{
  "best_metric": 0.7743580937385559,
  "best_model_checkpoint": "./qlora-out2/checkpoint-2780",
  "epoch": 1.9805685498380714,
  "eval_steps": 278,
  "global_step": 2780,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.3887,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.258455753326416,
      "eval_runtime": 928.8248,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.395,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4607,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-06,
      "loss": 1.1136,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.3151,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 1.2919,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.2e-05,
      "loss": 1.3233,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 1.3953,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.3477,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-05,
      "loss": 1.3716,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 1.2323,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.2161,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 1.3484,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.4808,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.2378,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 1.3383,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.3504,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.3068,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.6e-05,
      "loss": 1.1443,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.8e-05,
      "loss": 1.0418,
      "step": 19
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 1.1951,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2e-05,
      "loss": 1.2499,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.2837,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.2841,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 1.1383,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 1.191,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.0524,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.1453,
      "step": 27
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.2299,
      "step": 28
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.8e-05,
      "loss": 1.1684,
      "step": 29
    },
    {
      "epoch": 0.02,
      "learning_rate": 6e-05,
      "loss": 1.131,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.2e-05,
      "loss": 0.9653,
      "step": 31
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.1623,
      "step": 32
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.6e-05,
      "loss": 1.2385,
      "step": 33
    },
    {
      "epoch": 0.02,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.3423,
      "step": 34
    },
    {
      "epoch": 0.03,
      "learning_rate": 7e-05,
      "loss": 1.1423,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.2e-05,
      "loss": 1.1936,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.4e-05,
      "loss": 0.966,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.6e-05,
      "loss": 1.1428,
      "step": 38
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.2166,
      "step": 39
    },
    {
      "epoch": 0.03,
      "learning_rate": 8e-05,
      "loss": 0.9608,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.2e-05,
      "loss": 1.0341,
      "step": 41
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.4e-05,
      "loss": 1.0809,
      "step": 42
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.6e-05,
      "loss": 0.8755,
      "step": 43
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.0842,
      "step": 44
    },
    {
      "epoch": 0.03,
      "learning_rate": 9e-05,
      "loss": 0.966,
      "step": 45
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.1058,
      "step": 46
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.4e-05,
      "loss": 1.0969,
      "step": 47
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.6e-05,
      "loss": 0.9709,
      "step": 48
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.8e-05,
      "loss": 1.0876,
      "step": 49
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.0509,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.1217,
      "step": 51
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.0509,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.9607,
      "step": 53
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.9612,
      "step": 54
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.08,
      "step": 55
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.0707,
      "step": 56
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.1231,
      "step": 57
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000116,
      "loss": 1.1311,
      "step": 58
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000118,
      "loss": 1.0952,
      "step": 59
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00012,
      "loss": 0.9414,
      "step": 60
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000122,
      "loss": 1.0844,
      "step": 61
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000124,
      "loss": 1.289,
      "step": 62
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000126,
      "loss": 0.9816,
      "step": 63
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.2302,
      "step": 64
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.9629,
      "step": 65
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000132,
      "loss": 1.1123,
      "step": 66
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000134,
      "loss": 1.0533,
      "step": 67
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.0773,
      "step": 68
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000138,
      "loss": 1.121,
      "step": 69
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00014,
      "loss": 1.0892,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000142,
      "loss": 0.9789,
      "step": 71
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000144,
      "loss": 0.9463,
      "step": 72
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000146,
      "loss": 0.9908,
      "step": 73
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000148,
      "loss": 1.0459,
      "step": 74
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0564,
      "step": 75
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000152,
      "loss": 1.0615,
      "step": 76
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000154,
      "loss": 0.9861,
      "step": 77
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.2164,
      "step": 78
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.1109,
      "step": 79
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00016,
      "loss": 0.9864,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000162,
      "loss": 0.9934,
      "step": 81
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000164,
      "loss": 1.1521,
      "step": 82
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000166,
      "loss": 1.0644,
      "step": 83
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000168,
      "loss": 1.068,
      "step": 84
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00017,
      "loss": 0.917,
      "step": 85
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000172,
      "loss": 1.0865,
      "step": 86
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000174,
      "loss": 1.1467,
      "step": 87
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.9763,
      "step": 88
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.1863,
      "step": 89
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00018,
      "loss": 1.212,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000182,
      "loss": 0.896,
      "step": 91
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.961,
      "step": 92
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.0941,
      "step": 93
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000188,
      "loss": 0.9946,
      "step": 94
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019,
      "loss": 1.0024,
      "step": 95
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000192,
      "loss": 1.102,
      "step": 96
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000194,
      "loss": 1.2857,
      "step": 97
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000196,
      "loss": 1.0461,
      "step": 98
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.0695,
      "step": 99
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.9776,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019999997016532006,
      "loss": 1.12,
      "step": 101
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019999988066129803,
      "loss": 1.1123,
      "step": 102
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001999997314879873,
      "loss": 1.0875,
      "step": 103
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019999952264547686,
      "loss": 0.9013,
      "step": 104
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001999992541338914,
      "loss": 1.0349,
      "step": 105
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999892595339106,
      "loss": 1.1303,
      "step": 106
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999853810417174,
      "loss": 0.9909,
      "step": 107
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001999980905864648,
      "loss": 1.3324,
      "step": 108
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001999975834005373,
      "loss": 1.1674,
      "step": 109
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999701654669188,
      "loss": 1.0373,
      "step": 110
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999639002526672,
      "loss": 1.0269,
      "step": 111
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999570383663574,
      "loss": 1.0732,
      "step": 112
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001999949579812084,
      "loss": 1.1633,
      "step": 113
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999415245942968,
      "loss": 1.1388,
      "step": 114
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001999932872717802,
      "loss": 1.0891,
      "step": 115
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999236241877632,
      "loss": 1.0402,
      "step": 116
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999137790096982,
      "loss": 0.9818,
      "step": 117
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001999903337189482,
      "loss": 1.1637,
      "step": 118
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998922987333445,
      "loss": 1.0578,
      "step": 119
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001999880663647873,
      "loss": 0.9704,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998684319400093,
      "loss": 1.1897,
      "step": 121
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998556036170527,
      "loss": 1.0213,
      "step": 122
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998421786866574,
      "loss": 1.2087,
      "step": 123
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998281571568342,
      "loss": 1.2416,
      "step": 124
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998135390359497,
      "loss": 1.1849,
      "step": 125
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001999798324332726,
      "loss": 1.1871,
      "step": 126
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019997825130562422,
      "loss": 1.0915,
      "step": 127
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019997661052159323,
      "loss": 0.9596,
      "step": 128
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019997491008215867,
      "loss": 1.1949,
      "step": 129
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019997314998833525,
      "loss": 1.0249,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019997133024117313,
      "loss": 0.984,
      "step": 131
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001999694508417582,
      "loss": 1.123,
      "step": 132
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019996751179121182,
      "loss": 1.1197,
      "step": 133
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019996551309069108,
      "loss": 1.2459,
      "step": 134
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019996345474138858,
      "loss": 1.135,
      "step": 135
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019996133674453245,
      "loss": 1.0909,
      "step": 136
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001999591591013866,
      "loss": 1.0918,
      "step": 137
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001999569218132503,
      "loss": 1.0223,
      "step": 138
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001999546248814586,
      "loss": 1.1071,
      "step": 139
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019995226830738205,
      "loss": 1.0082,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019994985209242677,
      "loss": 0.9964,
      "step": 141
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019994737623803456,
      "loss": 1.1876,
      "step": 142
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001999448407456827,
      "loss": 1.0405,
      "step": 143
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019994224561688414,
      "loss": 0.838,
      "step": 144
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001999395908531873,
      "loss": 1.0024,
      "step": 145
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993687645617636,
      "loss": 1.0407,
      "step": 146
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993410242747094,
      "loss": 0.9703,
      "step": 147
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993126876872625,
      "loss": 0.8565,
      "step": 148
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019992837548163316,
      "loss": 1.3603,
      "step": 149
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019992542256791804,
      "loss": 1.018,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019992241002934295,
      "loss": 1.1121,
      "step": 151
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019991933786770537,
      "loss": 1.0008,
      "step": 152
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019991620608483847,
      "loss": 1.2188,
      "step": 153
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019991301468261097,
      "loss": 1.0712,
      "step": 154
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019990976366292715,
      "loss": 1.0614,
      "step": 155
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019990645302772687,
      "loss": 1.1297,
      "step": 156
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019990308277898557,
      "loss": 0.987,
      "step": 157
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019989965291871426,
      "loss": 1.1924,
      "step": 158
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019989616344895952,
      "loss": 1.0035,
      "step": 159
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019989261437180348,
      "loss": 1.203,
      "step": 160
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019988900568936388,
      "loss": 1.0142,
      "step": 161
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019988533740379397,
      "loss": 1.1076,
      "step": 162
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001998816095172826,
      "loss": 1.1963,
      "step": 163
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019987782203205413,
      "loss": 0.8563,
      "step": 164
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019987397495036864,
      "loss": 1.0479,
      "step": 165
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019987006827452156,
      "loss": 1.013,
      "step": 166
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019986610200684398,
      "loss": 1.1211,
      "step": 167
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019986207614970262,
      "loss": 1.0974,
      "step": 168
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019985799070549963,
      "loss": 1.0056,
      "step": 169
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019985384567667279,
      "loss": 1.1454,
      "step": 170
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019984964106569536,
      "loss": 0.9264,
      "step": 171
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001998453768750763,
      "loss": 1.0058,
      "step": 172
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019984105310735995,
      "loss": 1.1618,
      "step": 173
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019983666976512628,
      "loss": 0.8789,
      "step": 174
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001998322268509908,
      "loss": 0.9891,
      "step": 175
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019982772436760463,
      "loss": 1.2456,
      "step": 176
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019982316231765431,
      "loss": 1.1748,
      "step": 177
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019981854070386202,
      "loss": 1.1217,
      "step": 178
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019981385952898541,
      "loss": 0.9817,
      "step": 179
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019980911879581776,
      "loss": 1.0194,
      "step": 180
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019980431850718776,
      "loss": 1.0868,
      "step": 181
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001997994586659598,
      "loss": 1.0833,
      "step": 182
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019979453927503364,
      "loss": 1.2889,
      "step": 183
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019978956033734471,
      "loss": 1.2581,
      "step": 184
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019978452185586386,
      "loss": 1.1737,
      "step": 185
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019977942383359753,
      "loss": 0.8918,
      "step": 186
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001997742662735877,
      "loss": 0.8485,
      "step": 187
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019976904917891187,
      "loss": 1.0112,
      "step": 188
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000199763772552683,
      "loss": 1.0506,
      "step": 189
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001997584363980496,
      "loss": 1.0577,
      "step": 190
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001997530407181958,
      "loss": 1.1833,
      "step": 191
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019974758551634112,
      "loss": 1.1172,
      "step": 192
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019974207079574062,
      "loss": 1.1574,
      "step": 193
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019973649655968497,
      "loss": 1.272,
      "step": 194
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001997308628115002,
      "loss": 0.88,
      "step": 195
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.000199725169554548,
      "loss": 0.9808,
      "step": 196
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019971941679222546,
      "loss": 1.1954,
      "step": 197
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019971360452796522,
      "loss": 1.0671,
      "step": 198
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019970773276523543,
      "loss": 1.1125,
      "step": 199
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019970180150753972,
      "loss": 1.2618,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019969581075841725,
      "loss": 0.938,
      "step": 201
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019968976052144266,
      "loss": 1.0011,
      "step": 202
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019968365080022608,
      "loss": 0.8927,
      "step": 203
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019967748159841313,
      "loss": 1.0846,
      "step": 204
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019967125291968496,
      "loss": 0.9639,
      "step": 205
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019966496476775817,
      "loss": 1.1716,
      "step": 206
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019965861714638488,
      "loss": 1.0234,
      "step": 207
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019965221005935262,
      "loss": 1.0007,
      "step": 208
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019964574351048452,
      "loss": 1.0117,
      "step": 209
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019963921750363909,
      "loss": 0.8718,
      "step": 210
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001996326320427104,
      "loss": 1.0578,
      "step": 211
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019962598713162786,
      "loss": 0.984,
      "step": 212
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019961928277435656,
      "loss": 1.1567,
      "step": 213
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019961251897489686,
      "loss": 1.0619,
      "step": 214
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001996056957372847,
      "loss": 1.1284,
      "step": 215
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019959881306559152,
      "loss": 0.9052,
      "step": 216
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019959187096392408,
      "loss": 1.0749,
      "step": 217
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001995848694364247,
      "loss": 1.0252,
      "step": 218
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019957780848727123,
      "loss": 0.9863,
      "step": 219
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001995706881206768,
      "loss": 1.0206,
      "step": 220
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019956350834089015,
      "loss": 1.0172,
      "step": 221
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019955626915219536,
      "loss": 0.8074,
      "step": 222
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019954897055891201,
      "loss": 1.2516,
      "step": 223
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019954161256539518,
      "loss": 1.0903,
      "step": 224
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001995341951760353,
      "loss": 0.9665,
      "step": 225
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019952671839525824,
      "loss": 0.7986,
      "step": 226
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019951918222752544,
      "loss": 1.0346,
      "step": 227
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001995115866773336,
      "loss": 1.0043,
      "step": 228
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019950393174921494,
      "loss": 1.0331,
      "step": 229
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019949621744773713,
      "loss": 0.9585,
      "step": 230
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001994884437775033,
      "loss": 1.1217,
      "step": 231
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019948061074315186,
      "loss": 1.0722,
      "step": 232
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019947271834935677,
      "loss": 1.182,
      "step": 233
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001994647666008274,
      "loss": 1.1241,
      "step": 234
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019945675550230843,
      "loss": 0.8764,
      "step": 235
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019944868505858009,
      "loss": 0.8608,
      "step": 236
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019944055527445795,
      "loss": 0.9757,
      "step": 237
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000199432366154793,
      "loss": 0.9922,
      "step": 238
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019942411770447162,
      "loss": 0.9226,
      "step": 239
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001994158099284156,
      "loss": 0.9811,
      "step": 240
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019940744283158225,
      "loss": 0.9933,
      "step": 241
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000199399016418964,
      "loss": 1.1078,
      "step": 242
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001993905306955889,
      "loss": 0.967,
      "step": 243
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019938198566652035,
      "loss": 1.0784,
      "step": 244
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019937338133685711,
      "loss": 1.0092,
      "step": 245
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001993647177117333,
      "loss": 1.1874,
      "step": 246
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001993559947963185,
      "loss": 1.0331,
      "step": 247
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019934721259581758,
      "loss": 0.9994,
      "step": 248
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001993383711154708,
      "loss": 0.9614,
      "step": 249
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019932947036055385,
      "loss": 0.9099,
      "step": 250
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019932051033637774,
      "loss": 0.96,
      "step": 251
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019931149104828887,
      "loss": 0.908,
      "step": 252
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000199302412501669,
      "loss": 1.0627,
      "step": 253
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001992932747019352,
      "loss": 0.9946,
      "step": 254
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019928407765453998,
      "loss": 1.0672,
      "step": 255
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019927482136497114,
      "loss": 1.0209,
      "step": 256
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019926550583875186,
      "loss": 0.9764,
      "step": 257
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019925613108144066,
      "loss": 0.9098,
      "step": 258
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019924669709863135,
      "loss": 0.9398,
      "step": 259
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019923720389595318,
      "loss": 1.0845,
      "step": 260
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019922765147907065,
      "loss": 0.8524,
      "step": 261
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019921803985368364,
      "loss": 1.0538,
      "step": 262
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019920836902552735,
      "loss": 1.0558,
      "step": 263
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001991986390003723,
      "loss": 1.1774,
      "step": 264
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019918884978402433,
      "loss": 0.9959,
      "step": 265
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001991790013823246,
      "loss": 1.0679,
      "step": 266
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019916909380114962,
      "loss": 1.2467,
      "step": 267
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019915912704641112,
      "loss": 1.2266,
      "step": 268
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019914910112405626,
      "loss": 1.0708,
      "step": 269
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019913901604006736,
      "loss": 0.9028,
      "step": 270
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019912887180046225,
      "loss": 1.253,
      "step": 271
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019911866841129382,
      "loss": 1.1908,
      "step": 272
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001991084058786504,
      "loss": 1.0397,
      "step": 273
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001990980842086556,
      "loss": 0.8802,
      "step": 274
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019908770340746829,
      "loss": 1.0615,
      "step": 275
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019907726348128261,
      "loss": 0.8866,
      "step": 276
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019906676443632803,
      "loss": 1.09,
      "step": 277
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019905620627886923,
      "loss": 1.0737,
      "step": 278
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.8134894371032715,
      "eval_runtime": 935.9991,
      "eval_samples_per_second": 0.783,
      "eval_steps_per_second": 0.392,
      "step": 278
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019904558901520617,
      "loss": 1.0679,
      "step": 279
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019903491265167418,
      "loss": 0.9924,
      "step": 280
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001990241771946437,
      "loss": 1.1988,
      "step": 281
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019901338265052056,
      "loss": 1.0417,
      "step": 282
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019900252902574578,
      "loss": 1.2493,
      "step": 283
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019899161632679565,
      "loss": 1.1256,
      "step": 284
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001989806445601817,
      "loss": 0.8917,
      "step": 285
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019896961373245072,
      "loss": 1.1094,
      "step": 286
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019895852385018472,
      "loss": 0.9568,
      "step": 287
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000198947374920001,
      "loss": 1.0238,
      "step": 288
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000198936166948552,
      "loss": 0.9434,
      "step": 289
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001989248999425255,
      "loss": 0.9298,
      "step": 290
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001989135739086444,
      "loss": 0.8585,
      "step": 291
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001989021888536669,
      "loss": 1.1661,
      "step": 292
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019889074478438641,
      "loss": 1.2018,
      "step": 293
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019887924170763148,
      "loss": 0.8965,
      "step": 294
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019886767963026597,
      "loss": 1.0932,
      "step": 295
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019885605855918885,
      "loss": 0.9806,
      "step": 296
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019884437850133438,
      "loss": 1.1125,
      "step": 297
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000198832639463672,
      "loss": 1.2403,
      "step": 298
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019882084145320626,
      "loss": 1.1134,
      "step": 299
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019880898447697696,
      "loss": 0.9156,
      "step": 300
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019879706854205914,
      "loss": 1.1116,
      "step": 301
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019878509365556287,
      "loss": 1.1377,
      "step": 302
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019877305982463357,
      "loss": 0.9514,
      "step": 303
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001987609670564517,
      "loss": 0.9504,
      "step": 304
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000198748815358233,
      "loss": 1.244,
      "step": 305
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019873660473722823,
      "loss": 0.8826,
      "step": 306
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019872433520072344,
      "loss": 1.1367,
      "step": 307
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019871200675603977,
      "loss": 0.8752,
      "step": 308
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019869961941053354,
      "loss": 0.8808,
      "step": 309
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019868717317159617,
      "loss": 0.9724,
      "step": 310
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001986746680466543,
      "loss": 1.0365,
      "step": 311
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001986621040431696,
      "loss": 1.0302,
      "step": 312
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019864948116863894,
      "loss": 0.958,
      "step": 313
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019863679943059431,
      "loss": 1.0285,
      "step": 314
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019862405883660288,
      "loss": 0.8903,
      "step": 315
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019861125939426682,
      "loss": 1.0428,
      "step": 316
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001985984011112235,
      "loss": 1.1962,
      "step": 317
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019858548399514535,
      "loss": 1.0527,
      "step": 318
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019857250805373994,
      "loss": 1.1006,
      "step": 319
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019855947329474994,
      "loss": 0.9753,
      "step": 320
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019854637972595315,
      "loss": 0.8998,
      "step": 321
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019853322735516234,
      "loss": 0.8299,
      "step": 322
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001985200161902255,
      "loss": 0.7969,
      "step": 323
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019850674623902558,
      "loss": 1.0663,
      "step": 324
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019849341750948076,
      "loss": 1.185,
      "step": 325
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019848003000954418,
      "loss": 1.1135,
      "step": 326
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019846658374720404,
      "loss": 1.0711,
      "step": 327
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019845307873048369,
      "loss": 0.9847,
      "step": 328
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019843951496744145,
      "loss": 1.0958,
      "step": 329
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019842589246617075,
      "loss": 1.1431,
      "step": 330
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001984122112348,
      "loss": 1.0647,
      "step": 331
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001983984712814928,
      "loss": 1.0588,
      "step": 332
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001983846726144476,
      "loss": 1.1006,
      "step": 333
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000198370815241898,
      "loss": 1.1349,
      "step": 334
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019835689917211267,
      "loss": 1.1999,
      "step": 335
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019834292441339515,
      "loss": 1.2147,
      "step": 336
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019832889097408415,
      "loss": 0.9424,
      "step": 337
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001983147988625533,
      "loss": 1.2383,
      "step": 338
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001983006480872113,
      "loss": 1.0342,
      "step": 339
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001982864386565018,
      "loss": 1.1958,
      "step": 340
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019827217057890345,
      "loss": 1.1097,
      "step": 341
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019825784386293,
      "loss": 1.2901,
      "step": 342
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019824345851713005,
      "loss": 1.0156,
      "step": 343
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019822901455008728,
      "loss": 1.0615,
      "step": 344
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019821451197042026,
      "loss": 0.9822,
      "step": 345
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019819995078678267,
      "loss": 0.9301,
      "step": 346
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000198185331007863,
      "loss": 0.9293,
      "step": 347
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019817065264238478,
      "loss": 1.0347,
      "step": 348
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019815591569910654,
      "loss": 1.0457,
      "step": 349
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001981411201868217,
      "loss": 0.9566,
      "step": 350
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019812626611435865,
      "loss": 1.0948,
      "step": 351
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019811135349058072,
      "loss": 1.0096,
      "step": 352
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019809638232438616,
      "loss": 1.0751,
      "step": 353
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001980813526247082,
      "loss": 1.0018,
      "step": 354
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019806626440051493,
      "loss": 1.1267,
      "step": 355
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019805111766080943,
      "loss": 1.0547,
      "step": 356
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019803591241462966,
      "loss": 1.0539,
      "step": 357
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001980206486710485,
      "loss": 1.0655,
      "step": 358
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019800532643917364,
      "loss": 1.3095,
      "step": 359
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001979899457281479,
      "loss": 0.898,
      "step": 360
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019797450654714872,
      "loss": 1.1565,
      "step": 361
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019795900890538865,
      "loss": 0.9624,
      "step": 362
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000197943452812115,
      "loss": 0.8897,
      "step": 363
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019792783827661002,
      "loss": 0.9926,
      "step": 364
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019791216530819073,
      "loss": 1.1383,
      "step": 365
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019789643391620917,
      "loss": 1.0988,
      "step": 366
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019788064411005213,
      "loss": 1.2379,
      "step": 367
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019786479589914126,
      "loss": 1.0312,
      "step": 368
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019784888929293314,
      "loss": 0.9131,
      "step": 369
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019783292430091911,
      "loss": 1.0023,
      "step": 370
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019781690093262534,
      "loss": 0.985,
      "step": 371
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019780081919761294,
      "loss": 0.9263,
      "step": 372
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019778467910547777,
      "loss": 0.9212,
      "step": 373
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001977684806658505,
