{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2313668179370818,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.0749,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.0939,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.0808,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.0523,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 2.0731,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.0781,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 2.0222,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 2.0379,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 2.0547,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.088,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.2e-06,
      "loss": 2.0938,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.9722,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.6e-06,
      "loss": 2.0697,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 2.0278,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 3e-06,
      "loss": 2.0449,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 2.0585,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 2.0547,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 2.0735,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 2.1028,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.1025,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 2.0129,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.4e-06,
      "loss": 2.0452,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.600000000000001e-06,
      "loss": 2.0978,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.800000000000001e-06,
      "loss": 2.0609,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 5e-06,
      "loss": 2.0783,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.2e-06,
      "loss": 2.0535,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.400000000000001e-06,
      "loss": 2.0383,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.600000000000001e-06,
      "loss": 2.0492,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.8e-06,
      "loss": 2.097,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 6e-06,
      "loss": 2.0641,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.200000000000001e-06,
      "loss": 2.0511,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 2.0927,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.600000000000001e-06,
      "loss": 1.9922,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.800000000000001e-06,
      "loss": 2.0557,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 7e-06,
      "loss": 1.992,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 2.0997,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.4e-06,
      "loss": 2.0116,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.9953,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 7.800000000000002e-06,
      "loss": 2.043,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0136,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.2e-06,
      "loss": 2.0295,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.400000000000001e-06,
      "loss": 2.0217,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.6e-06,
      "loss": 2.0433,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.8e-06,
      "loss": 1.937,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 9e-06,
      "loss": 1.9604,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.9755,
      "step": 46
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.4e-06,
      "loss": 1.9808,
      "step": 47
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.600000000000001e-06,
      "loss": 2.0126,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.800000000000001e-06,
      "loss": 2.0072,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 1e-05,
      "loss": 2.0112,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.02e-05,
      "loss": 2.0066,
      "step": 51
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.04e-05,
      "loss": 1.9487,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 2.0321,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 1.9578,
      "step": 54
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 2.0002,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 1.9924,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.14e-05,
      "loss": 1.9803,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.16e-05,
      "loss": 1.9154,
      "step": 58
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.18e-05,
      "loss": 1.9307,
      "step": 59
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.2e-05,
      "loss": 1.9131,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.22e-05,
      "loss": 1.9555,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 1.9246,
      "step": 62
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 1.9316,
      "step": 63
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 1.8861,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 1.9391,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 1.8988,
      "step": 66
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.3400000000000002e-05,
      "loss": 1.8759,
      "step": 67
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.8406,
      "step": 68
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.38e-05,
      "loss": 1.8932,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.4e-05,
      "loss": 1.8809,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.4200000000000001e-05,
      "loss": 1.877,
      "step": 71
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 1.8344,
      "step": 72
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.46e-05,
      "loss": 1.8449,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.48e-05,
      "loss": 1.7725,
      "step": 74
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.7643,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 1.7966,
      "step": 76
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.54e-05,
      "loss": 1.8069,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 1.7931,
      "step": 78
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.58e-05,
      "loss": 1.7639,
      "step": 79
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.7514,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.62e-05,
      "loss": 1.7457,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.64e-05,
      "loss": 1.7195,
      "step": 82
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.66e-05,
      "loss": 1.7307,
      "step": 83
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.6572,
      "step": 84
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.7e-05,
      "loss": 1.6728,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.72e-05,
      "loss": 1.6499,
      "step": 86
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.7400000000000003e-05,
      "loss": 1.6669,
      "step": 87
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.76e-05,
      "loss": 1.5629,
      "step": 88
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 1.5887,
      "step": 89
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.8e-05,
      "loss": 1.5662,
      "step": 90
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 1.574,
      "step": 91
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 1.5435,
      "step": 92
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.86e-05,
      "loss": 1.5675,
      "step": 93
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.88e-05,
      "loss": 1.5504,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.9e-05,
      "loss": 1.5344,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 1.5012,
      "step": 96
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.94e-05,
      "loss": 1.4572,
      "step": 97
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 1.4746,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.98e-05,
      "loss": 1.3997,
      "step": 99
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 1.4291,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.9982110912343474e-05,
