_epochs": 3,
  "save_steps": 50,
  "total_flos": 2.6670638381550797e+17,
  "trial_name": null,
  "trial_params": null
}