      "loss": 1.0235,
      "step": 374
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001977522238883966,
      "loss": 0.963,
      "step": 375
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019773590878281643,
      "loss": 1.1552,
      "step": 376
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001977195353588451,
      "loss": 1.1238,
      "step": 377
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019770310362625252,
      "loss": 1.0905,
      "step": 378
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019768661359484342,
      "loss": 1.1769,
      "step": 379
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019767006527445728,
      "loss": 0.9444,
      "step": 380
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019765345867496837,
      "loss": 1.1479,
      "step": 381
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019763679380628574,
      "loss": 0.8908,
      "step": 382
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019762007067835325,
      "loss": 0.9612,
      "step": 383
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019760328930114941,
      "loss": 1.0336,
      "step": 384
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019758644968468768,
      "loss": 1.0254,
      "step": 385
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019756955183901603,
      "loss": 0.8938,
      "step": 386
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019755259577421732,
      "loss": 0.8883,
      "step": 387
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019753558150040917,
      "loss": 0.895,
      "step": 388
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019751850902774388,
      "loss": 1.1311,
      "step": 389
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019750137836640843,
      "loss": 1.084,
      "step": 390
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019748418952662467,
      "loss": 1.1146,
      "step": 391
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019746694251864897,
      "loss": 1.0621,
      "step": 392
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019744963735277257,
      "loss": 1.1309,
      "step": 393
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019743227403932134,
      "loss": 1.1483,
      "step": 394
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019741485258865588,
      "loss": 0.9676,
      "step": 395
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001973973730111714,
      "loss": 1.2032,
      "step": 396
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001973798353172979,
      "loss": 0.9192,
      "step": 397
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019736223951750002,
      "loss": 0.9469,
      "step": 398
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000197344585622277,
      "loss": 1.1012,
      "step": 399
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019732687364216287,
      "loss": 0.9184,
      "step": 400
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001973091035877262,
      "loss": 0.8816,
      "step": 401
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019729127546957032,
      "loss": 1.1294,
      "step": 402
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019727338929833313,
      "loss": 0.9797,
      "step": 403
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001972554450846872,
      "loss": 0.9374,
      "step": 404
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019723744283933972,
      "loss": 1.2324,
      "step": 405
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001972193825730325,
      "loss": 0.9085,
      "step": 406
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000197201264296542,
      "loss": 0.9259,
      "step": 407
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001971830880206793,
      "loss": 1.2243,
      "step": 408
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019716485375629003,
      "loss": 0.8665,
      "step": 409
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019714656151425449,
      "loss": 1.0972,
      "step": 410
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019712821130548754,
      "loss": 0.8733,
      "step": 411
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001971098031409386,
      "loss": 1.0331,
      "step": 412
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019709133703159175,
      "loss": 0.9977,
      "step": 413
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019707281298846557,
      "loss": 1.1635,
      "step": 414
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019705423102261326,
      "loss": 1.3189,
      "step": 415
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001970355911451225,
      "loss": 0.9383,
      "step": 416
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019701689336711566,
      "loss": 1.2546,
      "step": 417
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019699813769974954,
      "loss": 1.0726,
      "step": 418
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019697932415421555,
      "loss": 1.0723,
      "step": 419
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019696045274173962,
      "loss": 1.0325,
      "step": 420
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019694152347358217,
      "loss": 1.0079,
      "step": 421
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001969225363610382,
      "loss": 0.8953,
      "step": 422
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019690349141543716,
      "loss": 1.1939,
      "step": 423
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019688438864814308,
      "loss": 0.9531,
      "step": 424
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019686522807055447,
      "loss": 0.9127,
      "step": 425
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001968460096941043,
      "loss": 1.088,
      "step": 426
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019682673353026004,
      "loss": 1.0371,
      "step": 427
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001968073995905237,
      "loss": 1.046,
      "step": 428
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019678800788643167,
      "loss": 0.9797,
      "step": 429
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019676855842955487,
      "loss": 1.0912,
      "step": 430
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019674905123149872,
      "loss": 1.1189,
      "step": 431
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019672948630390294,
      "loss": 0.9582,
      "step": 432
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019670986365844187,
      "loss": 1.0963,
      "step": 433
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019669018330682422,
      "loss": 1.018,
      "step": 434
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019667044526079308,
      "loss": 1.0862,
      "step": 435
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019665064953212604,
      "loss": 1.0341,
      "step": 436
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001966307961326351,
      "loss": 1.1146,
      "step": 437
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019661088507416663,
      "loss": 1.0489,
      "step": 438
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019659091636860143,
      "loss": 1.1304,
      "step": 439
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019657089002785474,
      "loss": 0.8507,
      "step": 440
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001965508060638761,
      "loss": 1.147,
      "step": 441
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019653066448864953,
      "loss": 1.2613,
      "step": 442
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019651046531419332,
      "loss": 1.0675,
      "step": 443
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019649020855256027,
      "loss": 1.0492,
      "step": 444
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001964698942158374,
      "loss": 0.9987,
      "step": 445
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019644952231614613,
      "loss": 1.1948,
      "step": 446
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019642909286564229,
      "loss": 0.9737,
      "step": 447
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019640860587651597,
      "loss": 0.9763,
      "step": 448
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019638806136099165,
      "loss": 0.9916,
      "step": 449
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019636745933132807,
      "loss": 1.0921,
      "step": 450
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019634679979981838,
      "loss": 0.9436,
      "step": 451
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019632608277878996,
      "loss": 1.0915,
      "step": 452
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019630530828060455,
      "loss": 1.2092,
      "step": 453
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001962844763176581,
      "loss": 1.1242,
      "step": 454
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.000196263586902381,
      "loss": 0.9851,
      "step": 455
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019624264004723774,
      "loss": 1.0044,
      "step": 456
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019622163576472724,
      "loss": 0.9243,
      "step": 457
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001962005740673826,
      "loss": 1.111,
      "step": 458
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019617945496777116,
      "loss": 1.0343,
      "step": 459
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019615827847849462,
      "loss": 1.0007,
      "step": 460
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001961370446121888,
      "loss": 1.0913,
      "step": 461
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019611575338152385,
      "loss": 1.0495,
      "step": 462
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001960944047992041,
      "loss": 1.032,
      "step": 463
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001960729988779681,
      "loss": 0.9336,
      "step": 464
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001960515356305886,
      "loss": 1.1091,
      "step": 465
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019603001506987268,
      "loss": 1.3603,
      "step": 466
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019600843720866143,
      "loss": 0.955,
      "step": 467
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019598680205983024,
      "loss": 0.9921,
      "step": 468
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001959651096362887,
      "loss": 1.0685,
      "step": 469
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019594335995098047,
      "loss": 0.9915,
      "step": 470
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019592155301688356,
      "loss": 0.9539,
      "step": 471
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001958996888470099,
      "loss": 0.9649,
      "step": 472
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019587776745440578,
      "loss": 0.9364,
      "step": 473
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019585578885215156,
      "loss": 0.8455,
      "step": 474
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019583375305336166,
      "loss": 0.9459,
      "step": 475
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019581166007118478,
      "loss": 0.9976,
      "step": 476
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019578950991880364,
      "loss": 1.2671,
      "step": 477
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019576730260943503,
      "loss": 1.1577,
      "step": 478
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019574503815632997,
      "loss": 1.1734,
      "step": 479
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019572271657277354,
      "loss": 1.0998,
      "step": 480
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019570033787208484,
      "loss": 1.2226,
      "step": 481
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001956779020676171,
      "loss": 1.095,
      "step": 482
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001956554091727577,
      "loss": 1.1626,
      "step": 483
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019563285920092785,
      "loss": 1.1719,
      "step": 484
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001956102521655831,
      "loss": 0.9034,
      "step": 485
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019558758808021289,
      "loss": 1.0854,
      "step": 486
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019556486695834072,
      "loss": 0.8689,
      "step": 487
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019554208881352415,
      "loss": 1.2379,
      "step": 488
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019551925365935476,
      "loss": 1.0795,
      "step": 489
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001954963615094581,
      "loss": 1.1472,
      "step": 490
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019547341237749385,
      "loss": 1.0888,
      "step": 491
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001954504062771555,
      "loss": 1.0139,
      "step": 492
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019542734322217076,
      "loss": 1.127,
      "step": 493
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019540422322630115,
      "loss": 0.9941,
      "step": 494
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019538104630334221,
      "loss": 1.0601,
      "step": 495
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019535781246712345,
      "loss": 0.9994,
      "step": 496
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019533452173150844,
      "loss": 0.9786,
      "step": 497
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001953111741103945,
      "loss": 1.0259,
      "step": 498
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019528776961771308,
      "loss": 1.0008,
      "step": 499
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019526430826742944,
      "loss": 1.1346,
      "step": 500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019524079007354287,
      "loss": 0.9866,
      "step": 501
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001952172150500865,
      "loss": 1.0805,
      "step": 502
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001951935832111274,
      "loss": 1.1178,
      "step": 503
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001951698945707665,
      "loss": 1.0151,
      "step": 504
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019514614914313872,
      "loss": 1.1953,
      "step": 505
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019512234694241278,
      "loss": 0.9272,
      "step": 506
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001950984879827913,
      "loss": 1.1223,
      "step": 507
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001950745722785108,
      "loss": 1.1102,
      "step": 508
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019505059984384153,
      "loss": 1.2288,
      "step": 509
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019502657069308778,
      "loss": 1.1882,
      "step": 510
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019500248484058757,
      "loss": 0.9214,
      "step": 511
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019497834230071276,
      "loss": 0.8448,
      "step": 512
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019495414308786909,
      "loss": 1.0775,
      "step": 513
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000194929887216496,
      "loss": 1.0918,
      "step": 514
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019490557470106686,
      "loss": 1.0166,
      "step": 515
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019488120555608883,
      "loss": 1.0576,
      "step": 516
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019485677979610272,
      "loss": 0.9171,
      "step": 517
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019483229743568332,
      "loss": 1.0014,
      "step": 518
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019480775848943908,
      "loss": 0.7498,
      "step": 519
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019478316297201218,
      "loss": 1.0724,
      "step": 520
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019475851089807868,
      "loss": 0.9778,
      "step": 521
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019473380228234824,
      "loss": 1.0711,
      "step": 522
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001947090371395644,
      "loss": 1.2759,
      "step": 523
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019468421548450433,
      "loss": 1.0588,
      "step": 524
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019465933733197894,
      "loss": 1.005,
      "step": 525
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001946344026968329,
      "loss": 0.9049,
      "step": 526
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001946094115939445,
      "loss": 1.0826,
      "step": 527
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001945843640382258,
      "loss": 1.1609,
      "step": 528
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019455926004462255,
      "loss": 1.0182,
      "step": 529
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019453409962811409,
      "loss": 1.2203,
      "step": 530
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001945088828037135,
      "loss": 0.8381,
      "step": 531
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019448360958646747,
      "loss": 1.1398,
      "step": 532
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001944582799914564,
      "loss": 1.0641,
      "step": 533
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001944328940337943,
      "loss": 1.1007,
      "step": 534
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001944074517286288,
      "loss": 1.0872,
      "step": 535
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019438195309114115,
      "loss": 0.929,
      "step": 536
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001943563981365462,
      "loss": 1.1229,
      "step": 537
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001943307868800925,
      "loss": 1.0044,
      "step": 538
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019430511933706207,
      "loss": 1.0296,
      "step": 539
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001942793955227706,
      "loss": 1.2795,
      "step": 540
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019425361545256727,
      "loss": 1.149,
      "step": 541
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019422777914183495,
      "loss": 1.1244,
      "step": 542
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019420188660598995,
      "loss": 0.9324,
      "step": 543
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019417593786048222,
      "loss": 1.1006,
      "step": 544
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019414993292079515,
      "loss": 1.0008,
      "step": 545
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001941238718024458,
      "loss": 1.0735,
      "step": 546
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019409775452098463,
      "loss": 1.2546,
      "step": 547
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019407158109199565,
      "loss": 0.9172,
      "step": 548
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019404535153109636,
      "loss": 0.9154,
      "step": 549
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019401906585393786,
      "loss": 1.3201,
      "step": 550
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019399272407620455,
      "loss": 1.06,
      "step": 551
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019396632621361442,
      "loss": 1.0562,
      "step": 552
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001939398722819189,
      "loss": 0.9977,
      "step": 553
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019391336229690294,
      "loss": 1.2566,
      "step": 554
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019388679627438483,
      "loss": 0.9249,
      "step": 555
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019386017423021637,
      "loss": 0.8896,
      "step": 556
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.8007223010063171,
      "eval_runtime": 935.7709,
      "eval_samples_per_second": 0.783,
      "eval_steps_per_second": 0.392,
      "step": 556
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001938334961802827,
      "loss": 1.2621,
      "step": 557
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019380676214050252,
      "loss": 1.0005,
      "step": 558
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019377997212682784,
      "loss": 1.0977,
      "step": 559
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019375312615524406,
      "loss": 0.9215,
      "step": 560
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019372622424177003,
      "loss": 1.0171,
      "step": 561
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019369926640245796,
      "loss": 1.2476,
      "step": 562
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019367225265339334,
      "loss": 1.0844,
      "step": 563
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019364518301069521,
      "loss": 0.9909,
      "step": 564
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019361805749051577,
      "loss": 1.136,
      "step": 565
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001935908761090407,
      "loss": 1.0928,
      "step": 566
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001935636388824889,
      "loss": 1.0913,
      "step": 567
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001935363458271127,
      "loss": 0.8671,
      "step": 568
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001935089969591977,
      "loss": 0.9824,
      "step": 569
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019348159229506275,
      "loss": 0.9347,
      "step": 570
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019345413185106004,
      "loss": 0.9473,
      "step": 571
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019342661564357506,
      "loss": 0.9483,
      "step": 572
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019339904368902654,
      "loss": 1.0393,
      "step": 573
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019337141600386652,
      "loss": 1.0093,
      "step": 574
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019334373260458025,
      "loss": 0.8723,
      "step": 575
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019331599350768622,
      "loss": 0.9628,
      "step": 576
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019328819872973618,
      "loss": 1.2224,
      "step": 577
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001932603482873151,
      "loss": 0.964,
      "step": 578
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019323244219704116,
      "loss": 1.1318,
      "step": 579
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001932044804755657,
      "loss": 1.0822,
      "step": 580
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019317646313957344,
      "loss": 0.9938,
      "step": 581
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019314839020578197,
      "loss": 1.1083,
      "step": 582
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019312026169094232,
      "loss": 0.9021,
      "step": 583
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001930920776118386,
      "loss": 1.0046,
      "step": 584
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019306383798528803,
      "loss": 0.9083,
      "step": 585
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019303554282814106,
      "loss": 1.1854,
      "step": 586
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001930071921572812,
      "loss": 1.2245,
      "step": 587
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019297878598962515,
      "loss": 1.214,
      "step": 588
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001929503243421226,
      "loss": 1.0312,
      "step": 589
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019292180723175654,
      "loss": 0.9124,
      "step": 590
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019289323467554286,
      "loss": 1.0549,
      "step": 591
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001928646066905307,
      "loss": 1.0301,
      "step": 592
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019283592329380212,
      "loss": 1.0214,
      "step": 593
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019280718450247238,
      "loss": 0.9199,
      "step": 594
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019277839033368972,
      "loss": 0.9153,
      "step": 595
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019274954080463537,
      "loss": 0.9379,
      "step": 596
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019272063593252377,
      "loss": 0.8975,
      "step": 597
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001926916757346022,
      "loss": 0.943,
      "step": 598
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019266266022815103,
      "loss": 1.1155,
      "step": 599
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019263358943048364,
      "loss": 1.0209,
      "step": 600
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019260446335894637,
      "loss": 0.9107,
      "step": 601
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019257528203091862,
      "loss": 1.0173,
      "step": 602
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001925460454638126,
      "loss": 1.1534,
      "step": 603
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019251675367507368,
      "loss": 1.0227,
      "step": 604
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019248740668218004,
      "loss": 0.8669,
      "step": 605
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019245800450264284,
      "loss": 1.0436,
      "step": 606
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019242854715400618,
      "loss": 1.0512,
      "step": 607
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019239903465384707,
      "loss": 0.9131,
      "step": 608
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019236946701977543,
      "loss": 1.1827,
      "step": 609
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019233984426943407,
      "loss": 1.1883,
      "step": 610
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001923101664204987,
      "loss": 0.9893,
      "step": 611
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019228043349067795,
      "loss": 1.0296,
      "step": 612
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019225064549771318,
      "loss": 0.9537,
      "step": 613
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019222080245937876,
      "loss": 0.928,
      "step": 614
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001921909043934818,
      "loss": 0.9254,
      "step": 615
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019216095131786233,
      "loss": 0.8904,
      "step": 616
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001921309432503931,
      "loss": 0.9838,
      "step": 617
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001921008802089798,
      "loss": 0.967,
      "step": 618
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001920707622115608,
      "loss": 1.1355,
      "step": 619
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019204058927610733,
      "loss": 0.9885,
      "step": 620
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001920103614206234,
      "loss": 1.0149,
      "step": 621
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019198007866314578,
      "loss": 1.2358,
      "step": 622
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019194974102174395,
      "loss": 1.0837,
      "step": 623
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019191934851452028,
      "loss": 1.0201,
      "step": 624
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019188890115960967,
      "loss": 0.8788,
      "step": 625
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019185839897517995,
      "loss": 0.9971,
      "step": 626
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001918278419794316,
      "loss": 1.0585,
      "step": 627
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019179723019059766,
      "loss": 0.8125,
      "step": 628
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019176656362694406,
      "loss": 0.8666,
      "step": 629
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019173584230676937,
      "loss": 1.0923,
      "step": 630
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001917050662484048,
      "loss": 0.9902,
      "step": 631
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019167423547021418,
      "loss": 0.9257,
      "step": 632
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019164334999059404,
      "loss": 0.9262,
      "step": 633
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019161240982797358,
      "loss": 1.0063,
      "step": 634
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001915814150008146,
      "loss": 0.8897,
      "step": 635
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019155036552761154,
      "loss": 1.0061,
      "step": 636
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019151926142689133,
      "loss": 1.0707,
      "step": 637
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001914881027172137,
      "loss": 0.9347,
      "step": 638
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019145688941717075,
      "loss": 1.0359,
      "step": 639
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001914256215453873,
      "loss": 0.9633,
      "step": 640
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001913942991205207,
      "loss": 1.1403,
      "step": 641
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019136292216126083,
      "loss": 1.1599,
      "step": 642
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019133149068633012,
      "loss": 1.1016,
      "step": 643
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019130000471448354,
      "loss": 0.9649,
      "step": 644
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019126846426450856,
      "loss": 0.9538,
      "step": 645
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019123686935522516,
      "loss": 0.8934,
      "step": 646
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019120522000548584,
      "loss": 0.9522,
      "step": 647
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019117351623417555,
      "loss": 0.9962,
      "step": 648
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001911417580602117,
      "loss": 0.9452,
      "step": 649
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019110994550254425,
      "loss": 1.0177,
      "step": 650
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019107807858015547,
      "loss": 1.0924,
      "step": 651
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019104615731206024,
      "loss": 1.1307,
      "step": 652
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019101418171730568,
      "loss": 1.0051,
      "step": 653
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019098215181497153,
      "loss": 0.9909,
      "step": 654
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019095006762416973,
      "loss": 0.9886,
      "step": 655
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019091792916404475,
      "loss": 1.0279,
      "step": 656
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001908857364537734,
      "loss": 1.1566,
      "step": 657
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001908534895125649,
      "loss": 0.9541,
      "step": 658
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019082118835966078,
      "loss": 0.9898,
      "step": 659
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019078883301433484,
      "loss": 1.1042,
      "step": 660
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019075642349589345,
      "loss": 0.8216,
      "step": 661
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019072395982367506,
      "loss": 1.1339,
      "step": 662
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019069144201705056,
      "loss": 1.2166,
      "step": 663
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019065887009542316,
      "loss": 1.1485,
      "step": 664
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019062624407822828,
      "loss": 1.2549,
      "step": 665
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019059356398493362,
      "loss": 0.8784,
      "step": 666
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019056082983503924,
      "loss": 0.9762,
      "step": 667
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019052804164807738,
      "loss": 1.0137,
      "step": 668
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019049519944361256,
      "loss": 1.0347,
      "step": 669
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001904623032412415,
      "loss": 1.2376,
      "step": 670
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019042935306059312,
      "loss": 1.0529,
      "step": 671
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001903963489213286,
      "loss": 1.0353,
      "step": 672
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019036329084314133,
      "loss": 0.951,
      "step": 673
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001903301788457568,
      "loss": 0.9964,
      "step": 674
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001902970129489328,
      "loss": 1.1489,
      "step": 675
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001902637931724591,
      "loss": 1.0404,
      "step": 676
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019023051953615788,
      "loss": 1.0047,
      "step": 677
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001901971920598832,
      "loss": 1.0887,
      "step": 678
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019016381076352134,
      "loss": 1.0835,
      "step": 679
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019013037566699076,
      "loss": 1.0559,
      "step": 680
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.0637,
      "step": 681
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019006334415325746,
      "loss": 0.9811,
      "step": 682
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019002974777605205,
      "loss": 0.9983,
      "step": 683
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00018999609767867242,
      "loss": 1.0093,
      "step": 684
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00018996239388119736,
      "loss": 1.016,
      "step": 685
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00018992863640373772,
      "loss": 1.0398,
      "step": 686
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00018989482526643637,
      "loss": 1.033,
      "step": 687
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018986096048946824,
      "loss": 1.0072,
      "step": 688
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018982704209304015,
      "loss": 0.9693,
      "step": 689
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018979307009739103,
      "loss": 0.972,
      "step": 690
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018975904452279177,
      "loss": 1.1036,
      "step": 691
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018972496538954516,
      "loss": 0.8385,
      "step": 692
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018969083271798607,
      "loss": 1.0482,
      "step": 693
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001896566465284812,
      "loss": 0.9408,
      "step": 694
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018962240684142922,
      "loss": 1.0657,
      "step": 695
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018958811367726078,
      "loss": 1.0926,
      "step": 696
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018955376705643835,
      "loss": 1.1755,
      "step": 697
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018951936699945635,
      "loss": 1.0571,
      "step": 698
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018948491352684108,
      "loss": 0.9532,
      "step": 699
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018945040665915071,
      "loss": 1.0971,
      "step": 700
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018941584641697526,
      "loss": 1.1328,
      "step": 701
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018938123282093657,
      "loss": 0.8574,
      "step": 702
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018934656589168842,
      "loss": 1.1912,
      "step": 703
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001893118456499163,
      "loss": 1.0407,
      "step": 704
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018927707211633757,
      "loss": 0.9783,
      "step": 705
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001892422453117014,
      "loss": 1.1885,
      "step": 706
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018920736525678865,
      "loss": 0.9877,
      "step": 707
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001891724319724121,
      "loss": 1.0459,
      "step": 708
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001891374454794162,
      "loss": 1.0179,
      "step": 709
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001891024057986771,
      "loss": 0.8615,
      "step": 710
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018906731295110281,
      "loss": 1.1418,
      "step": 711
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018903216695763305,
      "loss": 0.9445,
      "step": 712
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018899696783923915,
      "loss": 1.099,
      "step": 713
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001889617156169242,
      "loss": 0.9344,
      "step": 714
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00018892641031172298,
      "loss": 1.1293,
      "step": 715
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000188891051944702,
      "loss": 1.0181,
      "step": 716
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018885564053695926,
      "loss": 0.9525,
      "step": 717
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018882017610962458,
      "loss": 0.9675,
      "step": 718
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018878465868385936,
      "loss": 1.043,
      "step": 719
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018874908828085663,
      "loss": 0.9619,
      "step": 720
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018871346492184098,
      "loss": 1.0472,
      "step": 721
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018867778862806872,
      "loss": 1.2485,
      "step": 722