      "loss": 1.3956,
      "step": 101
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.9964221824686943e-05,
      "loss": 1.3893,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.9946332737030415e-05,
      "loss": 1.3612,
      "step": 103
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.9928443649373884e-05,
      "loss": 1.3851,
      "step": 104
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.9910554561717356e-05,
      "loss": 1.4022,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.9892665474060825e-05,
      "loss": 1.3556,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.9874776386404297e-05,
      "loss": 1.3112,
      "step": 107
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9856887298747766e-05,
      "loss": 1.3367,
      "step": 108
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9838998211091234e-05,
      "loss": 1.2876,
      "step": 109
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9821109123434707e-05,
      "loss": 1.2824,
      "step": 110
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.9803220035778175e-05,
      "loss": 1.2417,
      "step": 111
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.9785330948121648e-05,
      "loss": 1.2683,
      "step": 112
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.9767441860465116e-05,
      "loss": 1.2332,
      "step": 113
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.974955277280859e-05,
      "loss": 1.2492,
      "step": 114
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.9731663685152057e-05,
      "loss": 1.2397,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.971377459749553e-05,
      "loss": 1.2537,
      "step": 116
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9695885509839e-05,
      "loss": 1.2242,
      "step": 117
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.967799642218247e-05,
      "loss": 1.211,
      "step": 118
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9660107334525943e-05,
      "loss": 1.1657,
      "step": 119
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.964221824686941e-05,
      "loss": 1.1705,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9624329159212884e-05,
      "loss": 1.1687,
      "step": 121
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9606440071556353e-05,
      "loss": 1.1469,
      "step": 122
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.9588550983899825e-05,
      "loss": 1.1621,
      "step": 123
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.9570661896243294e-05,
      "loss": 1.1559,
      "step": 124
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.9552772808586762e-05,
      "loss": 1.1086,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.9534883720930235e-05,
      "loss": 1.089,
      "step": 126
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.9516994633273703e-05,
      "loss": 1.0888,
      "step": 127
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9499105545617176e-05,
      "loss": 1.0849,
      "step": 128
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9481216457960644e-05,
      "loss": 1.0562,
      "step": 129
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9463327370304117e-05,
      "loss": 1.0523,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9445438282647585e-05,
      "loss": 1.0164,
      "step": 131
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9427549194991058e-05,
      "loss": 1.0467,
      "step": 132
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.9409660107334526e-05,
      "loss": 1.0242,
      "step": 133
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.9391771019678e-05,
      "loss": 1.0218,
      "step": 134
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.9373881932021467e-05,
      "loss": 0.988,
      "step": 135
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.935599284436494e-05,
      "loss": 1.0138,
      "step": 136
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.933810375670841e-05,
      "loss": 1.0288,
      "step": 137
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.932021466905188e-05,
      "loss": 0.9849,
      "step": 138
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9302325581395353e-05,
      "loss": 1.0165,
      "step": 139
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.928443649373882e-05,
      "loss": 0.979,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.9266547406082294e-05,
      "loss": 0.9418,
      "step": 141
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.9248658318425763e-05,
      "loss": 0.9832,
      "step": 142
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.923076923076923e-05,
      "loss": 0.9422,
      "step": 143
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.9212880143112704e-05,
      "loss": 1.0011,
      "step": 144
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9194991055456172e-05,
      "loss": 0.9562,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.917710196779964e-05,
      "loss": 0.9214,
      "step": 146
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9159212880143113e-05,
      "loss": 0.9713,
      "step": 147
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9141323792486586e-05,
      "loss": 0.9227,
      "step": 148
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9123434704830054e-05,
      "loss": 0.944,
      "step": 149
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9105545617173527e-05,
      "loss": 0.9623,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9087656529516995e-05,
      "loss": 0.9324,
      "step": 151
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9069767441860468e-05,
      "loss": 0.941,
      "step": 152
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.9051878354203936e-05,
      "loss": 0.9442,
      "step": 153
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.903398926654741e-05,
      "loss": 0.8992,
      "step": 154
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.9016100178890877e-05,
      "loss": 0.8882,
      "step": 155
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.899821109123435e-05,
      "loss": 0.9508,
      "step": 156
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.8980322003577822e-05,
      "loss": 0.9295,
      "step": 157
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.896243291592129e-05,
      "loss": 0.9519,
      "step": 158
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.894454382826476e-05,
      "loss": 0.9342,
      "step": 159
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.892665474060823e-05,
      "loss": 0.9766,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.89087656529517e-05,
      "loss": 0.9625,
      "step": 161
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.889087656529517e-05,
      "loss": 0.8774,
      "step": 162
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.887298747763864e-05,
      "loss": 0.9137,
      "step": 163
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.885509838998211e-05,
      "loss": 0.9574,
      "step": 164
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.8837209302325582e-05,
      "loss": 0.9246,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.881932021466905e-05,
      "loss": 0.8908,
      "step": 166
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.8801431127012523e-05,
      "loss": 0.8991,
      "step": 167
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.8783542039355996e-05,
      "loss": 0.9756,
      "step": 168
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.8765652951699464e-05,
      "loss": 0.9422,
      "step": 169
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.8747763864042937e-05,
      "loss": 0.9082,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.8729874776386405e-05,
      "loss": 0.9071,
      "step": 171
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.8711985688729878e-05,
      "loss": 0.9027,
      "step": 172
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8694096601073346e-05,
      "loss": 0.8683,