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018864205942082757,
      "loss": 1.0675,
      "step": 723
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018860627732143696,
      "loss": 0.9207,
      "step": 724
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018857044235124785,
      "loss": 1.1124,
      "step": 725
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018853455453164274,
      "loss": 1.1404,
      "step": 726
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018849861388403567,
      "loss": 0.8605,
      "step": 727
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018846262042987214,
      "loss": 1.034,
      "step": 728
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00018842657419062926,
      "loss": 0.9884,
      "step": 729
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018839047518781561,
      "loss": 1.0719,
      "step": 730
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018835432344297117,
      "loss": 0.7864,
      "step": 731
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001883181189776675,
      "loss": 0.9789,
      "step": 732
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018828186181350754,
      "loss": 1.1249,
      "step": 733
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001882455519721258,
      "loss": 0.9164,
      "step": 734
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018820918947518798,
      "loss": 1.0882,
      "step": 735
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018817277434439146,
      "loss": 0.9613,
      "step": 736
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018813630660146488,
      "loss": 1.041,
      "step": 737
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018809978626816833,
      "loss": 0.9729,
      "step": 738
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018806321336629323,
      "loss": 0.9462,
      "step": 739
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001880265879176624,
      "loss": 0.9251,
      "step": 740
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018798990994413003,
      "loss": 1.0409,
      "step": 741
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018795317946758165,
      "loss": 1.1742,
      "step": 742
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.000187916396509934,
      "loss": 0.8062,
      "step": 743
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018787956109313537,
      "loss": 1.1662,
      "step": 744
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018784267323916512,
      "loss": 0.9709,
      "step": 745
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018780573297003404,
      "loss": 1.0399,
      "step": 746
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018776874030778417,
      "loss": 1.1762,
      "step": 747
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018773169527448873,
      "loss": 0.9552,
      "step": 748
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018769459789225233,
      "loss": 1.0847,
      "step": 749
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018765744818321066,
      "loss": 1.0173,
      "step": 750
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018762024616953075,
      "loss": 0.8956,
      "step": 751
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018758299187341085,
      "loss": 0.93,
      "step": 752
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018754568531708033,
      "loss": 0.9971,
      "step": 753
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001875083265227997,
      "loss": 1.0605,
      "step": 754
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018747091551286083,
      "loss": 1.0162,
      "step": 755
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018743345230958655,
      "loss": 1.14,
      "step": 756
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018739593693533095,
      "loss": 1.0253,
      "step": 757
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001873583694124792,
      "loss": 1.0164,
      "step": 758
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001873207497634476,
      "loss": 1.1235,
      "step": 759
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018728307801068355,
      "loss": 1.035,
      "step": 760
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001872453541766656,
      "loss": 0.9681,
      "step": 761
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018720757828390324,
      "loss": 1.0253,
      "step": 762
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018716975035493712,
      "loss": 0.9558,
      "step": 763
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018713187041233896,
      "loss": 1.0271,
      "step": 764
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018709393847871143,
      "loss": 0.9601,
      "step": 765
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018705595457668833,
      "loss": 1.0534,
      "step": 766
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018701791872893436,
      "loss": 1.0472,
      "step": 767
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001869798309581453,
      "loss": 1.0622,
      "step": 768
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018694169128704785,
      "loss": 0.9739,
      "step": 769
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018690349973839976,
      "loss": 1.0406,
      "step": 770
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018686525633498962,
      "loss": 1.0688,
      "step": 771
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018682696109963704,
      "loss": 0.9272,
      "step": 772
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018678861405519256,
      "loss": 0.9449,
      "step": 773
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018675021522453764,
      "loss": 1.1619,
      "step": 774
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018671176463058457,
      "loss": 1.1099,
      "step": 775
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018667326229627657,
      "loss": 1.1406,
      "step": 776
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018663470824458776,
      "loss": 1.054,
      "step": 777
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001865961024985231,
      "loss": 1.2223,
      "step": 778
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018655744508111837,
      "loss": 1.0028,
      "step": 779
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018651873601544024,
      "loss": 1.0749,
      "step": 780
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018647997532458612,
      "loss": 1.1845,
      "step": 781
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001864411630316843,
      "loss": 1.0231,
      "step": 782
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001864022991598938,
      "loss": 0.9711,
      "step": 783
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018636338373240446,
      "loss": 0.9044,
      "step": 784
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00018632441677243682,
      "loss": 1.0031,
      "step": 785
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018628539830324229,
      "loss": 0.8864,
      "step": 786
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001862463283481029,
      "loss": 0.945,
      "step": 787
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018620720693033146,
      "loss": 1.0882,
      "step": 788
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018616803407327142,
      "loss": 0.852,
      "step": 789
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018612880980029708,
      "loss": 0.9174,
      "step": 790
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018608953413481322,
      "loss": 1.1542,
      "step": 791
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018605020710025537,
      "loss": 1.115,
      "step": 792
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018601082872008977,
      "loss": 1.0146,
      "step": 793
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018597139901781323,
      "loss": 0.996,
      "step": 794
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001859319180169532,
      "loss": 1.259,
      "step": 795
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018589238574106775,
      "loss": 1.0187,
      "step": 796
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018585280221374551,
      "loss": 1.0248,
      "step": 797
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018581316745860574,
      "loss": 1.1209,
      "step": 798
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018577348149929828,
      "loss": 1.1306,
      "step": 799
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001857337443595034,
      "loss": 0.914,
      "step": 800
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018569395606293204,
      "loss": 1.0591,
      "step": 801
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018565411663332566,
      "loss": 0.9798,
      "step": 802
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018561422609445613,
      "loss": 1.065,
      "step": 803
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001855742844701259,
      "loss": 0.9392,
      "step": 804
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018553429178416793,
      "loss": 0.8949,
      "step": 805
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018549424806044553,
      "loss": 0.9186,
      "step": 806
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018545415332285256,
      "loss": 0.8853,
      "step": 807
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001854140075953133,
      "loss": 0.9959,
      "step": 808
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018537381090178245,
      "loss": 0.9417,
      "step": 809
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018533356326624512,
      "loss": 1.0456,
      "step": 810
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018529326471271678,
      "loss": 1.0429,
      "step": 811
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001852529152652434,
      "loss": 0.9922,
      "step": 812
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018521251494790116,
      "loss": 0.9308,
      "step": 813
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018517206378479667,
      "loss": 1.0013,
      "step": 814
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018513156180006694,
      "loss": 1.0356,
      "step": 815
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018509100901787924,
      "loss": 1.0195,
      "step": 816
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001850504054624311,
      "loss": 1.0305,
      "step": 817
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001850097511579504,
      "loss": 1.1224,
      "step": 818
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018496904612869534,
      "loss": 1.3125,
      "step": 819
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001849282903989544,
      "loss": 0.8629,
      "step": 820
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018488748399304617,
      "loss": 0.9605,
      "step": 821
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001848466269353196,
      "loss": 1.0858,
      "step": 822
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018480571925015384,
      "loss": 1.1522,
      "step": 823
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018476476096195826,
      "loss": 0.9044,
      "step": 824
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018472375209517238,
      "loss": 1.1976,
      "step": 825
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018468269267426596,
      "loss": 1.0506,
      "step": 826
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018464158272373885,
      "loss": 1.1228,
      "step": 827
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018460042226812115,
      "loss": 1.0962,
      "step": 828
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.000184559211331973,
      "loss": 0.8256,
      "step": 829
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001845179499398847,
      "loss": 1.0029,
      "step": 830
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018447663811647672,
      "loss": 0.93,
      "step": 831
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018443527588639946,
      "loss": 0.9816,
      "step": 832
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018439386327433356,
      "loss": 1.1442,
      "step": 833
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001843524003049897,
      "loss": 0.962,
      "step": 834
    },
    {
      "epoch": 0.6,
      "eval_loss": 0.790631115436554,
      "eval_runtime": 928.3265,
      "eval_samples_per_second": 0.79,
      "eval_steps_per_second": 0.395,
      "step": 834
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018431088700310844,
      "loss": 0.952,
      "step": 835
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018426932339346065,
      "loss": 1.0966,
      "step": 836
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018422770950084696,
      "loss": 1.0316,
      "step": 837
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018418604535009816,
      "loss": 1.0865,
      "step": 838
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00018414433096607498,
      "loss": 1.064,
      "step": 839
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001841025663736681,
      "loss": 0.9754,
      "step": 840
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018406075159779826,
      "loss": 1.1642,
      "step": 841
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000184018886663416,
      "loss": 1.1243,
      "step": 842
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018397697159550184,
      "loss": 1.1004,
      "step": 843
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018393500641906627,
      "loss": 0.9641,
      "step": 844
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001838929911591497,
      "loss": 1.0616,
      "step": 845
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018385092584082222,
      "loss": 0.9353,
      "step": 846
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018380881048918405,
      "loss": 1.1074,
      "step": 847
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018376664512936513,
      "loss": 1.1671,
      "step": 848
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018372442978652532,
      "loss": 0.834,
      "step": 849
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001836821644858541,
      "loss": 0.9856,
      "step": 850
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.000183639849252571,
      "loss": 1.1499,
      "step": 851
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018359748411192524,
      "loss": 0.8755,
      "step": 852
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001835550690891958,
      "loss": 1.078,
      "step": 853
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00018351260420969146,
      "loss": 1.2049,
      "step": 854
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001834700894987508,
      "loss": 1.0189,
      "step": 855
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000183427524981742,
      "loss": 0.8357,
      "step": 856
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018338491068406308,
      "loss": 0.9937,
      "step": 857
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001833422466311417,
      "loss": 1.0231,
      "step": 858
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001832995328484352,
      "loss": 1.3451,
      "step": 859
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001832567693614307,
      "loss": 1.0229,
      "step": 860
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018321395619564482,
      "loss": 1.133,
      "step": 861
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018317109337662394,
      "loss": 0.9986,
      "step": 862
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018312818092994403,
      "loss": 0.9516,
      "step": 863
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018308521888121061,
      "loss": 0.9859,
      "step": 864
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018304220725605898,
      "loss": 0.8551,
      "step": 865
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001829991460801538,
      "loss": 1.1586,
      "step": 866
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018295603537918945,
      "loss": 0.8917,
      "step": 867
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001829128751788898,
      "loss": 0.9428,
      "step": 868
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018286966550500823,
      "loss": 1.1589,
      "step": 869
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018282640638332773,
      "loss": 0.8785,
      "step": 870
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001827830978396607,
      "loss": 1.1924,
      "step": 871
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018273973989984908,
      "loss": 1.1383,
      "step": 872
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001826963325897643,
      "loss": 0.8081,
      "step": 873
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001826528759353072,
      "loss": 1.0141,
      "step": 874
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018260936996240807,
      "loss": 1.0061,
      "step": 875
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001825658146970267,
      "loss": 0.9673,
      "step": 876
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001825222101651522,
      "loss": 0.8959,
      "step": 877
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018247855639280308,
      "loss": 0.8317,
      "step": 878
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018243485340602736,
      "loss": 0.8467,
      "step": 879
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018239110123090225,
      "loss": 1.0435,
      "step": 880
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018234729989353442,
      "loss": 0.9639,
      "step": 881
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018230344942005985,
      "loss": 0.9363,
      "step": 882
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018225954983664387,
      "loss": 0.9425,
      "step": 883
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018221560116948103,
      "loss": 1.0822,
      "step": 884
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001821716034447952,
      "loss": 1.1434,
      "step": 885
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001821275566888396,
      "loss": 1.0569,
      "step": 886
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018208346092789667,
      "loss": 1.0889,
      "step": 887
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018203931618827795,
      "loss": 0.7756,
      "step": 888
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018199512249632443,
      "loss": 1.0365,
      "step": 889
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018195087987840614,
      "loss": 0.9777,
      "step": 890
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018190658836092244,
      "loss": 0.9918,
      "step": 891
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018186224797030174,
      "loss": 1.2357,
      "step": 892
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018181785873300167,
      "loss": 1.1194,
      "step": 893
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000181773420675509,
      "loss": 1.1123,
      "step": 894
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018172893382433967,
      "loss": 1.0078,
      "step": 895
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018168439820603864,
      "loss": 1.0214,
      "step": 896
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001816398138471801,
      "loss": 0.9918,
      "step": 897
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018159518077436718,
      "loss": 0.8445,
      "step": 898
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018155049901423222,
      "loss": 1.0491,
      "step": 899
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001815057685934365,
      "loss": 0.8525,
      "step": 900
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018146098953867037,
      "loss": 0.83,
      "step": 901
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018141616187665322,
      "loss": 1.1714,
      "step": 902
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018137128563413342,
      "loss": 1.1176,
      "step": 903
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018132636083788834,
      "loss": 0.9715,
      "step": 904
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018128138751472432,
      "loss": 0.8237,
      "step": 905
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018123636569147665,
      "loss": 1.1067,
      "step": 906
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001811912953950096,
      "loss": 1.1357,
      "step": 907
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018114617665221621,
      "loss": 0.9148,
      "step": 908
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018110100949001872,
      "loss": 0.9245,
      "step": 909
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018105579393536795,
      "loss": 1.0649,
      "step": 910
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001810105300152438,
      "loss": 1.0159,
      "step": 911
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018096521775665494,
      "loss": 1.0524,
      "step": 912
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001809198571866389,
      "loss": 0.8424,
      "step": 913
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018087444833226202,
      "loss": 0.874,
      "step": 914
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018082899122061954,
      "loss": 0.9366,
      "step": 915
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018078348587883536,
      "loss": 0.9427,
      "step": 916
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018073793233406224,
      "loss": 1.0578,
      "step": 917
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018069233061348175,
      "loss": 0.8559,
      "step": 918
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018064668074430404,
      "loss": 0.8947,
      "step": 919
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001806009827537682,
      "loss": 1.0308,
      "step": 920
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018055523666914185,
      "loss": 0.9428,
      "step": 921
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018050944251772142,
      "loss": 0.911,
      "step": 922
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018046360032683198,
      "loss": 1.1307,
      "step": 923
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018041771012382727,
      "loss": 1.2655,
      "step": 924
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001803717719360897,
      "loss": 0.9411,
      "step": 925
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018032578579103029,
      "loss": 0.8339,
      "step": 926
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018027975171608861,
      "loss": 1.1345,
      "step": 927
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018023366973873303,
      "loss": 0.8715,
      "step": 928
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018018753988646022,
      "loss": 0.9443,
      "step": 929
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018014136218679567,
      "loss": 0.9342,
      "step": 930
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001800951366672933,
      "loss": 1.1972,
      "step": 931
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018004886335553554,
      "loss": 1.0768,
      "step": 932
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018000254227913348,
      "loss": 1.0127,
      "step": 933
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00017995617346572645,
      "loss": 0.9837,
      "step": 934
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00017990975694298257,
      "loss": 1.0244,
      "step": 935
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00017986329273859822,
      "loss": 1.064,
      "step": 936
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001798167808802983,
      "loss": 1.191,
      "step": 937
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017977022139583612,
      "loss": 1.1063,
      "step": 938
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017972361431299345,
      "loss": 0.8724,
      "step": 939
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017967695965958046,
      "loss": 1.1161,
      "step": 940
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001796302574634356,
      "loss": 1.0124,
      "step": 941
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017958350775242588,
      "loss": 0.9694,
      "step": 942
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017953671055444644,
      "loss": 0.8534,
      "step": 943
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017948986589742097,
      "loss": 0.8823,
      "step": 944
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017944297380930135,
      "loss": 1.0866,
      "step": 945
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017939603431806774,
      "loss": 1.0312,
      "step": 946
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017934904745172872,
      "loss": 0.8528,
      "step": 947
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017930201323832095,
      "loss": 1.2447,
      "step": 948
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017925493170590947,
      "loss": 0.9413,
      "step": 949
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001792078028825876,
      "loss": 0.8646,
      "step": 950
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00017916062679647677,
      "loss": 1.0288,
      "step": 951
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001791134034757266,
      "loss": 1.0052,
      "step": 952
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000179066132948515,
      "loss": 1.1004,
      "step": 953
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.000179018815243048,
      "loss": 1.1048,
      "step": 954
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001789714503875597,
      "loss": 1.1335,
      "step": 955
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017892403841031248,
      "loss": 1.0825,
      "step": 956
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017887657933959674,
      "loss": 1.0604,
      "step": 957
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017882907320373098,
      "loss": 0.9123,
      "step": 958
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001787815200310618,
      "loss": 1.1866,
      "step": 959
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017873391984996395,
      "loss": 1.0811,
      "step": 960
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017868627268884007,
      "loss": 1.0107,
      "step": 961
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017863857857612097,
      "loss": 0.9008,
      "step": 962
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001785908375402654,
      "loss": 1.0014,
      "step": 963
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00017854304960976012,
      "loss": 1.0865,
      "step": 964
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001784952148131199,
      "loss": 1.0138,
      "step": 965
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017844733317888745,
      "loss": 1.0609,
      "step": 966
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017839940473563345,
      "loss": 0.8813,
      "step": 967
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017835142951195642,
      "loss": 0.9901,
      "step": 968
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017830340753648298,
      "loss": 1.1038,
      "step": 969
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017825533883786748,
      "loss": 1.0063,
      "step": 970
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001782072234447922,
      "loss": 1.0556,
      "step": 971
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017815906138596733,
      "loss": 1.1839,
      "step": 972
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017811085269013076,
      "loss": 1.1704,
      "step": 973
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017806259738604844,
      "loss": 0.9245,
      "step": 974
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017801429550251392,
      "loss": 1.1319,
      "step": 975
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017796594706834864,
      "loss": 0.8611,
      "step": 976
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017791755211240182,
      "loss": 1.064,
      "step": 977
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017786911066355039,
      "loss": 0.9075,
      "step": 978
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017782062275069907,
      "loss": 1.1436,
      "step": 979
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001777720884027803,
      "loss": 0.9099,
      "step": 980
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001777235076487542,
      "loss": 1.0102,
      "step": 981
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017767488051760857,
      "loss": 0.9966,
      "step": 982
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017762620703835896,
      "loss": 0.9717,
      "step": 983
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017757748724004846,
      "loss": 1.0171,
      "step": 984
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017752872115174792,
      "loss": 0.9607,
      "step": 985
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017747990880255575,
      "loss": 1.2005,
      "step": 986
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017743105022159793,
      "loss": 0.9784,
      "step": 987
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001773821454380281,
      "loss": 1.0315,
      "step": 988
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001773331944810274,
      "loss": 0.9319,
      "step": 989
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017728419737980455,
      "loss": 1.0673,
      "step": 990
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017723515416359585,
      "loss": 1.0483,
      "step": 991
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.000177186064861665,
      "loss": 0.9204,
      "step": 992
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00017713692950330337,
      "loss": 1.0385,
      "step": 993
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001770877481178296,
      "loss": 1.0929,
      "step": 994
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017703852073459002,
      "loss": 1.0733,
      "step": 995
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001769892473829582,
      "loss": 1.128,
      "step": 996
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001769399280923353,
      "loss": 1.0461,
      "step": 997
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017689056289214982,
      "loss": 1.0365,
      "step": 998
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001768411518118576,
      "loss": 0.9022,
      "step": 999
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.000176791694880942,
      "loss": 1.1053,
      "step": 1000
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017674219212891358,
      "loss": 0.9865,
      "step": 1001
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017669264358531034,
      "loss": 1.1135,
      "step": 1002
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001766430492796976,
      "loss": 0.9625,
      "step": 1003
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017659340924166793,
      "loss": 1.0107,
      "step": 1004
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017654372350084128,
      "loss": 0.8601,
      "step": 1005
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017649399208686473,
      "loss": 0.9929,
      "step": 1006
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017644421502941278,
      "loss": 0.9153,
      "step": 1007
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017639439235818703,
      "loss": 0.9541,
      "step": 1008
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017634452410291633,
      "loss": 0.9031,
      "step": 1009
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001762946102933568,
      "loss": 1.0,
      "step": 1010
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001762446509592917,
      "loss": 1.0147,
      "step": 1011
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001761946461305314,
      "loss": 1.0703,
      "step": 1012
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017614459583691346,
      "loss": 1.0713,
      "step": 1013
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001760945001083026,
      "loss": 0.9328,
      "step": 1014
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001760443589745906,
      "loss": 0.9234,
      "step": 1015
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017599417246569636,
      "loss": 1.0064,
      "step": 1016
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017594394061156584,
      "loss": 0.9894,
      "step": 1017
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001758936634421721,
      "loss": 1.0218,
      "step": 1018
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017584334098751518,
      "loss": 1.2169,
      "step": 1019
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017579297327762215,
      "loss": 0.827,
      "step": 1020
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017574256034254716,
      "loss": 1.1552,
      "step": 1021
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017569210221237121,
      "loss": 0.8574,
      "step": 1022
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017564159891720235,
      "loss": 0.9458,
      "step": 1023
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017559105048717562,
      "loss": 1.2934,
      "step": 1024
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017554045695245294,
      "loss": 1.3456,
      "step": 1025
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001754898183432231,
      "loss": 0.9249,
      "step": 1026
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001754391346897019,
      "loss": 0.9839,
      "step": 1027
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001753884060221319,
      "loss": 0.9816,
      "step": 1028
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017533763237078263,
      "loss": 0.8397,
      "step": 1029
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001752868137659503,
      "loss": 1.0189,
      "step": 1030
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017523595023795813,
      "loss": 1.2528,
      "step": 1031
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017518504181715606,
      "loss": 1.0308,
      "step": 1032
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017513408853392078,
      "loss": 0.9419,
      "step": 1033
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001750830904186558,
      "loss": 0.9383,
      "step": 1034
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001750320475017914,
      "loss": 1.1052,
      "step": 1035
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001749809598137845,
      "loss": 0.8541,
      "step": 1036
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017492982738511888,
      "loss": 0.9303,
      "step": 1037
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017487865024630485,
      "loss": 1.0925,
      "step": 1038
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001748274284278795,
      "loss": 0.898,
      "step": 1039
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017477616196040664,
      "loss": 0.9776,
      "step": 1040
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017472485087447655,
      "loss": 1.0811,
      "step": 1041
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017467349520070626,
      "loss": 1.1641,
      "step": 1042
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017462209496973938,
      "loss": 0.9178,
      "step": 1043
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017457065021224608,
      "loss": 1.0422,
      "step": 1044
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017451916095892312,
      "loss": 1.0625,
      "step": 1045
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017446762724049382,
      "loss": 1.0104,
      "step": 1046
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017441604908770798,
      "loss": 0.9569,
      "step": 1047
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017436442653134205,
      "loss": 1.0902,
      "step": 1048
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00017431275960219878,
      "loss": 0.9708,
      "step": 1049
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017426104833110755,
      "loss": 1.0172,
      "step": 1050
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001742092927489241,
      "loss": 1.1096,
      "step": 1051
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017415749288653072,
      "loss": 0.915,
      "step": 1052
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000174105648774836,
      "loss": 1.082,
      "step": 1053
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000174053760444775,
      "loss": 1.035,
      "step": 1054
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017400182792730914,
      "loss": 1.0713,
      "step": 1055
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001739498512534263,
      "loss": 1.0281,
      "step": 1056
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017389783045414055,
      "loss": 0.9376,
      "step": 1057
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017384576556049236,
      "loss": 0.9492,
      "step": 1058
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017379365660354857,
      "loss": 0.9355,
      "step": 1059
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017374150361440226,
      "loss": 0.9861,
      "step": 1060
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001736893066241727,
      "loss": 1.1467,
      "step": 1061
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017363706566400562,
      "loss": 1.0955,
      "step": 1062
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001735847807650728,
      "loss": 0.9131,
      "step": 1063
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017353245195857232,
      "loss": 0.9677,
      "step": 1064
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017348007927572842,
      "loss": 1.1566,
      "step": 1065
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017342766274779157,
      "loss": 1.0431,
      "step": 1066
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001733752024060384,
      "loss": 0.936,
      "step": 1067
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001733226982817716,
      "loss": 0.9462,
      "step": 1068
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017327015040632007,
      "loss": 1.027,
      "step": 1069
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017321755881103882,
      "loss": 0.9844,
      "step": 1070
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017316492352730886,
      "loss": 1.1758,
      "step": 1071
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001731122445865374,
      "loss": 0.9771,
      "step": 1072
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017305952202015755,
      "loss": 0.853,
      "step": 1073
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017300675585962857,
      "loss": 1.0162,
      "step": 1074
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017295394613643574,
      "loss": 0.8723,
      "step": 1075
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00017290109288209017,
      "loss": 0.8866,
      "step": 1076
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017284819612812914,
      "loss": 0.9987,
      "step": 1077
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001727952559061158,
      "loss": 1.065,
      "step": 1078
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017274227224763918,
      "loss": 0.9546,
      "step": 1079
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017268924518431438,
      "loss": 1.1346,
      "step": 1080
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017263617474778224,
      "loss": 0.9991,
      "step": 1081
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017258306096970958,
      "loss": 0.9799,
      "step": 1082
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017252990388178904,
      "loss": 0.9767,
      "step": 1083
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017247670351573912,
      "loss": 0.9792,
      "step": 1084
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017242345990330416,
      "loss": 1.0054,
      "step": 1085
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017237017307625423,
      "loss": 1.1675,
      "step": 1086
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017231684306638528,
      "loss": 0.8316,
      "step": 1087
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017226346990551896,
      "loss": 1.0149,
      "step": 1088
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017221005362550273,
      "loss": 1.0557,
      "step": 1089
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017215659425820972,
      "loss": 1.0901,
      "step": 1090
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017210309183553877,
      "loss": 0.846,
      "step": 1091
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017204954638941447,
      "loss": 0.8797,
      "step": 1092
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000171995957951787,
      "loss": 1.0523,
      "step": 1093
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001719423265546323,
      "loss": 1.0589,
      "step": 1094
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017188865222995186,
      "loss": 1.2338,
      "step": 1095
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017183493500977278,
      "loss": 1.1319,
      "step": 1096
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017178117492614779,
      "loss": 0.8717,
      "step": 1097
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001717273720111552,
      "loss": 1.0893,
      "step": 1098
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017167352629689884,
      "loss": 1.001,
      "step": 1099
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00017161963781550814,
      "loss": 0.9663,
      "step": 1100
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.000171565706599138,
      "loss": 1.1009,
      "step": 1101
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001715117326799688,
      "loss": 1.2291,
      "step": 1102
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001714577160902065,
      "loss": 0.8837,
      "step": 1103
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001714036568620824,
      "loss": 1.1645,
      "step": 1104
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017134955502785327,
      "loss": 1.0058,
      "step": 1105
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001712954106198014,
      "loss": 0.9453,
      "step": 1106
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017124122367023433,
      "loss": 1.2104,
      "step": 1107
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017118699421148518,
      "loss": 1.2069,
      "step": 1108
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001711327222759122,
      "loss": 1.1256,
      "step": 1109
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017107840789589918,
      "loss": 1.0814,
      "step": 1110
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017102405110385515,
      "loss": 0.9653,
      "step": 1111
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017096965193221447,
      "loss": 1.0777,
      "step": 1112
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.7850486040115356,
      "eval_runtime": 935.8449,
      "eval_samples_per_second": 0.783,
      "eval_steps_per_second": 0.392,
      "step": 1112
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001709152104134367,
      "loss": 0.8384,
      "step": 1113
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017086072658000685,
      "loss": 1.0747,
      "step": 1114
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017080620046443503,
      "loss": 1.0254,
      "step": 1115
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001707516320992566,
      "loss": 1.0319,
      "step": 1116
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001706970215170322,
      "loss": 1.0869,
      "step": 1117
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001706423687503476,
      "loss": 0.8592,
      "step": 1118
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017058767383181374,
      "loss": 0.8758,
      "step": 1119
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017053293679406673,
      "loss": 1.0283,
      "step": 1120
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017047815766976782,
      "loss": 1.3295,
      "step": 1121
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017042333649160336,
      "loss": 0.8878,
      "step": 1122
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001703684732922848,
      "loss": 0.985,
      "step": 1123
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017031356810454865,
      "loss": 1.2045,
      "step": 1124
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017025862096115653,
      "loss": 1.0417,
      "step": 1125
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017020363189489495,
      "loss": 1.1186,
      "step": 1126
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017014860093857563,
      "loss": 1.1804,
      "step": 1127
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017009352812503514,
      "loss": 0.9827,
      "step": 1128
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001700384134871351,
      "loss": 0.9053,
      "step": 1129
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00016998325705776203,
      "loss": 0.8919,
      "step": 1130
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00016992805886982746,
      "loss": 0.7927,
      "step": 1131
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00016987281895626774,
      "loss": 0.9655,
      "step": 1132
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001698175373500442,
      "loss": 0.9204,
      "step": 1133
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016976221408414308,
      "loss": 1.0255,
      "step": 1134
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016970684919157534,
      "loss": 1.2521,
      "step": 1135
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016965144270537688,
      "loss": 1.0593,
      "step": 1136
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001695959946586084,
      "loss": 1.0341,
      "step": 1137
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001695405050843554,
      "loss": 1.0431,
      "step": 1138
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016948497401572814,
      "loss": 1.1649,
      "step": 1139
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016942940148586164,
      "loss": 1.0737,
      "step": 1140
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016937378752791572,
      "loss": 0.8796,
      "step": 1141
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016931813217507485,
      "loss": 1.0517,
      "step": 1142
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016926243546054817,
      "loss": 1.1173,
      "step": 1143
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016920669741756964,
      "loss": 0.9743,
      "step": 1144
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016915091807939776,
      "loss": 1.0478,
      "step": 1145
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016909509747931568,
      "loss": 1.1699,
      "step": 1146
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001690392356506312,
      "loss": 0.999,
      "step": 1147
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016898333262667674,
      "loss": 0.7764,
      "step": 1148
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016892738844080928,
      "loss": 1.2541,
      "step": 1149
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016887140312641034,
      "loss": 0.9131,
      "step": 1150
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000168815376716886,
      "loss": 0.932,
      "step": 1151
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016875930924566682,
      "loss": 0.9076,
      "step": 1152
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.000168703200746208,
      "loss": 1.0231,
      "step": 1153
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016864705125198905,
      "loss": 1.0026,
      "step": 1154
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016859086079651402,
      "loss": 0.8801,
      "step": 1155
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016853462941331142,
      "loss": 0.9526,
      "step": 1156
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016847835713593412,
      "loss": 0.8467,
      "step": 1157
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016842204399795946,
      "loss": 0.9244,
      "step": 1158
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016836569003298913,
      "loss": 1.0666,
      "step": 1159
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00016830929527464914,
      "loss": 0.9873,
      "step": 1160
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001682528597565899,
      "loss": 1.1895,
      "step": 1161
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016819638351248616,
      "loss": 1.0929,
      "step": 1162
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016813986657603688,
      "loss": 0.9381,
      "step": 1163
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016808330898096543,
      "loss": 0.9383,
      "step": 1164
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016802671076101926,
      "loss": 1.2002,
      "step": 1165
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016797007194997027,
      "loss": 1.0335,
      "step": 1166
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016791339258161436,
      "loss": 1.0879,
      "step": 1167
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016785667268977186,
      "loss": 0.9462,
      "step": 1168
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001677999123082871,
      "loss": 1.1709,
      "step": 1169
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016774311147102865,
      "loss": 1.0744,
      "step": 1170
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016768627021188922,
      "loss": 1.2164,
      "step": 1171
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001676293885647856,
      "loss": 0.9576,
      "step": 1172
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00016757246656365875,
      "loss": 0.8686,
      "step": 1173
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001675155042424736,
      "loss": 1.0919,
      "step": 1174
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016745850163521925,
      "loss": 1.0016,
      "step": 1175
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016740145877590877,
      "loss": 1.2136,
      "step": 1176
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016734437569857928,
      "loss": 1.0336,
      "step": 1177
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001672872524372919,
      "loss": 1.0491,
      "step": 1178
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001672300890261317,
      "loss": 1.0801,
      "step": 1179
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001671728854992077,
      "loss": 1.0044,
      "step": 1180
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001671156418906529,
      "loss": 1.0646,
      "step": 1181
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001670583582346242,
      "loss": 0.9919,
      "step": 1182
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016700103456530237,
      "loss": 0.8766,
      "step": 1183
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001669436709168921,
      "loss": 0.9111,
      "step": 1184
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001668862673236219,
      "loss": 0.92,
      "step": 1185
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016682882381974413,
      "loss": 0.9201,
      "step": 1186
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016677134043953495,
      "loss": 0.9167,
      "step": 1187
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016671381721729435,
      "loss": 1.0405,
      "step": 1188
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016665625418734606,
      "loss": 1.1332,
      "step": 1189
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016659865138403754,
      "loss": 0.9363,
      "step": 1190
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016654100884174003,
      "loss": 1.2223,
      "step": 1191
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016648332659484848,
      "loss": 0.9267,
      "step": 1192
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016642560467778155,
      "loss": 1.0808,
      "step": 1193
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016636784312498145,
      "loss": 1.0618,
      "step": 1194
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001663100419709142,
      "loss": 1.0127,
      "step": 1195
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016625220125006938,
      "loss": 0.9506,
      "step": 1196
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016619432099696012,
      "loss": 1.0672,
      "step": 1197
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016613640124612326,
      "loss": 1.0275,
      "step": 1198
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001660784420321191,
      "loss": 0.8082,
      "step": 1199
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016602044338953156,
      "loss": 1.0314,
      "step": 1200
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016596240535296804,
      "loss": 1.1101,
      "step": 1201
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001659043279570595,
      "loss": 1.2972,
      "step": 1202
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016584621123646027,
      "loss": 1.2246,
      "step": 1203
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001657880552258483,
      "loss": 0.916,
      "step": 1204
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001657298599599249,
      "loss": 1.0836,
      "step": 1205
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016567162547341478,
      "loss": 1.0405,
      "step": 1206
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016561335180106612,
      "loss": 0.9903,
      "step": 1207
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016555503897765044,
      "loss": 1.2245,
      "step": 1208
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016549668703796263,
      "loss": 0.9374,
      "step": 1209
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016543829601682085,
      "loss": 1.0898,
      "step": 1210
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016537986594906677,
      "loss": 1.0507,
      "step": 1211
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016532139686956514,
      "loss": 1.1046,
      "step": 1212
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016526288881320414,
      "loss": 0.9592,
      "step": 1213
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016520434181489514,
      "loss": 0.9685,
      "step": 1214
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00016514575590957273,
      "loss": 0.9625,
      "step": 1215
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016508713113219477,
      "loss": 1.1145,
      "step": 1216
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016502846751774233,
      "loss": 0.96,
      "step": 1217
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016496976510121952,
      "loss": 0.9616,
      "step": 1218
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016491102391765378,
      "loss": 0.9774,
      "step": 1219
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016485224400209555,
      "loss": 0.9279,
      "step": 1220
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016479342538961843,
      "loss": 0.7609,
      "step": 1221
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016473456811531912,
      "loss": 0.9027,
      "step": 1222
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016467567221431742,
      "loss": 1.1036,
      "step": 1223
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001646167377217561,
      "loss": 0.8461,
      "step": 1224
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016455776467280098,
      "loss": 1.0095,
      "step": 1225
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016449875310264091,
      "loss": 1.2907,
      "step": 1226
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001644397030464877,
      "loss": 1.0966,
      "step": 1227
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016438061453957618,
      "loss": 1.0124,
      "step": 1228
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001643214876171641,
      "loss": 0.9925,
      "step": 1229
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016426232231453206,
      "loss": 1.1358,
      "step": 1230
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001642031186669836,
      "loss": 0.8899,
      "step": 1231
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016414387670984524,
      "loss": 0.9189,
      "step": 1232
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016408459647846623,
      "loss": 1.0855,
      "step": 1233
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001640252780082187,
      "loss": 0.9616,
      "step": 1234
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001639659213344976,
      "loss": 1.0654,
      "step": 1235
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001639065264927207,
      "loss": 0.9351,
      "step": 1236
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001638470935183285,
      "loss": 1.111,
      "step": 1237
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016378762244678428,
      "loss": 1.0434,
      "step": 1238
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016372811331357405,
      "loss": 0.858,
      "step": 1239
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016366856615420656,
      "loss": 0.9691,
      "step": 1240
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016360898100421318,
      "loss": 0.8984,
      "step": 1241
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016354935789914798,
      "loss": 1.0145,
      "step": 1242
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016348969687458772,
      "loss": 1.0961,
      "step": 1243
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001634299979661317,
      "loss": 0.9336,
      "step": 1244
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016337026120940196,
      "loss": 1.2343,
      "step": 1245
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016331048664004297,
      "loss": 1.157,
      "step": 1246
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016325067429372183,
      "loss": 0.8916,
      "step": 1247
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016319082420612825,
      "loss": 0.9962,
      "step": 1248
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001631309364129743,
      "loss": 1.0054,
      "step": 1249
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016307101094999472,
      "loss": 0.8677,
      "step": 1250
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001630110478529466,
      "loss": 0.9484,
      "step": 1251
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001629510471576096,
      "loss": 0.9662,
      "step": 1252
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001628910088997857,
      "loss": 1.0315,
      "step": 1253
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016283093311529937,
      "loss": 1.1276,
      "step": 1254
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001627708198399974,
      "loss": 0.9817,
      "step": 1255
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016271066910974907,
      "loss": 1.1461,
      "step": 1256
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00016265048096044584,
      "loss": 1.0183,
      "step": 1257
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001625902554280017,
      "loss": 0.919,
      "step": 1258
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016252999254835277,
      "loss": 1.0625,
      "step": 1259
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016246969235745752,
      "loss": 0.9431,
      "step": 1260
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016240935489129674,
      "loss": 0.9984,
      "step": 1261
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.8475,
      "step": 1262
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016228856827721263,
      "loss": 0.9092,
      "step": 1263
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016222811920136188,
      "loss": 1.1795,
      "step": 1264
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016216763299439074,
      "loss": 1.0169,
      "step": 1265
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016210710969239092,
      "loss": 0.9836,
      "step": 1266
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001620465493314763,
      "loss": 0.9672,
      "step": 1267
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016198595194778288,
      "loss": 1.2314,
      "step": 1268
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016192531757746868,
      "loss": 0.9379,
      "step": 1269
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001618646462567139,
      "loss": 0.9434,
      "step": 1270
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016180393802172065,
      "loss": 1.0288,
      "step": 1271
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001617431929087132,
      "loss": 1.0137,
      "step": 1272
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016168241095393778,
      "loss": 1.0412,
      "step": 1273
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016162159219366255,
      "loss": 0.9809,
      "step": 1274
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016156073666417773,
      "loss": 0.8514,
      "step": 1275
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016149984440179537,
      "loss": 1.0141,
      "step": 1276
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016143891544284953,
      "loss": 0.949,
      "step": 1277
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001613779498236961,
      "loss": 1.0975,
      "step": 1278
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001613169475807129,
      "loss": 1.0926,
      "step": 1279
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016125590875029958,
      "loss": 1.073,
      "step": 1280
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001611948333688776,
      "loss": 1.0413,
      "step": 1281
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016113372147289026,
      "loss": 0.9657,
      "step": 1282
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001610725730988026,
      "loss": 1.0505,
      "step": 1283
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016101138828310157,
      "loss": 0.9828,
      "step": 1284
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016095016706229565,
      "loss": 0.9952,
      "step": 1285
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016088890947291517,
      "loss": 1.0206,
      "step": 1286
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016082761555151218,
      "loss": 1.0307,
      "step": 1287
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016076628533466037,
      "loss": 1.1467,
      "step": 1288
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016070491885895503,
      "loss": 0.9348,
      "step": 1289
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016064351616101318,
      "loss": 1.2734,
      "step": 1290
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016058207727747344,
      "loss": 1.1221,
      "step": 1291
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016052060224499597,
      "loss": 0.8512,
      "step": 1292
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001604590911002625,
      "loss": 0.9494,
      "step": 1293
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001603975438799764,
      "loss": 0.8365,
      "step": 1294
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016033596062086248,
      "loss": 1.1157,
      "step": 1295
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016027434135966706,
      "loss": 0.9591,
      "step": 1296
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016021268613315796,
      "loss": 1.0524,
      "step": 1297
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016015099497812446,
      "loss": 0.8711,
      "step": 1298
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016008926793137734,
      "loss": 0.7844,
      "step": 1299
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001600275050297486,
      "loss": 1.0912,
      "step": 1300
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00015996570631009188,
      "loss": 0.9163,
      "step": 1301
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00015990387180928205,
      "loss": 0.9337,
      "step": 1302
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00015984200156421536,
      "loss": 0.885,
      "step": 1303
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001597800956118094,
      "loss": 0.8827,
      "step": 1304
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00015971815398900302,
      "loss": 0.8996,
      "step": 1305
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001596561767327564,
      "loss": 0.9129,
      "step": 1306
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000159594163880051,
      "loss": 0.9626,
      "step": 1307
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001595321154678895,
      "loss": 0.911,
      "step": 1308
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00015947003153329574,
      "loss": 0.9815,
      "step": 1309
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001594079121133148,
      "loss": 1.1268,
      "step": 1310
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000159345757245013,
      "loss": 0.9514,
      "step": 1311
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00015928356696547774,
      "loss": 1.0646,
      "step": 1312
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00015922134131181754,
      "loss": 0.8848,
      "step": 1313
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015915908032116207,
      "loss": 0.8997,
      "step": 1314
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015909678403066204,
      "loss": 1.017,
      "step": 1315
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015903445247748924,
      "loss": 1.0123,
      "step": 1316
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015897208569883655,
      "loss": 1.0782,
      "step": 1317
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001589096837319178,
      "loss": 1.1566,
      "step": 1318
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015884724661396785,
      "loss": 0.9521,
      "step": 1319
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015878477438224252,
      "loss": 1.009,
      "step": 1320
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015872226707401864,
      "loss": 0.9304,
      "step": 1321
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015865972472659383,
      "loss": 1.0072,
      "step": 1322
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015859714737728674,
      "loss": 0.8733,
      "step": 1323
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00015853453506343694,
      "loss": 0.9394,
      "step": 1324
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001584718878224047,
      "loss": 0.9074,
      "step": 1325
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001584092056915713,
      "loss": 0.9996,
      "step": 1326
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015834648870833876,
      "loss": 0.8327,
      "step": 1327
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001582837369101299,
      "loss": 0.9426,
      "step": 1328
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015822095033438826,
      "loss": 1.0115,
      "step": 1329
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015815812901857825,
      "loss": 0.9013,
      "step": 1330
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015809527300018493,
      "loss": 1.1093,
      "step": 1331
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015803238231671405,
      "loss": 1.0391,
      "step": 1332
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015796945700569212,
      "loss": 0.9817,
      "step": 1333
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015790649710466627,
      "loss": 1.0939,
      "step": 1334
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015784350265120426,
      "loss": 1.2318,
      "step": 1335
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015778047368289445,
      "loss": 1.0294,
      "step": 1336
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015771741023734586,
      "loss": 0.8372,
      "step": 1337
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015765431235218805,
      "loss": 0.9652,
      "step": 1338
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001575911800650711,
      "loss": 0.9536,
      "step": 1339
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015752801341366562,
      "loss": 0.9297,
      "step": 1340
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001574648124356628,
      "loss": 0.9724,
      "step": 1341
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015740157716877422,
      "loss": 0.9901,
      "step": 1342
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.000157338307650732,
      "loss": 0.8892,
      "step": 1343
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001572750039192886,
      "loss": 1.0164,
      "step": 1344
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015721166601221698,
      "loss": 0.9222,
      "step": 1345
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015714829396731048,
      "loss": 1.0177,
      "step": 1346
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015708488782238277,
      "loss": 1.0282,
      "step": 1347
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015702144761526788,
      "loss": 1.0142,
      "step": 1348
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015695797338382018,
      "loss": 0.999,
      "step": 1349
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015689446516591442,
      "loss": 1.124,
      "step": 1350
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015683092299944543,
      "loss": 0.9825,
      "step": 1351
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015676734692232847,
      "loss": 1.0264,
      "step": 1352
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015670373697249896,
      "loss": 0.9841,
      "step": 1353
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00015664009318791256,
      "loss": 1.1235,
      "step": 1354
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001565764156065451,
      "loss": 0.9877,
      "step": 1355
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001565127042663926,
      "loss": 0.8606,
      "step": 1356
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015644895920547124,
      "loss": 1.1673,
      "step": 1357
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015638518046181722,
      "loss": 0.8298,
      "step": 1358
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015632136807348696,
      "loss": 0.9338,
      "step": 1359
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015625752207855688,
      "loss": 1.0057,
      "step": 1360
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015619364251512346,
      "loss": 0.8649,
      "step": 1361
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015612972942130327,
      "loss": 1.0127,
      "step": 1362
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015606578283523283,
      "loss": 1.0491,
      "step": 1363
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001560018027950686,
      "loss": 0.9677,
      "step": 1364
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015593778933898717,
      "loss": 0.9017,
      "step": 1365
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015587374250518486,
      "loss": 1.0107,
      "step": 1366
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015580966233187812,
      "loss": 0.9913,
      "step": 1367
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00015574554885730302,
      "loss": 0.999,
      "step": 1368
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015568140211971577,
      "loss": 0.9822,
      "step": 1369
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001556172221573923,
      "loss": 0.9625,
      "step": 1370
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015555300900862835,
      "loss": 0.938,
      "step": 1371
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015548876271173954,
      "loss": 1.1189,
      "step": 1372
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001554244833050612,
      "loss": 0.7748,
      "step": 1373
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015536017082694846,
      "loss": 0.9517,
      "step": 1374
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015529582531577613,
      "loss": 1.0503,
      "step": 1375
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015523144680993882,
      "loss": 1.1711,
      "step": 1376
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001551670353478507,
      "loss": 1.0989,
      "step": 1377
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015510259096794573,
      "loss": 1.0802,
      "step": 1378
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015503811370867743,
      "loss": 0.8572,
      "step": 1379
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015497360360851897,
      "loss": 0.8439,
      "step": 1380
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015490906070596316,
      "loss": 1.2118,
      "step": 1381
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015484448503952226,
      "loss": 1.0119,
      "step": 1382
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015477987664772822,
      "loss": 1.0906,
      "step": 1383
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001547152355691324,
      "loss": 0.9709,
      "step": 1384
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001546505618423058,
      "loss": 0.921,
      "step": 1385
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015458585550583872,
      "loss": 1.0387,
      "step": 1386
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001545211165983411,
      "loss": 0.9929,
      "step": 1387
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015445634515844222,
      "loss": 0.9121,
      "step": 1388
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001543915412247907,
      "loss": 0.9964,
      "step": 1389
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015432670483605474,
      "loss": 0.8615,
      "step": 1390
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7791540026664734,
      "eval_runtime": 928.7562,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.395,
      "step": 1390
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015426183603092173,
      "loss": 0.9397,
      "step": 1391
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015419693484809848,
      "loss": 1.0379,
      "step": 1392
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015413200132631113,
      "loss": 0.9745,
      "step": 1393
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001540670355043051,
      "loss": 0.9844,
      "step": 1394
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015400203742084508,
      "loss": 1.0776,
      "step": 1395
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015393700711471495,
      "loss": 1.0496,
      "step": 1396
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015387194462471797,
      "loss": 1.0612,
      "step": 1397
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015380684998967642,
      "loss": 0.9598,
      "step": 1398
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015374172324843192,
      "loss": 1.0068,
      "step": 1399
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001536765644398452,
      "loss": 1.0536,
      "step": 1400
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015361137360279603,
      "loss": 1.0369,
      "step": 1401
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001535461507761834,
      "loss": 1.0309,
      "step": 1402
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015348089599892534,
      "loss": 0.8315,
      "step": 1403
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.000153415609309959,
      "loss": 0.9204,
      "step": 1404
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015335029074824047,
      "loss": 1.0262,
      "step": 1405
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015328494035274498,
      "loss": 0.9796,
      "step": 1406
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015321955816246664,
      "loss": 1.1701,
      "step": 1407
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001531541442164186,
      "loss": 1.0616,
      "step": 1408
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015308869855363294,
      "loss": 1.0088,
      "step": 1409
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015302322121316068,
      "loss": 0.9842,
      "step": 1410
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015295771223407175,
      "loss": 0.809,
      "step": 1411
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001528921716554549,
      "loss": 0.9582,
      "step": 1412
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015282659951641777,
      "loss": 0.8679,
      "step": 1413
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015276099585608685,
      "loss": 1.2286,
      "step": 1414
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015269536071360745,
      "loss": 1.0593,
      "step": 1415
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015262969412814357,
      "loss": 1.1407,
      "step": 1416
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015256399613887815,
      "loss": 1.0003,
      "step": 1417
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001524982667850127,
      "loss": 0.8867,
      "step": 1418
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015243250610576744,
      "loss": 0.9333,
      "step": 1419
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015236671414038143,
      "loss": 0.9329,
      "step": 1420
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015230089092811233,
      "loss": 0.9483,
      "step": 1421
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015223503650823634,
      "loss": 0.9292,
      "step": 1422
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015216915092004847,
      "loss": 0.9202,
      "step": 1423
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015210323420286216,
      "loss": 0.7027,
      "step": 1424
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015203728639600952,
      "loss": 0.8405,
      "step": 1425
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015197130753884117,
      "loss": 0.9071,
      "step": 1426
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015190529767072626,
      "loss": 0.8969,
      "step": 1427
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015183925683105254,
      "loss": 0.9092,
      "step": 1428
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.000151773185059226,
      "loss": 0.8918,
      "step": 1429
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001517070823946714,
      "loss": 0.9306,
      "step": 1430
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015164094887683171,
      "loss": 1.1913,
      "step": 1431
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015157478454516838,
      "loss": 0.9755,
      "step": 1432
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015150858943916123,
      "loss": 0.8202,
      "step": 1433
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015144236359830848,
      "loss": 1.0101,
      "step": 1434
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015137610706212666,
      "loss": 0.9648,
      "step": 1435
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015130981987015058,
      "loss": 1.0038,
      "step": 1436
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015124350206193347,
      "loss": 0.9932,
      "step": 1437
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015117715367704663,
      "loss": 1.0095,
      "step": 1438
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015111077475507984,
      "loss": 1.0926,
      "step": 1439
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015104436533564092,
      "loss": 0.9521,
      "step": 1440
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015097792545835587,
      "loss": 0.8567,
      "step": 1441
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015091145516286906,
      "loss": 0.9264,
      "step": 1442
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001508449544888428,
      "loss": 1.0447,
      "step": 1443
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015077842347595768,
      "loss": 1.1059,
      "step": 1444
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001507118621639123,
      "loss": 1.198,
      "step": 1445
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015064527059242336,
      "loss": 0.7798,
      "step": 1446
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001505786488012257,
      "loss": 0.9855,
      "step": 1447
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015051199683007203,
      "loss": 1.1815,
      "step": 1448
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015044531471873314,
      "loss": 0.7616,
      "step": 1449
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015037860250699788,
      "loss": 0.8544,
      "step": 1450
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015031186023467297,
      "loss": 1.077,
      "step": 1451
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00015024508794158313,
      "loss": 0.9286,
      "step": 1452
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00015017828566757092,
      "loss": 0.6964,
      "step": 1453
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00015011145345249685,
      "loss": 0.8996,
      "step": 1454
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00015004459133623928,
      "loss": 1.2624,
      "step": 1455
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014997769935869436,
      "loss": 1.0945,
      "step": 1456
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014991077755977615,
      "loss": 1.0649,
      "step": 1457
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001498438259794165,
      "loss": 0.8517,
      "step": 1458
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014977684465756485,
      "loss": 0.9769,
      "step": 1459
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014970983363418868,
      "loss": 0.8607,
      "step": 1460
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014964279294927296,
      "loss": 0.8379,
      "step": 1461
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014957572264282044,
      "loss": 0.8826,
      "step": 1462
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014950862275485159,
      "loss": 0.9381,
      "step": 1463
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014944149332540442,
      "loss": 0.9213,
      "step": 1464
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014937433439453466,
      "loss": 1.0044,
      "step": 1465
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00014930714600231562,
      "loss": 0.895,
      "step": 1466
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014923992818883817,
      "loss": 0.9081,
      "step": 1467
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014917268099421074,
      "loss": 0.804,
      "step": 1468
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014910540445855935,
      "loss": 1.0622,
      "step": 1469
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014903809862202742,
      "loss": 0.8233,
      "step": 1470
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014897076352477593,
      "loss": 1.0745,
      "step": 1471
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014890339920698334,
      "loss": 0.8422,
      "step": 1472
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014883600570884543,
      "loss": 0.9222,
      "step": 1473
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014876858307057554,
      "loss": 0.9488,
      "step": 1474
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014870113133240431,
      "loss": 0.7991,
      "step": 1475
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014863365053457975,
      "loss": 0.8259,
      "step": 1476
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014856614071736722,
      "loss": 0.8442,
      "step": 1477
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014849860192104938,
      "loss": 1.0084,
      "step": 1478
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001484310341859262,
      "loss": 0.7852,
      "step": 1479
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014836343755231495,
      "loss": 0.8642,
      "step": 1480
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014829581206055013,
      "loss": 0.817,
      "step": 1481
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014822815775098334,
      "loss": 0.7283,
      "step": 1482
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014816047466398354,
      "loss": 0.9651,
      "step": 1483
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001480927628399368,
      "loss": 0.9109,
      "step": 1484
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014802502231924628,
      "loss": 1.0948,
      "step": 1485
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014795725314233237,
      "loss": 0.8866,
      "step": 1486
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014788945534963252,
      "loss": 0.813,
      "step": 1487
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014782162898160114,
      "loss": 0.8861,
      "step": 1488
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014775377407870988,
      "loss": 0.9904,
      "step": 1489
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014768589068144734,
      "loss": 0.9179,
      "step": 1490
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014761797883031902,
      "loss": 0.8119,
      "step": 1491
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014755003856584757,
      "loss": 0.7655,
      "step": 1492
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00014748206992857245,
      "loss": 1.215,
      "step": 1493
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014741407295905013,
      "loss": 0.8933,
      "step": 1494
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014734604769785402,
      "loss": 0.9284,
      "step": 1495
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014727799418557427,
      "loss": 0.8354,
      "step": 1496
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014720991246281804,
      "loss": 1.0569,
      "step": 1497
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014714180257020923,
      "loss": 0.7894,
      "step": 1498
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014707366454838855,
      "loss": 0.8898,
      "step": 1499
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001470054984380136,
      "loss": 0.8795,
      "step": 1500
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014693730427975857,
      "loss": 1.0777,
      "step": 1501
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014686908211431455,
      "loss": 0.7832,
      "step": 1502
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014680083198238922,
      "loss": 0.9057,
      "step": 1503
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014673255392470705,
      "loss": 0.8926,
      "step": 1504
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014666424798200908,
      "loss": 0.7906,
      "step": 1505
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014659591419505306,
      "loss": 0.8016,
      "step": 1506
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00014652755260461325,
      "loss": 1.013,
      "step": 1507
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014645916325148065,
      "loss": 0.9187,
      "step": 1508
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014639074617646273,
      "loss": 1.105,
      "step": 1509
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001463223014203835,
      "loss": 0.8444,
      "step": 1510
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014625382902408356,
      "loss": 0.9258,
      "step": 1511
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014618532902841986,
      "loss": 0.888,
      "step": 1512
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014611680147426598,
      "loss": 1.0182,
      "step": 1513
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014604824640251186,
      "loss": 0.9515,
      "step": 1514
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014597966385406386,
      "loss": 1.0508,
      "step": 1515
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014591105386984482,
      "loss": 0.9691,
      "step": 1516
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001458424164907937,
      "loss": 0.9946,
      "step": 1517
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014577375175786616,
      "loss": 0.9429,
      "step": 1518
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014570505971203394,
      "loss": 0.8221,
      "step": 1519
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014563634039428512,
      "loss": 0.915,
      "step": 1520
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00014556759384562416,
      "loss": 0.6844,
      "step": 1521
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001454988201070716,
      "loss": 0.8546,
      "step": 1522
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014543001921966432,
      "loss": 0.9238,
      "step": 1523
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001453611912244554,
      "loss": 0.9909,
      "step": 1524
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.000145292336162514,
      "loss": 1.0559,
      "step": 1525
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014522345407492554,
      "loss": 0.8686,
      "step": 1526
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014515454500279153,
      "loss": 1.0868,
      "step": 1527
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014508560898722952,
      "loss": 0.9925,
      "step": 1528
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014501664606937325,
      "loss": 1.0425,
      "step": 1529
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014494765629037237,
      "loss": 1.1697,
      "step": 1530
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014487863969139272,
      "loss": 0.8216,
      "step": 1531
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014480959631361606,
      "loss": 0.8624,
      "step": 1532
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014474052619824006,
      "loss": 0.9548,
      "step": 1533
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014467142938647852,
      "loss": 0.9007,
      "step": 1534
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014460230591956097,
      "loss": 1.0247,
      "step": 1535
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014453315583873297,
      "loss": 0.9297,
      "step": 1536
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014446397918525597,
      "loss": 0.8734,
      "step": 1537
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001443947760004072,
      "loss": 0.866,
      "step": 1538
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014432554632547975,
      "loss": 0.9656,
      "step": 1539
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014425629020178252,
      "loss": 0.9656,
      "step": 1540
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014418700767064024,
      "loss": 0.867,
      "step": 1541
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014411769877339332,
      "loss": 0.9416,
      "step": 1542
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014404836355139792,
      "loss": 1.044,
      "step": 1543
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014397900204602597,
      "loss": 0.9714,
      "step": 1544
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000143909614298665,
      "loss": 0.8569,
      "step": 1545
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014384020035071823,
      "loss": 0.8368,
      "step": 1546
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014377076024360457,
      "loss": 0.7556,
      "step": 1547
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001437012940187584,
      "loss": 1.0584,
      "step": 1548
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014363180171762983,
      "loss": 0.9739,
      "step": 1549
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014356228338168448,
      "loss": 0.852,
      "step": 1550
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014349273905240348,
      "loss": 1.1317,
      "step": 1551
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001434231687712835,
      "loss": 1.1705,
      "step": 1552
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014335357257983666,
      "loss": 0.9476,
      "step": 1553
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014328395051959057,
      "loss": 0.9573,
      "step": 1554
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014321430263208824,
      "loss": 0.9498,
      "step": 1555
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014314462895888817,
      "loss": 1.0111,
      "step": 1556
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014307492954156414,
      "loss": 1.0951,
      "step": 1557
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014300520442170542,
      "loss": 0.6944,
      "step": 1558
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014293545364091648,
      "loss": 1.0027,
      "step": 1559
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014286567724081716,
      "loss": 1.0503,
      "step": 1560
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014279587526304266,
      "loss": 0.7178,
      "step": 1561
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00014272604774924328,
      "loss": 0.9294,
      "step": 1562
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001426561947410847,
      "loss": 0.8308,
      "step": 1563
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014258631628024778,
      "loss": 1.0206,
      "step": 1564
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014251641240842854,
      "loss": 0.9802,
      "step": 1565
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014244648316733815,
      "loss": 0.7762,
      "step": 1566
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014237652859870297,
      "loss": 0.8912,
      "step": 1567
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001423065487442644,
      "loss": 1.033,
      "step": 1568
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014223654364577904,
      "loss": 0.7925,
      "step": 1569
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001421665133450184,
      "loss": 0.7605,
      "step": 1570
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001420964578837692,
      "loss": 0.8598,
      "step": 1571
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.000142026377303833,
      "loss": 1.1695,
      "step": 1572
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001419562716470265,
      "loss": 0.86,
      "step": 1573
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014188614095518126,
      "loss": 0.7892,
      "step": 1574
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014181598527014384,
      "loss": 0.9313,
      "step": 1575
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014174580463377566,
      "loss": 0.8196,
      "step": 1576
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014167559908795306,
      "loss": 0.8073,
      "step": 1577
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014160536867456727,
      "loss": 0.9295,
      "step": 1578
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001415351134355243,
      "loss": 0.8311,
      "step": 1579
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014146483341274498,
      "loss": 0.8659,
      "step": 1580
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014139452864816505,
      "loss": 0.8492,
      "step": 1581
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014132419918373482,
      "loss": 1.0329,
      "step": 1582
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001412538450614194,
      "loss": 1.0641,
      "step": 1583
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014118346632319877,
      "loss": 0.983,
      "step": 1584
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014111306301106734,
      "loss": 1.0848,
      "step": 1585
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014104263516703442,
      "loss": 1.0393,
      "step": 1586
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001409721828331238,
      "loss": 0.717,
      "step": 1587
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014090170605137394,
      "loss": 1.107,
      "step": 1588
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001408312048638379,
      "loss": 0.9052,
      "step": 1589
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014076067931258326,
      "loss": 0.9793,
      "step": 1590
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001406901294396922,
      "loss": 0.9111,
      "step": 1591
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014061955528726135,
      "loss": 0.8291,
      "step": 1592
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001405489568974019,
      "loss": 0.9121,
      "step": 1593
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014047833431223938,
      "loss": 0.807,
      "step": 1594
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014040768757391393,
      "loss": 0.8318,
      "step": 1595
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014033701672457987,
      "loss": 0.7758,
      "step": 1596
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014026632180640623,
      "loss": 0.863,
      "step": 1597
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014019560286157606,
      "loss": 0.8492,
      "step": 1598
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014012485993228693,
      "loss": 0.9212,
      "step": 1599
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00014005409306075078,
      "loss": 0.9922,
      "step": 1600
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00013998330228919364,
      "loss": 1.0294,
      "step": 1601
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00013991248765985598,
      "loss": 0.904,
      "step": 1602
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00013984164921499243,
      "loss": 0.8833,
      "step": 1603
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00013977078699687178,
      "loss": 1.1101,
      "step": 1604
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00013969990104777713,
      "loss": 0.9328,
      "step": 1605
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013962899141000562,
      "loss": 0.8996,
      "step": 1606
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013955805812586861,
      "loss": 0.9525,
      "step": 1607
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013948710123769156,
      "loss": 1.0303,
      "step": 1608
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013941612078781392,
      "loss": 1.1084,
      "step": 1609
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013934511681858934,
      "loss": 0.9131,
      "step": 1610
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013927408937238538,
      "loss": 0.9034,
      "step": 1611
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001392030384915837,
      "loss": 1.2482,
      "step": 1612
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001391319642185799,
      "loss": 0.9724,
      "step": 1613
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013906086659578348,
      "loss": 1.1804,
      "step": 1614
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013898974566561804,
      "loss": 0.8643,
      "step": 1615
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013891860147052093,
      "loss": 0.7167,
      "step": 1616
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013884743405294346,
      "loss": 0.8131,
      "step": 1617
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00013877624345535073,
      "loss": 1.0451,
      "step": 1618
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013870502972022173,
      "loss": 1.0901,
      "step": 1619
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013863379289004926,
      "loss": 0.817,
      "step": 1620
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013856253300733985,
      "loss": 0.7033,
      "step": 1621
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013849125011461386,
      "loss": 0.938,
      "step": 1622
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013841994425440527,
      "loss": 0.9725,
      "step": 1623
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013834861546926192,
      "loss": 0.7769,
      "step": 1624
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013827726380174514,
      "loss": 0.9296,
      "step": 1625
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013820588929443014,
      "loss": 1.0251,
      "step": 1626
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013813449198990548,
      "loss": 0.8129,
      "step": 1627
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013806307193077358,
      "loss": 0.8553,
      "step": 1628
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001379916291596503,
      "loss": 0.9587,
      "step": 1629
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013792016371916508,
      "loss": 1.0043,
      "step": 1630
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013784867565196088,
      "loss": 0.8788,
      "step": 1631
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00013777716500069424,
      "loss": 0.9478,
      "step": 1632
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013770563180803502,
      "loss": 0.7938,
      "step": 1633
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013763407611666666,
      "loss": 1.0448,
      "step": 1634
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013756249796928596,
      "loss": 0.9509,
      "step": 1635
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001374908974086032,
      "loss": 0.9289,
      "step": 1636
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013741927447734188,
      "loss": 1.005,
      "step": 1637
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013734762921823902,
      "loss": 0.7128,
      "step": 1638
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001372759616740449,
      "loss": 1.1602,
      "step": 1639
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013720427188752306,
      "loss": 0.8829,
      "step": 1640
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013713255990145025,
      "loss": 0.7118,
      "step": 1641
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013706082575861672,
      "loss": 0.9856,
      "step": 1642
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013698906950182564,
      "loss": 0.9012,
      "step": 1643
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013691729117389358,
      "loss": 1.0288,
      "step": 1644
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001368454908176502,
      "loss": 0.9048,
      "step": 1645
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00013677366847593823,
      "loss": 0.9894,
      "step": 1646
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013670182419161375,
      "loss": 1.0886,
      "step": 1647
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013662995800754564,
      "loss": 0.9601,
      "step": 1648
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001365580699666161,
      "loss": 1.03,
      "step": 1649
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013648616011172022,
      "loss": 1.1353,
      "step": 1650
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001364142284857661,
      "loss": 0.8812,
      "step": 1651
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013634227513167497,
      "loss": 0.899,
      "step": 1652
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001362703000923809,
      "loss": 0.7508,
      "step": 1653
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001361983034108309,
      "loss": 0.9988,
      "step": 1654
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013612628512998498,
      "loss": 1.1625,
      "step": 1655
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.000136054245292816,
      "loss": 0.8746,
      "step": 1656
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013598218394230956,
      "loss": 0.982,
      "step": 1657
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013591010112146436,
      "loss": 0.9934,
      "step": 1658
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013583799687329163,
      "loss": 0.9845,
      "step": 1659
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00013576587124081562,
      "loss": 0.8263,
      "step": 1660
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013569372426707314,
      "loss": 1.0312,
      "step": 1661
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013562155599511385,
      "loss": 1.0683,
      "step": 1662
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013554936646800015,
      "loss": 0.9311,
      "step": 1663
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013547715572880702,
      "loss": 1.0131,
      "step": 1664
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013540492382062215,
      "loss": 1.173,
      "step": 1665
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013533267078654585,
      "loss": 0.8021,
      "step": 1666
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013526039666969107,
      "loss": 0.8081,
      "step": 1667
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001351881015131833,
      "loss": 0.818,
      "step": 1668
    },
    {
      "epoch": 1.18,
      "eval_loss": 0.7836685180664062,
      "eval_runtime": 934.3236,
      "eval_samples_per_second": 0.785,
      "eval_steps_per_second": 0.393,
      "step": 1668
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013511578536016064,
      "loss": 1.0035,
      "step": 1669
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013504344825377356,
      "loss": 0.8885,
      "step": 1670
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013497109023718527,
      "loss": 0.8129,
      "step": 1671
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013489871135357126,
      "loss": 0.8447,
      "step": 1672
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013482631164611958,
      "loss": 0.7096,
      "step": 1673
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00013475389115803069,
      "loss": 1.0408,
      "step": 1674
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013468144993251734,
      "loss": 1.0486,
      "step": 1675
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013460898801280488,
      "loss": 1.0318,
      "step": 1676
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013453650544213076,
      "loss": 0.8609,
      "step": 1677
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013446400226374493,
      "loss": 0.9255,
      "step": 1678
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001343914785209096,
      "loss": 0.9887,
      "step": 1679
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001343189342568991,
      "loss": 0.8369,
      "step": 1680
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013424636951500022,
      "loss": 0.8003,
      "step": 1681
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013417378433851188,
      "loss": 0.9334,
      "step": 1682
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013410117877074516,
      "loss": 0.7785,
      "step": 1683
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013402855285502338,
      "loss": 0.8739,
      "step": 1684
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001339559066346819,
      "loss": 0.7473,
      "step": 1685
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001338832401530683,
      "loss": 0.8595,
      "step": 1686
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013381055345354219,
      "loss": 0.7097,
      "step": 1687
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013373784657947523,
      "loss": 0.843,
      "step": 1688
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001336651195742512,
      "loss": 0.9633,
      "step": 1689
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001335923724812658,
      "loss": 0.7345,
      "step": 1690
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013351960534392678,
      "loss": 0.8813,
      "step": 1691
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013344681820565382,
      "loss": 1.0298,
      "step": 1692
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001333740111098785,
      "loss": 1.0543,
      "step": 1693
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013330118410004438,
      "loss": 0.9741,
      "step": 1694
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013322833721960689,
      "loss": 1.009,
      "step": 1695
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001331554705120332,
      "loss": 1.0895,
      "step": 1696
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013308258402080258,
      "loss": 1.0191,
      "step": 1697
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001330096777894058,
      "loss": 0.7984,
      "step": 1698
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013293675186134556,
      "loss": 0.9957,
      "step": 1699
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013286380628013634,
      "loss": 1.0073,
      "step": 1700
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013279084108930425,
      "loss": 0.9108,
      "step": 1701
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001327178563323872,
      "loss": 1.1517,
      "step": 1702
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013264485205293473,
      "loss": 1.031,
      "step": 1703
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013257182829450796,
      "loss": 0.8415,
      "step": 1704
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013249878510067977,
      "loss": 0.9839,
      "step": 1705
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001324257225150345,
      "loss": 0.9189,
      "step": 1706
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013235264058116818,
      "loss": 1.0045,
      "step": 1707
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013227953934268833,
      "loss": 0.9945,
      "step": 1708
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013220641884321394,
      "loss": 0.9577,
      "step": 1709
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013213327912637562,
      "loss": 0.9107,
      "step": 1710
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001320601202358153,
      "loss": 0.9295,
      "step": 1711
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013198694221518644,
      "loss": 0.921,
      "step": 1712
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013191374510815396,
      "loss": 1.0794,
      "step": 1713
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013184052895839402,
      "loss": 0.9698,
      "step": 1714
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013176729380959428,
      "loss": 0.8113,
      "step": 1715
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00013169403970545365,
      "loss": 0.8697,
      "step": 1716
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001316207666896824,
      "loss": 0.767,
      "step": 1717
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013154747480600208,
      "loss": 0.8966,
      "step": 1718
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013147416409814547,
      "loss": 0.9265,
      "step": 1719
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013140083460985664,
      "loss": 0.6937,
      "step": 1720
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001313274863848908,
      "loss": 0.8889,
      "step": 1721
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001312541194670143,
      "loss": 0.9465,
      "step": 1722
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013118073390000482,
      "loss": 0.9612,
      "step": 1723
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013110732972765102,
      "loss": 0.9971,
      "step": 1724
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013103390699375264,
      "loss": 1.0146,
      "step": 1725
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013096046574212063,
      "loss": 0.7795,
      "step": 1726
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013088700601657688,
      "loss": 0.8417,
      "step": 1727
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013081352786095435,
      "loss": 0.7575,
      "step": 1728
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.000130740031319097,
      "loss": 1.1119,
      "step": 1729
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013066651643485973,
      "loss": 0.8646,
      "step": 1730
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001305929832521084,
      "loss": 1.0883,
      "step": 1731
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001305194318147198,
      "loss": 0.7618,
      "step": 1732
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013044586216658157,
      "loss": 0.741,
      "step": 1733
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013037227435159227,
      "loss": 0.9787,
      "step": 1734
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013029866841366127,
      "loss": 0.9942,
      "step": 1735
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013022504439670878,
      "loss": 1.1576,
      "step": 1736
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001301514023446658,
      "loss": 0.9022,
      "step": 1737
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.000130077742301474,
      "loss": 0.8833,
      "step": 1738
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013000406431108594,
      "loss": 0.9176,
      "step": 1739
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00012993036841746472,
      "loss": 0.8195,
      "step": 1740
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00012985665466458426,
      "loss": 0.721,
      "step": 1741
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00012978292309642907,
      "loss": 0.7664,
      "step": 1742
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00012970917375699432,
      "loss": 0.9063,
      "step": 1743
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00012963540669028577,
      "loss": 0.9644,
      "step": 1744
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001295616219403197,
      "loss": 0.8659,
      "step": 1745
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012948781955112308,
      "loss": 0.8834,
      "step": 1746
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012941399956673327,
      "loss": 0.9119,
      "step": 1747
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012934016203119822,
      "loss": 0.8238,
      "step": 1748
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012926630698857628,
      "loss": 0.9757,
      "step": 1749
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001291924344829363,
      "loss": 0.9338,
      "step": 1750
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001291185445583575,
      "loss": 0.7941,
      "step": 1751
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012904463725892958,
      "loss": 0.8145,
      "step": 1752
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012897071262875254,
      "loss": 0.7823,
      "step": 1753
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012889677071193666,
      "loss": 1.0448,
      "step": 1754
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012882281155260272,
      "loss": 0.7496,
      "step": 1755
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00012874883519488158,
      "loss": 0.9043,
      "step": 1756
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001286748416829145,
      "loss": 1.0135,
      "step": 1757
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012860083106085296,
      "loss": 0.7927,
      "step": 1758
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001285268033728586,
      "loss": 1.1306,
      "step": 1759
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012845275866310324,
      "loss": 0.7366,
      "step": 1760
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012837869697576894,
      "loss": 0.9837,
      "step": 1761
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001283046183550478,
      "loss": 1.0372,
      "step": 1762
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012823052284514208,
      "loss": 0.8726,
      "step": 1763
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012815641049026405,
      "loss": 0.85,
      "step": 1764
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012808228133463615,
      "loss": 0.9431,
      "step": 1765
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012800813542249072,
      "loss": 0.7633,
      "step": 1766
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012793397279807012,
      "loss": 1.125,
      "step": 1767
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012785979350562682,
      "loss": 1.1042,
      "step": 1768
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012778559758942304,
      "loss": 1.1566,
      "step": 1769
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00012771138509373102,
      "loss": 0.9023,
      "step": 1770
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001276371560628329,
      "loss": 0.946,
      "step": 1771
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012756291054102068,
      "loss": 0.8148,
      "step": 1772
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012748864857259617,
      "loss": 0.8172,
      "step": 1773
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.000127414370201871,
      "loss": 0.7556,
      "step": 1774
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012734007547316663,
      "loss": 0.9343,
      "step": 1775
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012726576443081422,
      "loss": 0.9465,
      "step": 1776
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001271914371191547,
      "loss": 0.9691,
      "step": 1777
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001271170935825387,
      "loss": 0.7638,
      "step": 1778
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012704273386532653,
      "loss": 1.0198,
      "step": 1779
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012696835801188816,
      "loss": 0.9296,
      "step": 1780
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012689396606660323,
      "loss": 0.9198,
      "step": 1781
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012681955807386085,
      "loss": 0.9076,
      "step": 1782
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012674513407805985,
      "loss": 0.9951,
      "step": 1783
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00012667069412360856,
      "loss": 0.9294,
      "step": 1784
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001265962382549248,
      "loss": 0.7834,
      "step": 1785
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001265217665164359,
      "loss": 0.8793,
      "step": 1786
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012644727895257872,
      "loss": 0.7094,
      "step": 1787
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012637277560779942,
      "loss": 1.0673,
      "step": 1788
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012629825652655377,
      "loss": 0.9566,
      "step": 1789
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001262237217533068,
      "loss": 0.8909,
      "step": 1790
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012614917133253287,
      "loss": 0.7661,
      "step": 1791
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012607460530871586,
      "loss": 0.9872,
      "step": 1792
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012600002372634869,
      "loss": 0.8555,
      "step": 1793
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012592542662993384,
      "loss": 0.9303,
      "step": 1794
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012585081406398286,
      "loss": 0.9245,
      "step": 1795
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012577618607301658,
      "loss": 0.882,
      "step": 1796
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012570154270156506,
      "loss": 0.803,
      "step": 1797
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012562688399416755,
      "loss": 1.0067,
      "step": 1798
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012555220999537238,
      "loss": 0.9438,
      "step": 1799
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012547752074973707,
      "loss": 0.845,
      "step": 1800
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001254028163018282,
      "loss": 1.0588,
      "step": 1801
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012532809669622147,
      "loss": 0.8435,
      "step": 1802
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012525336197750158,
      "loss": 1.1037,
      "step": 1803
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001251786121902622,
      "loss": 0.9547,
      "step": 1804
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012510384737910614,
      "loss": 0.9643,
      "step": 1805
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012502906758864502,
      "loss": 0.7601,
      "step": 1806
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012495427286349946,
      "loss": 1.0108,
      "step": 1807
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012487946324829904,
      "loss": 1.034,
      "step": 1808
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012480463878768213,
      "loss": 0.9072,
      "step": 1809
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012472979952629607,
      "loss": 0.8542,
      "step": 1810
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012465494550879694,
      "loss": 0.761,
      "step": 1811
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012458007677984957,
      "loss": 1.0001,
      "step": 1812
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001245051933841278,
      "loss": 0.8626,
      "step": 1813
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012443029536631393,
      "loss": 0.9196,
      "step": 1814
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001243553827710992,
      "loss": 0.821,
      "step": 1815
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001242804556431835,
      "loss": 1.0079,
      "step": 1816
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012420551402727531,
      "loss": 1.143,
      "step": 1817
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001241305579680919,
      "loss": 0.8365,
      "step": 1818
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012405558751035894,
      "loss": 0.8078,
      "step": 1819
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012398060269881093,
      "loss": 0.8283,
      "step": 1820
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001239056035781908,
      "loss": 0.9431,
      "step": 1821
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012383059019325,
      "loss": 1.0756,
      "step": 1822
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001237555625887486,
      "loss": 1.0663,
      "step": 1823
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012368052080945506,
      "loss": 0.8307,
      "step": 1824
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001236054649001463,
      "loss": 0.8351,
      "step": 1825
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012353039490560776,
      "loss": 0.9506,
      "step": 1826
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00012345531087063318,
      "loss": 0.7982,
      "step": 1827
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012338021284002477,
      "loss": 1.1871,
      "step": 1828
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.000123305100858593,
      "loss": 0.9963,
      "step": 1829
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012322997497115671,
      "loss": 0.9921,
      "step": 1830
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012315483522254308,
      "loss": 0.9298,
      "step": 1831
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012307968165758748,
      "loss": 1.0246,
      "step": 1832
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012300451432113352,
      "loss": 0.8436,
      "step": 1833
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001229293332580332,
      "loss": 0.8584,
      "step": 1834
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012285413851314644,
      "loss": 0.8835,
      "step": 1835
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012277893013134153,
      "loss": 0.8042,
      "step": 1836
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012270370815749482,
      "loss": 0.9384,
      "step": 1837
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001226284726364908,
      "loss": 0.8582,
      "step": 1838
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012255322361322198,
      "loss": 0.8888,
      "step": 1839
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00012247796113258903,
      "loss": 0.9913,
      "step": 1840
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001224026852395005,
      "loss": 0.7077,
      "step": 1841
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001223273959788731,
      "loss": 1.083,
      "step": 1842
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.9464,
      "step": 1843
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001221767775347081,
      "loss": 1.0163,
      "step": 1844
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012210144844104355,
      "loss": 0.9601,
      "step": 1845
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012202610615958618,
      "loss": 0.9661,
      "step": 1846
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012195075073529227,
      "loss": 1.1336,
      "step": 1847
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012187538221312592,
      "loss": 1.1764,
      "step": 1848
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012180000063805899,
      "loss": 0.9477,
      "step": 1849
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012172460605507126,
      "loss": 1.1893,
      "step": 1850
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001216491985091501,
      "loss": 0.9535,
      "step": 1851
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012157377804529082,
      "loss": 1.0089,
      "step": 1852
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012149834470849625,
      "loss": 0.8841,
      "step": 1853
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012142289854377703,
      "loss": 0.9831,
      "step": 1854
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012134743959615135,
      "loss": 0.928,
      "step": 1855
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001212719679106451,
      "loss": 0.9775,
      "step": 1856
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012119648353229179,
      "loss": 0.8345,
      "step": 1857
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012112098650613242,
      "loss": 0.9141,
      "step": 1858
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012104547687721556,
      "loss": 0.9759,
      "step": 1859
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012096995469059742,
      "loss": 0.9587,
      "step": 1860
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012089441999134152,
      "loss": 1.0034,
      "step": 1861
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012081887282451895,
      "loss": 0.9283,
      "step": 1862
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012074331323520824,
      "loss": 0.9654,
      "step": 1863
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012066774126849529,
      "loss": 0.9523,
      "step": 1864
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012059215696947346,
      "loss": 1.0128,
      "step": 1865
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012051656038324334,
      "loss": 0.8873,
      "step": 1866
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012044095155491295,
      "loss": 0.887,
      "step": 1867
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012036533052959765,
      "loss": 0.7831,
      "step": 1868
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00012028969735241998,
      "loss": 0.9209,
      "step": 1869
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00012021405206850973,
      "loss": 0.8649,
      "step": 1870
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00012013839472300406,
      "loss": 0.9424,
      "step": 1871
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001200627253610471,
      "loss": 0.8749,
      "step": 1872
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001199870440277904,
      "loss": 0.8986,
      "step": 1873
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011991135076839241,
      "loss": 0.8543,
      "step": 1874
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011983564562801888,
      "loss": 0.8557,
      "step": 1875
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001197599286518426,
      "loss": 0.8338,
      "step": 1876
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011968419988504337,
      "loss": 0.9756,
      "step": 1877
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011960845937280807,
      "loss": 1.1034,
      "step": 1878
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011953270716033058,
      "loss": 0.9096,
      "step": 1879
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011945694329281174,
      "loss": 0.7826,
      "step": 1880
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001193811678154594,
      "loss": 1.0009,
      "step": 1881
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00011930538077348827,
      "loss": 0.9488,
      "step": 1882
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011922958221211999,
      "loss": 0.8143,
      "step": 1883
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011915377217658315,
      "loss": 0.8813,
      "step": 1884
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011907795071211298,
      "loss": 0.7968,
      "step": 1885
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011900211786395179,
      "loss": 0.9775,
      "step": 1886
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001189262736773485,
      "loss": 0.7901,
      "step": 1887
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011885041819755885,
      "loss": 0.9998,
      "step": 1888
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011877455146984529,
      "loss": 0.8236,
      "step": 1889
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011869867353947707,
      "loss": 0.8284,
      "step": 1890
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011862278445173004,
      "loss": 0.9479,
      "step": 1891
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011854688425188673,
      "loss": 1.1683,
      "step": 1892
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011847097298523631,
      "loss": 0.8409,
      "step": 1893
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011839505069707454,
      "loss": 1.0242,
      "step": 1894
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00011831911743270381,
      "loss": 0.8885,
      "step": 1895
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001182431732374329,
      "loss": 0.8897,
      "step": 1896
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011816721815657734,
      "loss": 0.7726,
      "step": 1897
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011809125223545896,
      "loss": 0.9116,
      "step": 1898
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011801527551940619,
      "loss": 1.1006,
      "step": 1899
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011793928805375385,
      "loss": 0.823,
      "step": 1900
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011786328988384312,
      "loss": 0.7865,
      "step": 1901
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001177872810550217,
      "loss": 0.8989,
      "step": 1902
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011771126161264352,
      "loss": 0.9376,
      "step": 1903
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011763523160206886,
      "loss": 0.9894,
      "step": 1904
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011755919106866445,
      "loss": 0.9747,
      "step": 1905
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001174831400578031,
      "loss": 0.9447,
      "step": 1906
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011740707861486398,
      "loss": 1.0618,
      "step": 1907
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011733100678523248,
      "loss": 0.916,
      "step": 1908
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011725492461430016,
      "loss": 0.9919,
      "step": 1909
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001171788321474648,
      "loss": 1.0353,
      "step": 1910
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011710272943013023,
      "loss": 0.8586,
      "step": 1911
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001170266165077065,
      "loss": 0.9455,
      "step": 1912
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011695049342560968,
      "loss": 0.9073,
      "step": 1913
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011687436022926193,
      "loss": 1.0091,
      "step": 1914
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011679821696409146,
      "loss": 1.0059,
      "step": 1915
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011672206367553244,
      "loss": 0.9102,
      "step": 1916
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011664590040902506,
      "loss": 1.1164,
      "step": 1917
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011656972721001547,
      "loss": 0.7815,
      "step": 1918
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001164935441239557,
      "loss": 0.8469,
      "step": 1919
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011641735119630372,
      "loss": 0.8322,
      "step": 1920
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001163411484725234,
      "loss": 1.0683,
      "step": 1921
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011626493599808435,
      "loss": 0.8138,
      "step": 1922
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011618871381846215,
      "loss": 0.7951,
      "step": 1923
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011611248197913803,
      "loss": 0.809,
      "step": 1924
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.000116036240525599,
      "loss": 0.9174,
      "step": 1925
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011595998950333793,
      "loss": 0.9021,
      "step": 1926
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011588372895785328,
      "loss": 0.8785,
      "step": 1927
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011580745893464923,
      "loss": 0.935,
      "step": 1928
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011573117947923564,
      "loss": 0.886,
      "step": 1929
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011565489063712793,
      "loss": 0.8605,
      "step": 1930
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001155785924538472,
      "loss": 0.9049,
      "step": 1931
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011550228497492007,
      "loss": 0.9901,
      "step": 1932
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011542596824587868,
      "loss": 0.8655,
      "step": 1933
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011534964231226082,
      "loss": 0.9897,
      "step": 1934
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011527330721960962,
      "loss": 1.1211,
      "step": 1935
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001151969630134738,
      "loss": 0.9282,
      "step": 1936
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011512060973940741,
      "loss": 0.8796,
      "step": 1937
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011504424744296995,
      "loss": 0.8554,
      "step": 1938
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001149678761697264,
      "loss": 0.9196,
      "step": 1939
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011489149596524691,
      "loss": 0.8737,
      "step": 1940
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001148151068751071,
      "loss": 0.8794,
      "step": 1941
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011473870894488787,
      "loss": 0.8814,
      "step": 1942
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011466230222017531,
      "loss": 0.8602,
      "step": 1943
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011458588674656092,
      "loss": 1.0537,
      "step": 1944
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011450946256964125,
      "loss": 0.8741,
      "step": 1945
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011443302973501813,
      "loss": 0.9208,
      "step": 1946
    },
    {
      "epoch": 1.38,
      "eval_loss": 0.7829409837722778,
      "eval_runtime": 941.5318,
      "eval_samples_per_second": 0.779,
      "eval_steps_per_second": 0.39,
      "step": 1946
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011435658828829858,
      "loss": 0.9658,
      "step": 1947
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011428013827509467,
      "loss": 0.8388,
      "step": 1948
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011420367974102366,
      "loss": 0.9532,
      "step": 1949
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011412721273170787,
      "loss": 1.0344,
      "step": 1950
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011405073729277466,
      "loss": 0.8174,
      "step": 1951
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011397425346985649,
      "loss": 0.9393,
      "step": 1952
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011389776130859068,
      "loss": 1.0084,
      "step": 1953
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011382126085461968,
      "loss": 0.8451,
      "step": 1954
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001137447521535908,
      "loss": 0.9606,
      "step": 1955
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011366823525115627,
      "loss": 1.0641,
      "step": 1956
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011359171019297328,
      "loss": 0.7826,
      "step": 1957
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011351517702470383,
      "loss": 1.1684,
      "step": 1958
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001134386357920147,
      "loss": 1.0175,
      "step": 1959
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011336208654057767,
      "loss": 1.0285,
      "step": 1960
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011328552931606911,
      "loss": 1.0729,
      "step": 1961
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011320896416417026,
      "loss": 1.0842,
      "step": 1962
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011313239113056702,
      "loss": 0.9343,
      "step": 1963
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011305581026095007,
      "loss": 1.1409,
      "step": 1964
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011297922160101468,
      "loss": 0.8648,
      "step": 1965
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011290262519646088,
      "loss": 0.85,
      "step": 1966
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001128260210929932,
      "loss": 0.9589,
      "step": 1967
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011274940933632083,
      "loss": 1.0368,
      "step": 1968
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011267278997215756,
      "loss": 0.942,
      "step": 1969
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011259616304622157,
      "loss": 0.9129,
      "step": 1970
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011251952860423575,
      "loss": 0.8693,
      "step": 1971
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011244288669192733,
      "loss": 0.8246,
      "step": 1972
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011236623735502809,
      "loss": 1.018,
      "step": 1973
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011228958063927419,
      "loss": 1.0634,
      "step": 1974
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011221291659040616,
      "loss": 1.0015,
      "step": 1975
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.000112136245254169,
      "loss": 1.0095,
      "step": 1976
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011205956667631195,
      "loss": 0.8952,
      "step": 1977
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011198288090258864,
      "loss": 0.9879,
      "step": 1978
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011190618797875705,
      "loss": 0.9616,
      "step": 1979
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00011182948795057928,
      "loss": 1.0314,
      "step": 1980
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011175278086382177,
      "loss": 0.968,
      "step": 1981
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011167606676425517,
      "loss": 1.0022,
      "step": 1982
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011159934569765425,
      "loss": 1.1121,
      "step": 1983
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011152261770979799,
      "loss": 0.9744,
      "step": 1984
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001114458828464695,
      "loss": 1.0767,
      "step": 1985
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011136914115345603,
      "loss": 0.8906,
      "step": 1986
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011129239267654877,
      "loss": 0.8315,
      "step": 1987
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011121563746154306,
      "loss": 1.0203,
      "step": 1988
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011113887555423832,
      "loss": 0.9513,
      "step": 1989
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001110621070004378,
      "loss": 0.8586,
      "step": 1990
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011098533184594885,
      "loss": 0.9369,
      "step": 1991
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011090855013658272,
      "loss": 0.7558,
      "step": 1992
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011083176191815451,
      "loss": 0.7268,
      "step": 1993
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011075496723648333,
      "loss": 1.0383,
      "step": 1994
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011067816613739204,
      "loss": 0.8143,
      "step": 1995
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011060135866670736,
      "loss": 0.8654,
      "step": 1996
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011052454487025983,
      "loss": 0.7559,
      "step": 1997
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011044772479388375,
      "loss": 0.8528,
      "step": 1998
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011037089848341713,
      "loss": 0.8792,
      "step": 1999
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001102940659847018,
      "loss": 0.7646,
      "step": 2000
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011021722734358317,
      "loss": 0.8298,
      "step": 2001
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001101403826059104,
      "loss": 1.0609,
      "step": 2002
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011006353181753624,
      "loss": 1.0432,
      "step": 2003
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010998667502431706,
      "loss": 0.9711,
      "step": 2004
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001099098122721128,
      "loss": 0.9644,
      "step": 2005
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.000109832943606787,
      "loss": 0.9081,
      "step": 2006
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001097560690742067,
      "loss": 0.8412,
      "step": 2007
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00010967918872024241,
      "loss": 1.0141,
      "step": 2008
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010960230259076818,
      "loss": 0.8024,
      "step": 2009
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010952541073166147,
      "loss": 0.8395,
      "step": 2010
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010944851318880314,
      "loss": 0.8906,
      "step": 2011
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010937161000807745,
      "loss": 1.0102,
      "step": 2012
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010929470123537208,
      "loss": 1.0586,
      "step": 2013
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010921778691657798,
      "loss": 0.9924,
      "step": 2014
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010914086709758944,
      "loss": 0.735,
      "step": 2015
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000109063941824304,
      "loss": 0.8632,
      "step": 2016
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010898701114262246,
      "loss": 0.9363,
      "step": 2017
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010891007509844894,
      "loss": 0.8756,
      "step": 2018
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010883313373769062,
      "loss": 0.7833,
      "step": 2019
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010875618710625796,
      "loss": 0.8129,
      "step": 2020
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010867923525006451,
      "loss": 1.001,
      "step": 2021
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001086022782150269,
      "loss": 1.0812,
      "step": 2022
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010852531604706495,
      "loss": 0.7712,
      "step": 2023
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010844834879210153,
      "loss": 0.8816,
      "step": 2024
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010837137649606242,
      "loss": 0.8464,
      "step": 2025
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010829439920487656,
      "loss": 0.8593,
      "step": 2026
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010821741696447578,
      "loss": 0.8665,
      "step": 2027
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010814042982079491,
      "loss": 0.8466,
      "step": 2028
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010806343781977166,
      "loss": 1.3028,
      "step": 2029
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010798644100734667,
      "loss": 0.9123,
      "step": 2030
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010790943942946348,
      "loss": 0.8533,
      "step": 2031
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010783243313206839,
      "loss": 0.8334,
      "step": 2032
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010775542216111058,
      "loss": 0.9861,
      "step": 2033
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00010767840656254202,
      "loss": 0.9188,
      "step": 2034
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001076013863823174,
      "loss": 0.881,
      "step": 2035
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010752436166639422,
      "loss": 0.9576,
      "step": 2036
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010744733246073257,
      "loss": 0.9381,
      "step": 2037
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010737029881129528,
      "loss": 0.7655,
      "step": 2038
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001072932607640479,
      "loss": 0.982,
      "step": 2039
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010721621836495852,
      "loss": 0.888,
      "step": 2040
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001071391716599978,
      "loss": 0.8095,
      "step": 2041
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010706212069513908,
      "loss": 1.0661,
      "step": 2042
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010698506551635812,
      "loss": 0.9835,
      "step": 2043
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001069080061696333,
      "loss": 1.0733,
      "step": 2044
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010683094270094543,
      "loss": 0.7921,
      "step": 2045
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010675387515627773,
      "loss": 0.9542,
      "step": 2046
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010667680358161598,
      "loss": 0.7374,
      "step": 2047
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00010659972802294827,
      "loss": 1.0008,
      "step": 2048
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001065226485262651,
      "loss": 0.9192,
      "step": 2049
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001064455651375593,
      "loss": 0.9614,
      "step": 2050
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010636847790282602,
      "loss": 0.8875,
      "step": 2051
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010629138686806275,
      "loss": 1.0381,
      "step": 2052
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010621429207926923,
      "loss": 1.1204,
      "step": 2053
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010613719358244738,
      "loss": 0.8777,
      "step": 2054
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010606009142360142,
      "loss": 0.8927,
      "step": 2055
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010598298564873772,
      "loss": 0.9973,
      "step": 2056
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010590587630386473,
      "loss": 0.7201,
      "step": 2057
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010582876343499319,
      "loss": 0.9251,
      "step": 2058
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010575164708813578,
      "loss": 1.0621,
      "step": 2059
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010567452730930743,
      "loss": 0.9785,
      "step": 2060
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010559740414452492,
      "loss": 0.7465,
      "step": 2061
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010552027763980716,
      "loss": 0.8428,
      "step": 2062
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001054431478411751,
      "loss": 0.9805,
      "step": 2063
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010536601479465155,
      "loss": 0.9637,
      "step": 2064
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010528887854626135,
      "loss": 0.7869,
      "step": 2065
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010521173914203117,
      "loss": 0.909,
      "step": 2066
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010513459662798954,
      "loss": 0.889,
      "step": 2067
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010505745105016705,
      "loss": 0.9243,
      "step": 2068
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010498030245459587,
      "loss": 0.8292,
      "step": 2069
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010490315088731006,
      "loss": 1.0054,
      "step": 2070
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010482599639434554,
      "loss": 1.0054,
      "step": 2071
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010474883902173984,
      "loss": 1.0903,
      "step": 2072
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010467167881553231,
      "loss": 0.9519,
      "step": 2073
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010459451582176392,
      "loss": 1.0357,
      "step": 2074
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010451735008647733,
      "loss": 1.1174,
      "step": 2075
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010444018165571691,
      "loss": 0.7809,
      "step": 2076
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010436301057552848,
      "loss": 1.1563,
      "step": 2077
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010428583689195959,
      "loss": 0.8229,
      "step": 2078
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010420866065105925,
      "loss": 1.0371,
      "step": 2079
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010413148189887803,
      "loss": 0.7956,
      "step": 2080
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010405430068146802,
      "loss": 0.8338,
      "step": 2081
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010397711704488274,
      "loss": 0.7068,
      "step": 2082
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010389993103517714,
      "loss": 0.9014,
      "step": 2083
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010382274269840771,
      "loss": 0.9074,
      "step": 2084
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010374555208063215,
      "loss": 0.8881,
      "step": 2085
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010366835922790968,
      "loss": 0.9805,
      "step": 2086
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010359116418630071,
      "loss": 0.9473,
      "step": 2087
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010351396700186705,
      "loss": 0.7638,
      "step": 2088
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010343676772067179,
      "loss": 0.8532,
      "step": 2089
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010335956638877922,
      "loss": 0.9845,
      "step": 2090
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00010328236305225488,
      "loss": 1.0488,
      "step": 2091
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010320515775716555,
      "loss": 0.9217,
      "step": 2092
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010312795054957906,
      "loss": 0.9721,
      "step": 2093
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010305074147556453,
      "loss": 0.9441,
      "step": 2094
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010297353058119208,
      "loss": 0.7814,
      "step": 2095
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010289631791253295,
      "loss": 0.9872,
      "step": 2096
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010281910351565947,
      "loss": 1.059,
      "step": 2097
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010274188743664499,
      "loss": 0.7441,
      "step": 2098
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010266466972156379,
      "loss": 0.7952,
      "step": 2099
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010258745041649125,
      "loss": 1.0935,
      "step": 2100
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001025102295675036,
      "loss": 0.8909,
      "step": 2101
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010243300722067806,
      "loss": 0.8964,
      "step": 2102
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010235578342209267,
      "loss": 0.9922,
      "step": 2103
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00010227855821782637,
      "loss": 0.7603,
      "step": 2104
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.000102201331653959,
      "loss": 0.9693,
      "step": 2105
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010212410377657109,
      "loss": 0.8613,
      "step": 2106
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010204687463174407,
      "loss": 0.8455,
      "step": 2107
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010196964426556006,
      "loss": 0.8236,
      "step": 2108
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001018924127241019,
      "loss": 0.9275,
      "step": 2109
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010181518005345323,
      "loss": 0.7275,
      "step": 2110
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010173794629969819,
      "loss": 1.0211,
      "step": 2111
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010166071150892174,
      "loss": 0.9595,
      "step": 2112
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010158347572720937,
      "loss": 0.9284,
      "step": 2113
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010150623900064715,
      "loss": 1.2177,
      "step": 2114
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010142900137532178,
      "loss": 0.8631,
      "step": 2115
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010135176289732044,
      "loss": 0.8387,
      "step": 2116
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010127452361273082,
      "loss": 0.8408,
      "step": 2117
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010119728356764112,
      "loss": 0.8763,
      "step": 2118
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010112004280813998,
      "loss": 1.1133,
      "step": 2119
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010104280138031645,
      "loss": 1.1478,
      "step": 2120
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010096555933026004,
      "loss": 0.9982,
      "step": 2121
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010088831670406053,
      "loss": 0.7188,
      "step": 2122
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010081107354780816,
      "loss": 0.9576,
      "step": 2123
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001007338299075934,
      "loss": 0.7964,
      "step": 2124
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010065658582950698,
      "loss": 0.8348,
      "step": 2125
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010057934135964005,
      "loss": 0.9544,
      "step": 2126
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001005020965440838,
      "loss": 0.9541,
      "step": 2127
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010042485142892977,
      "loss": 0.9252,
      "step": 2128
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010034760606026963,
      "loss": 0.919,
      "step": 2129
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010027036048419513,
      "loss": 0.9362,
      "step": 2130
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010019311474679831,
      "loss": 0.9494,
      "step": 2131
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010011586889417114,
      "loss": 1.029,
      "step": 2132
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00010003862297240574,
      "loss": 0.8377,
      "step": 2133
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.996137702759424e-05,
      "loss": 1.1488,
      "step": 2134
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.988413110582887e-05,
      "loss": 0.8459,
      "step": 2135
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.980688525320169e-05,
      "loss": 0.9703,
      "step": 2136
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.972963951580486e-05,
      "loss": 0.8566,
      "step": 2137
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.965239393973038e-05,
      "loss": 0.9168,
      "step": 2138
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.957514857107024e-05,
      "loss": 0.9568,
      "step": 2139
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.949790345591623e-05,
      "loss": 1.0617,
      "step": 2140
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.942065864035998e-05,
      "loss": 0.8084,
      "step": 2141
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.934341417049303e-05,
      "loss": 0.9902,
      "step": 2142
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.926617009240663e-05,
      "loss": 0.9724,
      "step": 2143
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.918892645219187e-05,
      "loss": 0.9504,
      "step": 2144
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.911168329593949e-05,
      "loss": 0.7441,
      "step": 2145
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.903444066973998e-05,
      "loss": 0.8709,
      "step": 2146
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.895719861968356e-05,
      "loss": 0.968,
      "step": 2147
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.887995719186003e-05,
      "loss": 0.871,
      "step": 2148
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.88027164323589e-05,
      "loss": 0.7294,
      "step": 2149
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.87254763872692e-05,
      "loss": 0.8619,
      "step": 2150
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.864823710267958e-05,
      "loss": 0.8096,
      "step": 2151
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.857099862467823e-05,
      "loss": 0.9399,
      "step": 2152
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.849376099935287e-05,
      "loss": 0.9877,
      "step": 2153
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.841652427279065e-05,
      "loss": 0.9783,
      "step": 2154
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.833928849107828e-05,
      "loss": 0.9859,
      "step": 2155
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.826205370030183e-05,
      "loss": 0.8845,
      "step": 2156
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.818481994654682e-05,
      "loss": 0.9805,
      "step": 2157
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.810758727589813e-05,
      "loss": 0.9804,
      "step": 2158
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.803035573443999e-05,
      "loss": 0.9244,
      "step": 2159
    },
    {
      "epoch": 1.53,
      "learning_rate": 9.795312536825598e-05,
      "loss": 0.8905,
      "step": 2160
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.787589622342895e-05,
      "loss": 0.9759,
      "step": 2161
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.779866834604106e-05,
      "loss": 1.3009,
      "step": 2162
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.772144178217368e-05,
      "loss": 1.0439,
      "step": 2163
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.764421657790736e-05,
      "loss": 0.9948,
      "step": 2164
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.756699277932195e-05,
      "loss": 0.8353,
      "step": 2165
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.748977043249639e-05,
      "loss": 0.8932,
      "step": 2166
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.741254958350874e-05,
      "loss": 0.9978,
      "step": 2167
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.733533027843621e-05,
      "loss": 0.9912,
      "step": 2168
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.725811256335504e-05,
      "loss": 0.8963,
      "step": 2169
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.718089648434053e-05,
      "loss": 0.9239,
      "step": 2170
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.710368208746707e-05,
      "loss": 0.7904,
      "step": 2171
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.702646941880794e-05,
      "loss": 0.7873,
      "step": 2172
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.69492585244355e-05,
      "loss": 0.9678,
      "step": 2173
    },
    {
      "epoch": 1.54,
      "learning_rate": 9.687204945042096e-05,
      "loss": 0.9175,
      "step": 2174
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.679484224283449e-05,
      "loss": 0.8717,
      "step": 2175
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.671763694774513e-05,
      "loss": 1.0093,
      "step": 2176
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.66404336112208e-05,
      "loss": 0.9167,
      "step": 2177
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.656323227932824e-05,
      "loss": 0.8626,
      "step": 2178
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.648603299813298e-05,
      "loss": 1.299,
      "step": 2179
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.640883581369931e-05,
      "loss": 1.0569,
      "step": 2180
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.633164077209036e-05,
      "loss": 1.0771,
      "step": 2181
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.625444791936787e-05,
      "loss": 1.0188,
      "step": 2182
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.61772573015923e-05,
      "loss": 0.9787,
      "step": 2183
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.610006896482287e-05,
      "loss": 0.885,
      "step": 2184
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.602288295511729e-05,
      "loss": 1.0202,
      "step": 2185
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.594569931853203e-05,
      "loss": 0.827,
      "step": 2186
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.586851810112202e-05,
      "loss": 1.053,
      "step": 2187
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.579133934894078e-05,
      "loss": 0.9285,
      "step": 2188
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.571416310804046e-05,
      "loss": 1.0102,
      "step": 2189
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.563698942447154e-05,
      "loss": 0.9543,
      "step": 2190
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.555981834428314e-05,
      "loss": 0.796,
      "step": 2191
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.548264991352269e-05,
      "loss": 0.8849,
      "step": 2192
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.540548417823609e-05,
      "loss": 0.9179,
      "step": 2193
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.53283211844677e-05,
      "loss": 0.9939,
      "step": 2194
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.525116097826017e-05,
      "loss": 0.917,
      "step": 2195
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.517400360565447e-05,
      "loss": 0.9202,
      "step": 2196
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.509684911268994e-05,
      "loss": 0.7719,
      "step": 2197
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.501969754540416e-05,
      "loss": 0.8238,
      "step": 2198
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.494254894983295e-05,
      "loss": 0.8653,
      "step": 2199
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.486540337201046e-05,
      "loss": 0.8114,
      "step": 2200
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.478826085796885e-05,
      "loss": 0.7102,
      "step": 2201
    },
    {
      "epoch": 1.56,
      "learning_rate": 9.471112145373868e-05,
      "loss": 0.8328,
      "step": 2202
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.463398520534847e-05,
      "loss": 0.8101,
      "step": 2203
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.45568521588249e-05,
      "loss": 0.9933,
      "step": 2204
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.447972236019286e-05,
      "loss": 1.0964,
      "step": 2205
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.44025958554751e-05,
      "loss": 1.0421,
      "step": 2206
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.432547269069261e-05,
      "loss": 0.8594,
      "step": 2207
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.424835291186424e-05,
      "loss": 1.0185,
      "step": 2208
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.417123656500683e-05,
      "loss": 0.9105,
      "step": 2209
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.40941236961353e-05,
      "loss": 0.9538,
      "step": 2210
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.401701435126232e-05,
      "loss": 1.0344,
      "step": 2211
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.393990857639859e-05,
      "loss": 0.8253,
      "step": 2212
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.386280641755264e-05,
      "loss": 0.8611,
      "step": 2213
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.37857079207308e-05,
      "loss": 0.8585,
      "step": 2214
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.370861313193726e-05,
      "loss": 0.9313,
      "step": 2215
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.363152209717402e-05,
      "loss": 0.9127,
      "step": 2216
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.355443486244074e-05,
      "loss": 0.9611,
      "step": 2217
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.347735147373495e-05,
      "loss": 0.8481,
      "step": 2218
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.340027197705175e-05,
      "loss": 0.9214,
      "step": 2219
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.332319641838407e-05,
      "loss": 1.0907,
      "step": 2220
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.324612484372231e-05,
      "loss": 1.197,
      "step": 2221
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.316905729905464e-05,
      "loss": 0.9385,
      "step": 2222
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.30919938303667e-05,
      "loss": 1.0377,
      "step": 2223
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.301493448364188e-05,
      "loss": 0.9718,
      "step": 2224
    },
    {
      "epoch": 1.58,
      "eval_loss": 0.7833093404769897,
      "eval_runtime": 935.9,
      "eval_samples_per_second": 0.783,
      "eval_steps_per_second": 0.392,
      "step": 2224
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.293787930486092e-05,
      "loss": 1.076,
      "step": 2225
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.28608283400022e-05,
      "loss": 0.9264,
      "step": 2226
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.27837816350415e-05,
      "loss": 1.0137,
      "step": 2227
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.27067392359521e-05,
      "loss": 0.915,
      "step": 2228
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.262970118870473e-05,
      "loss": 1.0115,
      "step": 2229
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.255266753926745e-05,
      "loss": 0.9413,
      "step": 2230
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.247563833360582e-05,
      "loss": 0.9171,
      "step": 2231
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.239861361768262e-05,
      "loss": 0.8776,
      "step": 2232
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.2321593437458e-05,
      "loss": 0.9417,
      "step": 2233
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.224457783888944e-05,
      "loss": 0.9169,
      "step": 2234
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.216756686793164e-05,
      "loss": 0.7682,
      "step": 2235
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.209056057053656e-05,
      "loss": 0.9634,
      "step": 2236
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.201355899265336e-05,
      "loss": 0.9559,
      "step": 2237
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.193656218022836e-05,
      "loss": 1.0237,
      "step": 2238
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.185957017920512e-05,
      "loss": 1.015,
      "step": 2239
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.178258303552423e-05,
      "loss": 0.9505,
      "step": 2240
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.170560079512345e-05,
      "loss": 0.8193,
      "step": 2241
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.16286235039376e-05,
      "loss": 0.8826,
      "step": 2242
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.155165120789851e-05,
      "loss": 0.8743,
      "step": 2243
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.147468395293506e-05,
      "loss": 0.7951,
      "step": 2244
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.139772178497313e-05,
      "loss": 1.0489,
      "step": 2245
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.132076474993554e-05,
      "loss": 1.054,
      "step": 2246
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.124381289374207e-05,
      "loss": 0.9066,
      "step": 2247
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.116686626230939e-05,
      "loss": 0.7951,
      "step": 2248
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.10899249015511e-05,
      "loss": 0.8988,
      "step": 2249
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.101298885737756e-05,
      "loss": 0.6953,
      "step": 2250
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.093605817569604e-05,
      "loss": 0.9994,
      "step": 2251
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.085913290241061e-05,
      "loss": 0.9066,
      "step": 2252
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.078221308342203e-05,
      "loss": 0.9795,
      "step": 2253
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.070529876462791e-05,
      "loss": 1.1659,
      "step": 2254
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.062838999192255e-05,
      "loss": 0.9542,
      "step": 2255
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.055148681119688e-05,
      "loss": 0.8518,
      "step": 2256
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.047458926833854e-05,
      "loss": 0.9601,
      "step": 2257
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.039769740923183e-05,
      "loss": 0.8127,
      "step": 2258
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.03208112797576e-05,
      "loss": 0.8873,
      "step": 2259
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.024393092579332e-05,
      "loss": 0.9106,
      "step": 2260
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.016705639321302e-05,
      "loss": 1.1458,
      "step": 2261
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.00901877278872e-05,
      "loss": 0.958,
      "step": 2262
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.001332497568298e-05,
      "loss": 0.8501,
      "step": 2263
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.993646818246377e-05,
      "loss": 0.9327,
      "step": 2264
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.985961739408961e-05,
      "loss": 1.0559,
      "step": 2265
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.978277265641686e-05,
      "loss": 0.9539,
      "step": 2266
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.970593401529822e-05,
      "loss": 1.0314,
      "step": 2267
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.962910151658289e-05,
      "loss": 1.1463,
      "step": 2268
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.955227520611628e-05,
      "loss": 1.0409,
      "step": 2269
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.947545512974019e-05,
      "loss": 0.8686,
      "step": 2270
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.939864133329268e-05,
      "loss": 0.9859,
      "step": 2271
    },
    {
      "epoch": 1.61,
      "learning_rate": 8.932183386260799e-05,
      "loss": 0.9662,
      "step": 2272
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.92450327635167e-05,
      "loss": 0.9303,
      "step": 2273
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.91682380818455e-05,
      "loss": 1.0017,
      "step": 2274
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.909144986341733e-05,
      "loss": 0.8805,
      "step": 2275
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.90146681540512e-05,
      "loss": 0.8396,
      "step": 2276
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.893789299956223e-05,
      "loss": 0.896,
      "step": 2277
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.886112444576174e-05,
      "loss": 0.929,
      "step": 2278
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.878436253845696e-05,
      "loss": 0.9994,
      "step": 2279
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.870760732345127e-05,
      "loss": 0.8982,
      "step": 2280
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.863085884654402e-05,
      "loss": 0.8262,
      "step": 2281
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.855411715353048e-05,
      "loss": 1.015,
      "step": 2282
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.847738229020199e-05,
      "loss": 0.8223,
      "step": 2283
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.840065430234576e-05,
      "loss": 1.079,
      "step": 2284
    },
    {
      "epoch": 1.62,
      "learning_rate": 8.832393323574485e-05,
      "loss": 1.049,
      "step": 2285
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.824721913617822e-05,
      "loss": 0.945,
      "step": 2286
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.817051204942073e-05,
      "loss": 0.906,
      "step": 2287
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.809381202124296e-05,
      "loss": 0.7217,
      "step": 2288
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.801711909741134e-05,
      "loss": 0.7714,
      "step": 2289
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.794043332368809e-05,
      "loss": 1.0251,
      "step": 2290
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.786375474583104e-05,
      "loss": 0.9894,
      "step": 2291
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.778708340959388e-05,
      "loss": 0.9905,
      "step": 2292
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.771041936072583e-05,
      "loss": 1.1083,
      "step": 2293
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.763376264497192e-05,
      "loss": 1.0273,
      "step": 2294
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.755711330807268e-05,
      "loss": 0.8777,
      "step": 2295
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.748047139576426e-05,
      "loss": 0.7726,
      "step": 2296
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.740383695377845e-05,
      "loss": 1.1531,
      "step": 2297
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.732721002784247e-05,
      "loss": 0.8501,
      "step": 2298
    },
    {
      "epoch": 1.63,
      "learning_rate": 8.725059066367917e-05,
      "loss": 0.8828,
      "step": 2299
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.717397890700682e-05,
      "loss": 0.7514,
      "step": 2300
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.709737480353914e-05,
      "loss": 0.8597,
      "step": 2301
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.702077839898533e-05,
      "loss": 0.7979,
      "step": 2302
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.694418973904995e-05,
      "loss": 0.7826,
      "step": 2303
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.686760886943301e-05,
      "loss": 0.943,
      "step": 2304
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.679103583582979e-05,
      "loss": 0.6943,
      "step": 2305
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.671447068393093e-05,
      "loss": 0.9296,
      "step": 2306
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.663791345942238e-05,
      "loss": 0.8278,
      "step": 2307
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.656136420798533e-05,
      "loss": 0.9123,
      "step": 2308
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.648482297529624e-05,
      "loss": 0.8396,
      "step": 2309
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.640828980702677e-05,
      "loss": 1.017,
      "step": 2310
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.633176474884374e-05,
      "loss": 0.9451,
      "step": 2311
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.62552478464092e-05,
      "loss": 0.7461,
      "step": 2312
    },
    {
      "epoch": 1.64,
      "learning_rate": 8.617873914538033e-05,
      "loss": 1.0036,
      "step": 2313
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.610223869140933e-05,
      "loss": 1.03,
      "step": 2314
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.602574653014352e-05,
      "loss": 0.8223,
      "step": 2315
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.594926270722533e-05,
      "loss": 0.8754,
      "step": 2316
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.587278726829212e-05,
      "loss": 1.0194,
      "step": 2317
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.579632025897635e-05,
      "loss": 0.7601,
      "step": 2318
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.571986172490536e-05,
      "loss": 0.8102,
      "step": 2319
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.564341171170144e-05,
      "loss": 1.2085,
      "step": 2320
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.556697026498188e-05,
      "loss": 0.9191,
      "step": 2321
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.549053743035876e-05,
      "loss": 0.9785,
      "step": 2322
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.54141132534391e-05,
      "loss": 0.993,
      "step": 2323
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.53376977798247e-05,
      "loss": 0.9381,
      "step": 2324
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.526129105511216e-05,
      "loss": 0.9377,
      "step": 2325
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.518489312489293e-05,
      "loss": 1.1425,
      "step": 2326
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.51085040347531e-05,
      "loss": 0.9574,
      "step": 2327
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.503212383027364e-05,
      "loss": 0.8505,
      "step": 2328
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.495575255703005e-05,
      "loss": 0.7462,
      "step": 2329
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.487939026059261e-05,
      "loss": 0.9515,
      "step": 2330
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.480303698652624e-05,
      "loss": 0.886,
      "step": 2331
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.472669278039039e-05,
      "loss": 1.0413,
      "step": 2332
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.465035768773921e-05,
      "loss": 1.0051,
      "step": 2333
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.457403175412135e-05,
      "loss": 0.9116,
      "step": 2334
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.449771502508e-05,
      "loss": 0.7617,
      "step": 2335
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.442140754615286e-05,
      "loss": 0.8482,
      "step": 2336
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.43451093628721e-05,
      "loss": 0.732,
      "step": 2337
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.42688205207644e-05,
      "loss": 0.828,
      "step": 2338
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.41925410653508e-05,
      "loss": 0.9536,
      "step": 2339
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.411627104214674e-05,
      "loss": 0.8793,
      "step": 2340
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.404001049666211e-05,
      "loss": 0.8257,
      "step": 2341
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.396375947440101e-05,
      "loss": 0.7915,
      "step": 2342
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.388751802086201e-05,
      "loss": 0.998,
      "step": 2343
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.381128618153786e-05,
      "loss": 0.9892,
      "step": 2344
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.373506400191565e-05,
      "loss": 0.8382,
      "step": 2345
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.36588515274766e-05,
      "loss": 1.0807,
      "step": 2346
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.358264880369629e-05,
      "loss": 0.7951,
      "step": 2347
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.350645587604432e-05,
      "loss": 0.7283,
      "step": 2348
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.343027278998455e-05,
      "loss": 0.9414,
      "step": 2349
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.335409959097497e-05,
      "loss": 0.9152,
      "step": 2350
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.327793632446758e-05,
      "loss": 0.7883,
      "step": 2351
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.320178303590857e-05,
      "loss": 0.9785,
      "step": 2352
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.31256397707381e-05,
      "loss": 0.8964,
      "step": 2353
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.304950657439033e-05,
      "loss": 0.9104,
      "step": 2354
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.297338349229354e-05,
      "loss": 0.8687,
      "step": 2355
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.289727056986978e-05,
      "loss": 1.0292,
      "step": 2356
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.282116785253523e-05,
      "loss": 1.0249,
      "step": 2357
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.274507538569986e-05,
      "loss": 0.8478,
      "step": 2358
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.266899321476753e-05,
      "loss": 0.9056,
      "step": 2359
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.259292138513605e-05,
      "loss": 0.9355,
      "step": 2360
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.251685994219693e-05,
      "loss": 0.8311,
      "step": 2361
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.244080893133559e-05,
      "loss": 0.856,
      "step": 2362
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.236476839793115e-05,
      "loss": 0.8161,
      "step": 2363
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.228873838735653e-05,
      "loss": 0.9164,
      "step": 2364
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.221271894497834e-05,
      "loss": 0.8616,
      "step": 2365
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.213671011615689e-05,
      "loss": 0.7668,
      "step": 2366
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.206071194624619e-05,
      "loss": 0.9276,
      "step": 2367
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.198472448059385e-05,
      "loss": 1.0464,
      "step": 2368
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.190874776454107e-05,
      "loss": 0.8184,
      "step": 2369
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.183278184342271e-05,
      "loss": 0.8745,
      "step": 2370
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.17568267625671e-05,
      "loss": 1.0007,
      "step": 2371
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.168088256729623e-05,
      "loss": 0.9744,
      "step": 2372
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.160494930292544e-05,
      "loss": 0.776,
      "step": 2373
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.152902701476369e-05,
      "loss": 0.7115,
      "step": 2374
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.145311574811325e-05,
      "loss": 0.8726,
      "step": 2375
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.137721554826996e-05,
      "loss": 0.7806,
      "step": 2376
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.130132646052293e-05,
      "loss": 0.7819,
      "step": 2377
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.12254485301547e-05,
      "loss": 0.9655,
      "step": 2378
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.114958180244119e-05,
      "loss": 0.9095,
      "step": 2379
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.10737263226515e-05,
      "loss": 0.8407,
      "step": 2380
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.099788213604822e-05,
      "loss": 0.7555,
      "step": 2381
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.092204928788703e-05,
      "loss": 0.9926,
      "step": 2382
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.084622782341689e-05,
      "loss": 0.94,
      "step": 2383
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.077041778788002e-05,
      "loss": 0.9205,
      "step": 2384
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.069461922651175e-05,
      "loss": 0.9026,
      "step": 2385
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.061883218454063e-05,
      "loss": 1.1425,
      "step": 2386
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.054305670718829e-05,
      "loss": 0.93,
      "step": 2387
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.046729283966944e-05,
      "loss": 0.9696,
      "step": 2388
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.039154062719195e-05,
      "loss": 0.9275,
      "step": 2389
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.031580011495664e-05,
      "loss": 0.9437,
      "step": 2390
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.024007134815741e-05,
      "loss": 1.079,
      "step": 2391
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.016435437198113e-05,
      "loss": 0.8486,
      "step": 2392
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.00886492316076e-05,
      "loss": 0.8977,
      "step": 2393
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.001295597220966e-05,
      "loss": 0.7807,
      "step": 2394
    },
    {
      "epoch": 1.7,
      "learning_rate": 7.993727463895291e-05,
      "loss": 0.9272,
      "step": 2395
    },
    {
      "epoch": 1.7,
      "learning_rate": 7.9861605276996e-05,
      "loss": 0.9138,
      "step": 2396
    },
    {
      "epoch": 1.7,
      "learning_rate": 7.97859479314903e-05,
      "loss": 0.8003,
      "step": 2397
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.971030264758007e-05,
      "loss": 1.1201,
      "step": 2398
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.963466947040239e-05,
      "loss": 1.0385,
      "step": 2399
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.955904844508706e-05,
      "loss": 0.9037,
      "step": 2400
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.948343961675668e-05,
      "loss": 1.0338,
      "step": 2401
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.940784303052655e-05,
      "loss": 1.0711,
      "step": 2402
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.93322587315047e-05,
      "loss": 0.9767,
      "step": 2403
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.925668676479174e-05,
      "loss": 0.9293,
      "step": 2404
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.918112717548104e-05,
      "loss": 0.8342,
      "step": 2405
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.910558000865849e-05,
      "loss": 0.9475,
      "step": 2406
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.903004530940259e-05,
      "loss": 0.9524,
      "step": 2407
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.895452312278443e-05,
      "loss": 0.9246,
      "step": 2408
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.887901349386759e-05,
      "loss": 0.9549,
      "step": 2409
    },
    {
      "epoch": 1.71,
      "learning_rate": 7.880351646770824e-05,
      "loss": 0.6885,
      "step": 2410
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.872803208935492e-05,
      "loss": 0.8313,
      "step": 2411
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.865256040384867e-05,
      "loss": 0.8685,
      "step": 2412
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.857710145622301e-05,
      "loss": 1.0168,
      "step": 2413
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.850165529150376e-05,
      "loss": 0.757,
      "step": 2414
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.84262219547092e-05,
      "loss": 1.0379,
      "step": 2415
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.83508014908499e-05,
      "loss": 0.7579,
      "step": 2416
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.827539394492878e-05,
      "loss": 1.0029,
      "step": 2417
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.819999936194102e-05,
      "loss": 0.9039,
      "step": 2418
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.812461778687409e-05,
      "loss": 0.8193,
      "step": 2419
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.804924926470774e-05,
      "loss": 0.8238,
      "step": 2420
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.797389384041384e-05,
      "loss": 1.0802,
      "step": 2421
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.789855155895647e-05,
      "loss": 0.9647,
      "step": 2422
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.782322246529192e-05,
      "loss": 0.7785,
      "step": 2423
    },
    {
      "epoch": 1.72,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.8425,
      "step": 2424
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.767260402112692e-05,
      "loss": 0.9249,
      "step": 2425
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.759731476049955e-05,
      "loss": 0.9164,
      "step": 2426
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.752203886741103e-05,
      "loss": 0.7677,
      "step": 2427
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.744677638677806e-05,
      "loss": 1.0061,
      "step": 2428
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.737152736350923e-05,
      "loss": 0.9681,
      "step": 2429
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.72962918425052e-05,
      "loss": 0.8844,
      "step": 2430
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.722106986865846e-05,
      "loss": 0.9094,
      "step": 2431
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.714586148685357e-05,
      "loss": 0.8662,
      "step": 2432
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.707066674196682e-05,
      "loss": 0.8447,
      "step": 2433
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.699548567886646e-05,
      "loss": 0.8302,
      "step": 2434
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.692031834241255e-05,
      "loss": 1.0484,
      "step": 2435
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.684516477745692e-05,
      "loss": 0.8858,
      "step": 2436
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.67700250288433e-05,
      "loss": 0.8793,
      "step": 2437
    },
    {
      "epoch": 1.73,
      "learning_rate": 7.669489914140701e-05,
      "loss": 0.8758,
      "step": 2438
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.661978715997524e-05,
      "loss": 0.9642,
      "step": 2439
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.654468912936683e-05,
      "loss": 0.892,
      "step": 2440
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.646960509439226e-05,
      "loss": 0.8524,
      "step": 2441
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.639453509985372e-05,
      "loss": 0.9428,
      "step": 2442
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.631947919054498e-05,
      "loss": 0.8019,
      "step": 2443
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.624443741125144e-05,
      "loss": 0.6158,
      "step": 2444
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.616940980675004e-05,
      "loss": 0.9668,
      "step": 2445
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.609439642180924e-05,
      "loss": 0.8948,
      "step": 2446
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.60193973011891e-05,
      "loss": 1.0117,
      "step": 2447
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.594441248964107e-05,
      "loss": 0.9936,
      "step": 2448
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.586944203190815e-05,
      "loss": 0.9396,
      "step": 2449
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.579448597272471e-05,
      "loss": 1.0798,
      "step": 2450
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.571954435681652e-05,
      "loss": 0.9477,
      "step": 2451
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.564461722890081e-05,
      "loss": 0.8225,
      "step": 2452
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.55697046336861e-05,
      "loss": 0.8583,
      "step": 2453
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.549480661587227e-05,
      "loss": 1.091,
      "step": 2454
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.541992322015047e-05,
      "loss": 1.0287,
      "step": 2455
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.534505449120313e-05,
      "loss": 0.7684,
      "step": 2456
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.527020047370396e-05,
      "loss": 0.9528,
      "step": 2457
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.519536121231787e-05,
      "loss": 1.0081,
      "step": 2458
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.5120536751701e-05,
      "loss": 0.7083,
      "step": 2459
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.504572713650057e-05,
      "loss": 0.8219,
      "step": 2460
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.4970932411355e-05,
      "loss": 0.83,
      "step": 2461
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.489615262089386e-05,
      "loss": 0.7713,
      "step": 2462
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.48213878097378e-05,
      "loss": 0.8968,
      "step": 2463
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.474663802249846e-05,
      "loss": 0.7781,
      "step": 2464
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.467190330377853e-05,
      "loss": 1.1215,
      "step": 2465
    },
    {
      "epoch": 1.75,
      "learning_rate": 7.45971836981718e-05,
      "loss": 0.8159,
      "step": 2466
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.452247925026293e-05,
      "loss": 0.9373,
      "step": 2467
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.444779000462763e-05,
      "loss": 0.7791,
      "step": 2468
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.437311600583249e-05,
      "loss": 0.8335,
      "step": 2469
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.429845729843496e-05,
      "loss": 1.0827,
      "step": 2470
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.422381392698345e-05,
      "loss": 1.0292,
      "step": 2471
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.414918593601718e-05,
      "loss": 0.7648,
      "step": 2472
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.40745733700662e-05,
      "loss": 0.9552,
      "step": 2473
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.399997627365134e-05,
      "loss": 0.8132,
      "step": 2474
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.39253946912842e-05,
      "loss": 0.8548,
      "step": 2475
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.385082866746714e-05,
      "loss": 0.7461,
      "step": 2476
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.377627824669322e-05,
      "loss": 0.8848,
      "step": 2477
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.370174347344625e-05,
      "loss": 0.8315,
      "step": 2478
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.36272243922006e-05,
      "loss": 0.8691,
      "step": 2479
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.355272104742132e-05,
      "loss": 0.8441,
      "step": 2480
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.347823348356412e-05,
      "loss": 1.1182,
      "step": 2481
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.340376174507524e-05,
      "loss": 0.9379,
      "step": 2482
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.332930587639148e-05,
      "loss": 1.0104,
      "step": 2483
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.325486592194019e-05,
      "loss": 1.0399,
      "step": 2484
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.318044192613917e-05,
      "loss": 0.9433,
      "step": 2485
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.310603393339684e-05,
      "loss": 0.9382,
      "step": 2486
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.303164198811185e-05,
      "loss": 0.9314,
      "step": 2487
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.29572661346735e-05,
      "loss": 1.2215,
      "step": 2488
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.288290641746136e-05,
      "loss": 0.8407,
      "step": 2489
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.280856288084533e-05,
      "loss": 0.8234,
      "step": 2490
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.273423556918579e-05,
      "loss": 0.9642,
      "step": 2491
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.265992452683338e-05,
      "loss": 0.9272,
      "step": 2492
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.258562979812902e-05,
      "loss": 0.8561,
      "step": 2493
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.251135142740384e-05,
      "loss": 0.6893,
      "step": 2494
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.243708945897934e-05,
      "loss": 0.962,
      "step": 2495
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.23628439371671e-05,
      "loss": 0.8812,
      "step": 2496
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.228861490626899e-05,
      "loss": 0.9736,
      "step": 2497
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.2214402410577e-05,
      "loss": 0.8158,
      "step": 2498
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.214020649437319e-05,
      "loss": 0.9715,
      "step": 2499
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.206602720192987e-05,
      "loss": 0.9337,
      "step": 2500
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.19918645775093e-05,
      "loss": 0.8787,
      "step": 2501
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.191771866536388e-05,
      "loss": 0.8414,
      "step": 2502
    },
    {
      "epoch": 1.78,
      "eval_loss": 0.7788746953010559,
      "eval_runtime": 935.0864,
      "eval_samples_per_second": 0.784,
      "eval_steps_per_second": 0.392,
      "step": 2502
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.184358950973596e-05,
      "loss": 0.8357,
      "step": 2503
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.176947715485794e-05,
      "loss": 0.7207,
      "step": 2504
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.169538164495222e-05,
      "loss": 0.9593,
      "step": 2505
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.162130302423107e-05,
      "loss": 0.8291,
      "step": 2506
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.154724133689677e-05,
      "loss": 1.0755,
      "step": 2507
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.147319662714145e-05,
      "loss": 1.0628,
      "step": 2508
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.139916893914707e-05,
      "loss": 0.8854,
      "step": 2509
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.132515831708553e-05,
      "loss": 1.0965,
      "step": 2510
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.125116480511844e-05,
      "loss": 0.9877,
      "step": 2511
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.117718844739733e-05,
      "loss": 0.872,
      "step": 2512
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.110322928806338e-05,
      "loss": 0.9684,
      "step": 2513
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.102928737124751e-05,
      "loss": 0.9567,
      "step": 2514
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.095536274107046e-05,
      "loss": 0.7979,
      "step": 2515
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.08814554416425e-05,
      "loss": 0.8702,
      "step": 2516
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.080756551706373e-05,
      "loss": 0.7798,
      "step": 2517
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.073369301142376e-05,
      "loss": 0.8995,
      "step": 2518
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.065983796880181e-05,
      "loss": 0.9942,
      "step": 2519
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.058600043326671e-05,
      "loss": 0.851,
      "step": 2520
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.051218044887692e-05,
      "loss": 0.8664,
      "step": 2521
    },
    {
      "epoch": 1.79,
      "learning_rate": 7.043837805968027e-05,
      "loss": 0.9604,
      "step": 2522
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.036459330971426e-05,
      "loss": 0.8053,
      "step": 2523
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.029082624300569e-05,
      "loss": 0.8393,
      "step": 2524
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.021707690357094e-05,
      "loss": 1.1611,
      "step": 2525
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.014334533541575e-05,
      "loss": 1.0749,
      "step": 2526
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.006963158253532e-05,
      "loss": 0.9319,
      "step": 2527
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.99959356889141e-05,
      "loss": 0.8392,
      "step": 2528
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.992225769852601e-05,
      "loss": 0.7947,
      "step": 2529
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.984859765533421e-05,
      "loss": 0.6854,
      "step": 2530
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.977495560329121e-05,
      "loss": 0.982,
      "step": 2531
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.970133158633874e-05,
      "loss": 0.9473,
      "step": 2532
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.962772564840774e-05,
      "loss": 0.9611,
      "step": 2533
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.955413783341846e-05,
      "loss": 0.8996,
      "step": 2534
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.948056818528022e-05,
      "loss": 1.0347,
      "step": 2535
    },
    {
      "epoch": 1.8,
      "learning_rate": 6.940701674789162e-05,
      "loss": 0.9746,
      "step": 2536
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.933348356514029e-05,
      "loss": 0.941,
      "step": 2537
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.925996868090301e-05,
      "loss": 0.7881,
      "step": 2538
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.918647213904566e-05,
      "loss": 1.0062,
      "step": 2539
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.911299398342313e-05,
      "loss": 0.9559,
      "step": 2540
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.90395342578794e-05,
      "loss": 1.056,
      "step": 2541
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.896609300624741e-05,
      "loss": 0.8469,
      "step": 2542
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.889267027234905e-05,
      "loss": 1.0119,
      "step": 2543
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.881926609999522e-05,
      "loss": 0.9077,
      "step": 2544
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.874588053298572e-05,
      "loss": 1.0552,
      "step": 2545
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.867251361510927e-05,
      "loss": 1.2455,
      "step": 2546
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.859916539014342e-05,
      "loss": 0.6672,
      "step": 2547
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.852583590185456e-05,
      "loss": 1.1005,
      "step": 2548
    },
    {
      "epoch": 1.81,
      "learning_rate": 6.845252519399797e-05,
      "loss": 1.0121,
      "step": 2549
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.83792333103176e-05,
      "loss": 0.9378,
      "step": 2550
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.830596029454635e-05,
      "loss": 0.9711,
      "step": 2551
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.823270619040573e-05,
      "loss": 0.813,
      "step": 2552
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.8159471041606e-05,
      "loss": 1.0365,
      "step": 2553
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.808625489184605e-05,
      "loss": 0.9176,
      "step": 2554
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.801305778481356e-05,
      "loss": 0.7918,
      "step": 2555
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.793987976418472e-05,
      "loss": 0.9044,
      "step": 2556
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.78667208736244e-05,
      "loss": 0.9215,
      "step": 2557
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.779358115678607e-05,
      "loss": 0.9684,
      "step": 2558
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.772046065731169e-05,
      "loss": 0.8645,
      "step": 2559
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.764735941883184e-05,
      "loss": 0.9751,
      "step": 2560
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.757427748496552e-05,
      "loss": 1.0925,
      "step": 2561
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.750121489932025e-05,
      "loss": 0.7635,
      "step": 2562
    },
    {
      "epoch": 1.82,
      "learning_rate": 6.742817170549205e-05,
      "loss": 1.0927,
      "step": 2563
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.735514794706528e-05,
      "loss": 0.8607,
      "step": 2564
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.728214366761278e-05,
      "loss": 0.9463,
      "step": 2565
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.720915891069575e-05,
      "loss": 0.9928,
      "step": 2566
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.713619371986367e-05,
      "loss": 0.9857,
      "step": 2567
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.706324813865444e-05,
      "loss": 0.7185,
      "step": 2568
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.699032221059422e-05,
      "loss": 0.8535,
      "step": 2569
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.691741597919745e-05,
      "loss": 0.9681,
      "step": 2570
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.68445294879668e-05,
      "loss": 0.9093,
      "step": 2571
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.677166278039316e-05,
      "loss": 0.9502,
      "step": 2572
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.669881589995567e-05,
      "loss": 0.7346,
      "step": 2573
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.662598889012154e-05,
      "loss": 0.7227,
      "step": 2574
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.655318179434624e-05,
      "loss": 0.7625,
      "step": 2575
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.648039465607327e-05,
      "loss": 1.2417,
      "step": 2576
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.640762751873422e-05,
      "loss": 0.7674,
      "step": 2577
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.633488042574882e-05,
      "loss": 0.8473,
      "step": 2578
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.626215342052475e-05,
      "loss": 1.0561,
      "step": 2579
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.61894465464578e-05,
      "loss": 0.8821,
      "step": 2580
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.61167598469317e-05,
      "loss": 0.8335,
      "step": 2581
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.604409336531809e-05,
      "loss": 0.8861,
      "step": 2582
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.597144714497661e-05,
      "loss": 1.0907,
      "step": 2583
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.589882122925483e-05,
      "loss": 0.8688,
      "step": 2584
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.58262156614881e-05,
      "loss": 0.9556,
      "step": 2585
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.575363048499977e-05,
      "loss": 0.8552,
      "step": 2586
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.568106574310091e-05,
      "loss": 0.8077,
      "step": 2587
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.560852147909045e-05,
      "loss": 0.9151,
      "step": 2588
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.553599773625507e-05,
      "loss": 0.8515,
      "step": 2589
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.546349455786926e-05,
      "loss": 0.8352,
      "step": 2590
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.539101198719514e-05,
      "loss": 1.0196,
      "step": 2591
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.531855006748267e-05,
      "loss": 1.0819,
      "step": 2592
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.524610884196935e-05,
      "loss": 0.7959,
      "step": 2593
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.517368835388044e-05,
      "loss": 0.7826,
      "step": 2594
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.510128864642877e-05,
      "loss": 0.8247,
      "step": 2595
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.502890976281475e-05,
      "loss": 0.9112,
      "step": 2596
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.495655174622646e-05,
      "loss": 1.0684,
      "step": 2597
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.48842146398394e-05,
      "loss": 0.9276,
      "step": 2598
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.48118984868167e-05,
      "loss": 1.0917,
      "step": 2599
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.473960333030895e-05,
      "loss": 0.7403,
      "step": 2600
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.466732921345416e-05,
      "loss": 1.0569,
      "step": 2601
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.459507617937788e-05,
      "loss": 0.8178,
      "step": 2602
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.4522844271193e-05,
      "loss": 1.0889,
      "step": 2603
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.445063353199989e-05,
      "loss": 0.8218,
      "step": 2604
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.437844400488617e-05,
      "loss": 0.8488,
      "step": 2605
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.430627573292689e-05,
      "loss": 0.8396,
      "step": 2606
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.423412875918443e-05,
      "loss": 1.0444,
      "step": 2607
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.416200312670838e-05,
      "loss": 0.7901,
      "step": 2608
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.408989887853564e-05,
      "loss": 0.977,
      "step": 2609
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.401781605769041e-05,
      "loss": 1.0007,
      "step": 2610
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.394575470718403e-05,
      "loss": 0.829,
      "step": 2611
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.387371487001501e-05,
      "loss": 1.075,
      "step": 2612
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.38016965891691e-05,
      "loss": 0.8893,
      "step": 2613
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.372969990761911e-05,
      "loss": 0.8051,
      "step": 2614
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.365772486832504e-05,
      "loss": 0.9491,
      "step": 2615
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.358577151423391e-05,
      "loss": 0.8319,
      "step": 2616
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.351383988827981e-05,
      "loss": 0.9555,
      "step": 2617
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.344193003338393e-05,
      "loss": 0.8783,
      "step": 2618
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.337004199245438e-05,
      "loss": 0.8526,
      "step": 2619
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.329817580838628e-05,
      "loss": 0.8169,
      "step": 2620
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.322633152406176e-05,
      "loss": 0.9901,
      "step": 2621
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.315450918234983e-05,
      "loss": 0.8271,
      "step": 2622
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.308270882610643e-05,
      "loss": 0.807,
      "step": 2623
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.301093049817437e-05,
      "loss": 0.6978,
      "step": 2624
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.293917424138329e-05,
      "loss": 1.0534,
      "step": 2625
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.286744009854975e-05,
      "loss": 0.7516,
      "step": 2626
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.279572811247698e-05,
      "loss": 0.9035,
      "step": 2627
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.272403832595513e-05,
      "loss": 1.0035,
      "step": 2628
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.265237078176099e-05,
      "loss": 0.8635,
      "step": 2629
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.258072552265812e-05,
      "loss": 0.8295,
      "step": 2630
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.250910259139685e-05,
      "loss": 1.0359,
      "step": 2631
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.243750203071405e-05,
      "loss": 0.8249,
      "step": 2632
    },
    {
      "epoch": 1.87,
      "learning_rate": 6.236592388333338e-05,
      "loss": 0.8773,
      "step": 2633
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.229436819196503e-05,
      "loss": 0.8733,
      "step": 2634
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.22228349993058e-05,
      "loss": 1.0933,
      "step": 2635
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.215132434803914e-05,
      "loss": 0.7825,
      "step": 2636
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.207983628083495e-05,
      "loss": 0.8069,
      "step": 2637
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.200837084034974e-05,
      "loss": 1.0338,
      "step": 2638
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.193692806922642e-05,
      "loss": 0.8856,
      "step": 2639
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.186550801009451e-05,
      "loss": 0.7272,
      "step": 2640
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.179411070556989e-05,
      "loss": 0.9814,
      "step": 2641
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.172273619825484e-05,
      "loss": 0.6903,
      "step": 2642
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.165138453073807e-05,
      "loss": 0.849,
      "step": 2643
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.158005574559471e-05,
      "loss": 0.9964,
      "step": 2644
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.150874988538616e-05,
      "loss": 0.8178,
      "step": 2645
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.143746699266015e-05,
      "loss": 1.1617,
      "step": 2646
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.136620710995077e-05,
      "loss": 0.8582,
      "step": 2647
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.129497027977829e-05,
      "loss": 0.7264,
      "step": 2648
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.122375654464931e-05,
      "loss": 1.0562,
      "step": 2649
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.115256594705658e-05,
      "loss": 0.7768,
      "step": 2650
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.108139852947908e-05,
      "loss": 0.919,
      "step": 2651
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.1010254334381965e-05,
      "loss": 0.9824,
      "step": 2652
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.093913340421653e-05,
      "loss": 0.7711,
      "step": 2653
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.086803578142014e-05,
      "loss": 0.7902,
      "step": 2654
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.079696150841634e-05,
      "loss": 1.0755,
      "step": 2655
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.0725910627614634e-05,
      "loss": 0.9901,
      "step": 2656
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.0654883181410694e-05,
      "loss": 0.9776,
      "step": 2657
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.0583879212186114e-05,
      "loss": 0.8104,
      "step": 2658
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.051289876230848e-05,
      "loss": 0.8603,
      "step": 2659
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.0441941874131415e-05,
      "loss": 1.0903,
      "step": 2660
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.037100858999439e-05,
      "loss": 0.8172,
      "step": 2661
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.03000989522229e-05,
      "loss": 0.9312,
      "step": 2662
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.022921300312826e-05,
      "loss": 0.785,
      "step": 2663
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.0158350785007625e-05,
      "loss": 0.9403,
      "step": 2664
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.008751234014405e-05,
      "loss": 0.9413,
      "step": 2665
    },
    {
      "epoch": 1.9,
      "learning_rate": 6.001669771080638e-05,
      "loss": 1.0148,
      "step": 2666
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.994590693924926e-05,
      "loss": 1.1057,
      "step": 2667
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.9875140067713055e-05,
      "loss": 0.8462,
      "step": 2668
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.9804397138423965e-05,
      "loss": 0.8874,
      "step": 2669
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.973367819359379e-05,
      "loss": 0.9061,
      "step": 2670
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.96629832754201e-05,
      "loss": 1.0323,
      "step": 2671
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.9592312426086095e-05,
      "loss": 0.8773,
      "step": 2672
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.952166568776062e-05,
      "loss": 0.8414,
      "step": 2673
    },
    {
      "epoch": 1.9,
      "learning_rate": 5.945104310259813e-05,
      "loss": 0.8714,
      "step": 2674
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.938044471273865e-05,
      "loss": 0.9229,
      "step": 2675
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.930987056030781e-05,
      "loss": 0.8934,
      "step": 2676
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.923932068741673e-05,
      "loss": 0.96,
      "step": 2677
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.916879513616211e-05,
      "loss": 0.7015,
      "step": 2678
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.909829394862608e-05,
      "loss": 0.7696,
      "step": 2679
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.902781716687622e-05,
      "loss": 0.8665,
      "step": 2680
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.89573648329656e-05,
      "loss": 0.8554,
      "step": 2681
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.8886936988932676e-05,
      "loss": 0.6992,
      "step": 2682
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.8816533676801265e-05,
      "loss": 0.9711,
      "step": 2683
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.874615493858061e-05,
      "loss": 1.0169,
      "step": 2684
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.8675800816265226e-05,
      "loss": 0.8778,
      "step": 2685
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.860547135183498e-05,
      "loss": 1.1186,
      "step": 2686
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.853516658725502e-05,
      "loss": 0.9225,
      "step": 2687
    },
    {
      "epoch": 1.91,
      "learning_rate": 5.846488656447573e-05,
      "loss": 0.8429,
      "step": 2688
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.839463132543277e-05,
      "loss": 0.8301,
      "step": 2689
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.832440091204698e-05,
      "loss": 1.0508,
      "step": 2690
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.825419536622436e-05,
      "loss": 0.8307,
      "step": 2691
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.8184014729856194e-05,
      "loss": 1.0462,
      "step": 2692
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.8113859044818764e-05,
      "loss": 1.0018,
      "step": 2693
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.8043728352973535e-05,
      "loss": 1.2929,
      "step": 2694
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.797362269616704e-05,
      "loss": 0.7365,
      "step": 2695
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.790354211623084e-05,
      "loss": 0.8367,
      "step": 2696
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.7833486654981606e-05,
      "loss": 0.9139,
      "step": 2697
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.7763456354220955e-05,
      "loss": 0.9731,
      "step": 2698
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.769345125573559e-05,
      "loss": 1.0565,
      "step": 2699
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.7623471401297047e-05,
      "loss": 0.981,
      "step": 2700
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.7553516832661855e-05,
      "loss": 0.8824,
      "step": 2701
    },
    {
      "epoch": 1.92,
      "learning_rate": 5.748358759157149e-05,
      "loss": 1.038,
      "step": 2702
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.741368371975221e-05,
      "loss": 0.9379,
      "step": 2703
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.73438052589153e-05,
      "loss": 0.7339,
      "step": 2704
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.727395225075675e-05,
      "loss": 0.904,
      "step": 2705
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.72041247369574e-05,
      "loss": 1.0476,
      "step": 2706
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.713432275918287e-05,
      "loss": 1.1783,
      "step": 2707
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.706454635908354e-05,
      "loss": 0.8772,
      "step": 2708
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.699479557829461e-05,
      "loss": 0.8556,
      "step": 2709
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.692507045843587e-05,
      "loss": 0.755,
      "step": 2710
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.6855371041111874e-05,
      "loss": 0.7755,
      "step": 2711
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.6785697367911796e-05,
      "loss": 0.9737,
      "step": 2712
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.671604948040945e-05,
      "loss": 0.851,
      "step": 2713
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.664642742016336e-05,
      "loss": 0.9164,
      "step": 2714
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.657683122871652e-05,
      "loss": 0.8522,
      "step": 2715
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.650726094759653e-05,
      "loss": 0.7793,
      "step": 2716
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.643771661831554e-05,
      "loss": 0.8973,
      "step": 2717
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.6368198282370164e-05,
      "loss": 1.2387,
      "step": 2718
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.6298705981241615e-05,
      "loss": 0.8201,
      "step": 2719
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.622923975639548e-05,
      "loss": 1.0445,
      "step": 2720
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.61597996492818e-05,
      "loss": 0.7962,
      "step": 2721
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.609038570133505e-05,
      "loss": 0.9271,
      "step": 2722
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.602099795397405e-05,
      "loss": 1.068,
      "step": 2723
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.595163644860209e-05,
      "loss": 0.8711,
      "step": 2724
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.588230122660671e-05,
      "loss": 0.9634,
      "step": 2725
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.5812992329359804e-05,
      "loss": 0.8942,
      "step": 2726
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.574370979821753e-05,
      "loss": 0.8813,
      "step": 2727
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.567445367452029e-05,
      "loss": 0.8714,
      "step": 2728
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.56052239995928e-05,
      "loss": 0.8398,
      "step": 2729
    },
    {
      "epoch": 1.94,
      "learning_rate": 5.553602081474403e-05,
      "loss": 0.9852,
      "step": 2730
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.546684416126702e-05,
      "loss": 0.8375,
      "step": 2731
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.539769408043904e-05,
      "loss": 0.8266,
      "step": 2732
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.5328570613521524e-05,
      "loss": 1.0266,
      "step": 2733
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.525947380175991e-05,
      "loss": 0.7783,
      "step": 2734
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.5190403686383954e-05,
      "loss": 0.8951,
      "step": 2735
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.512136030860729e-05,
      "loss": 0.9894,
      "step": 2736
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.505234370962764e-05,
      "loss": 0.9864,
      "step": 2737
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.4983353930626816e-05,
      "loss": 0.8996,
      "step": 2738
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.491439101277049e-05,
      "loss": 0.9294,
      "step": 2739
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.4845454997208504e-05,
      "loss": 0.956,
      "step": 2740
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.477654592507449e-05,
      "loss": 1.0928,
      "step": 2741
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.470766383748602e-05,
      "loss": 1.0031,
      "step": 2742
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.463880877554464e-05,
      "loss": 0.7692,
      "step": 2743
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.456998078033566e-05,
      "loss": 0.9331,
      "step": 2744
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.45011798929284e-05,
      "loss": 0.8489,
      "step": 2745
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.443240615437586e-05,
      "loss": 0.8965,
      "step": 2746
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.436365960571488e-05,
      "loss": 1.0935,
      "step": 2747
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.429494028796609e-05,
      "loss": 1.1367,
      "step": 2748
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.4226248242133845e-05,
      "loss": 1.1471,
      "step": 2749
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.41575835092063e-05,
      "loss": 0.8956,
      "step": 2750
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.408894613015525e-05,
      "loss": 0.7775,
      "step": 2751
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.4020336145936154e-05,
      "loss": 0.9721,
      "step": 2752
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.3951753597488176e-05,
      "loss": 0.9202,
      "step": 2753
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.3883198525734025e-05,
      "loss": 0.9186,
      "step": 2754
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.381467097158016e-05,
      "loss": 0.9504,
      "step": 2755
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.37461709759165e-05,
      "loss": 1.0482,
      "step": 2756
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.3677698579616484e-05,
      "loss": 0.8153,
      "step": 2757
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.3609253823537276e-05,
      "loss": 0.7041,
      "step": 2758
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.354083674851936e-05,
      "loss": 0.773,
      "step": 2759
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.347244739538677e-05,
      "loss": 1.0722,
      "step": 2760
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.3404085804946955e-05,
      "loss": 0.906,
      "step": 2761
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.3335752017990926e-05,
      "loss": 0.9541,
      "step": 2762
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.3267446075292945e-05,
      "loss": 0.8461,
      "step": 2763
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.319916801761078e-05,
      "loss": 1.214,
      "step": 2764
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.313091788568547e-05,
      "loss": 0.7384,
      "step": 2765
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.306269572024143e-05,
      "loss": 0.8815,
      "step": 2766
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.299450156198642e-05,
      "loss": 0.7735,
      "step": 2767
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.292633545161146e-05,
      "loss": 0.9407,
      "step": 2768
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.285819742979081e-05,
      "loss": 0.9534,
      "step": 2769
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.2790087537182006e-05,
      "loss": 1.014,
      "step": 2770
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.272200581442574e-05,
      "loss": 0.7499,
      "step": 2771
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.265395230214601e-05,
      "loss": 0.8962,
      "step": 2772
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.258592704094987e-05,
      "loss": 0.8396,
      "step": 2773
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.251793007142758e-05,
      "loss": 0.7621,
      "step": 2774
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.2449961434152484e-05,
      "loss": 0.8623,
      "step": 2775
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.2382021169680986e-05,
      "loss": 0.7041,
      "step": 2776
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.2314109318552685e-05,
      "loss": 1.0564,
      "step": 2777
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.224622592129011e-05,
      "loss": 0.9351,
      "step": 2778
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.2178371018398886e-05,
      "loss": 0.8855,
      "step": 2779
    },
    {
      "epoch": 1.98,
      "learning_rate": 5.2110544650367546e-05,
      "loss": 1.0443,
      "step": 2780
    },
    {
      "epoch": 1.98,
      "eval_loss": 0.7743580937385559,
      "eval_runtime": 934.383,
      "eval_samples_per_second": 0.784,
      "eval_steps_per_second": 0.393,
      "step": 2780
    }
  ],
  "logging_steps": 1,
  "max_steps": 4167,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 278,
  "total_flos": 1.0393715520099582e+20,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}