      "step": 173
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.867620751341682e-05,
      "loss": 0.8829,
      "step": 174
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.8658318425760287e-05,
      "loss": 0.9089,
      "step": 175
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.864042933810376e-05,
      "loss": 0.9022,
      "step": 176
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.862254025044723e-05,
      "loss": 0.8839,
      "step": 177
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.86046511627907e-05,
      "loss": 0.9115,
      "step": 178
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.858676207513417e-05,
      "loss": 0.869,
      "step": 179
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8568872987477638e-05,
      "loss": 0.9228,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.855098389982111e-05,
      "loss": 0.9513,
      "step": 181
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.853309481216458e-05,
      "loss": 0.8936,
      "step": 182
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.851520572450805e-05,
      "loss": 0.883,
      "step": 183
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.849731663685152e-05,
      "loss": 0.8078,
      "step": 184
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8479427549194992e-05,
      "loss": 0.8923,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 0.8929,
      "step": 186
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8443649373881933e-05,
      "loss": 0.889,
      "step": 187
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8425760286225406e-05,
      "loss": 0.8927,
      "step": 188
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.8407871198568874e-05,
      "loss": 0.8774,
      "step": 189
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.8389982110912347e-05,
      "loss": 0.8691,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.8372093023255815e-05,
      "loss": 0.9064,
      "step": 191
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.8354203935599288e-05,
      "loss": 0.8597,
      "step": 192
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8336314847942756e-05,
      "loss": 0.8927,
      "step": 193
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.831842576028623e-05,
      "loss": 0.8337,
      "step": 194
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8300536672629697e-05,
      "loss": 0.8601,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.8282647584973166e-05,
      "loss": 0.8689,
      "step": 196
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.826475849731664e-05,
      "loss": 0.8508,
      "step": 197
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.8246869409660107e-05,
      "loss": 0.8423,
      "step": 198
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.822898032200358e-05,
      "loss": 0.8897,
      "step": 199
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.8211091234347048e-05,
      "loss": 0.867,
      "step": 200
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.819320214669052e-05,
      "loss": 0.8933,
      "step": 201
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.817531305903399e-05,
      "loss": 0.9027,
      "step": 202
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.815742397137746e-05,
      "loss": 0.8983,
      "step": 203
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.813953488372093e-05,
      "loss": 0.8857,
      "step": 204
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.8121645796064402e-05,
      "loss": 0.8266,
      "step": 205
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.8103756708407875e-05,
      "loss": 0.8404,
      "step": 206
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.8085867620751343e-05,
      "loss": 0.8731,
      "step": 207
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.8067978533094816e-05,
      "loss": 0.8429,
      "step": 208
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.8050089445438284e-05,
      "loss": 0.8586,
      "step": 209
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.8032200357781757e-05,
      "loss": 0.8492,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.8014311270125225e-05,
      "loss": 0.8351,
      "step": 211
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.7996422182468694e-05,
      "loss": 0.8566,
      "step": 212
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.7978533094812166e-05,
      "loss": 0.872,
      "step": 213
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7960644007155635e-05,
      "loss": 0.8946,
      "step": 214
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7942754919499107e-05,
      "loss": 0.8784,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7924865831842576e-05,
      "loss": 0.8371,
      "step": 216
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.790697674418605e-05,
      "loss": 0.8649,
      "step": 217
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.7889087656529517e-05,
      "loss": 0.819,
      "step": 218
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.787119856887299e-05,
      "loss": 0.8903,
      "step": 219
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.7853309481216458e-05,
      "loss": 0.8675,
      "step": 220
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.783542039355993e-05,
      "loss": 0.8728,
      "step": 221
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.78175313059034e-05,
      "loss": 0.8753,
      "step": 222
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.779964221824687e-05,
      "loss": 0.8156,
      "step": 223
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.7781753130590344e-05,
      "loss": 0.8388,
      "step": 224
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.7763864042933812e-05,
      "loss": 0.8928,
      "step": 225
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.7745974955277285e-05,
      "loss": 0.8225,
      "step": 226
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.7728085867620753e-05,
      "loss": 0.8366,
      "step": 227
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.7710196779964222e-05,
      "loss": 0.8131,
      "step": 228
    },
    {
      "epoch": 0.56,
      "learning_rate": 1.7692307692307694e-05,
      "loss": 0.8717,
      "step": 229
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.7674418604651163e-05,
      "loss": 0.8281,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.7656529516994635e-05,
      "loss": 0.8203,
      "step": 231
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.7638640429338104e-05,
      "loss": 0.8409,
      "step": 232
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.7620751341681576e-05,
      "loss": 0.9037,
      "step": 233
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.7602862254025045e-05,
      "loss": 0.9087,
      "step": 234
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.7584973166368517e-05,
      "loss": 0.8616,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.7567084078711986e-05,
      "loss": 0.8293,
      "step": 236
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.754919499105546e-05,
      "loss": 0.9028,
      "step": 237
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7531305903398927e-05,
      "loss": 0.8728,
      "step": 238
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.75134168157424e-05,
      "loss": 0.8617,
      "step": 239
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7495527728085868e-05,
      "loss": 0.8362,
      "step": 240
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.747763864042934e-05,
      "loss": 0.9042,
      "step": 241
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.745974955277281e-05,
      "loss": 0.8496,
      "step": 242
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.744186046511628e-05,
      "loss": 0.8953,
      "step": 243
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.742397137745975e-05,
      "loss": 0.8925,
      "step": 244
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.7406082289803222e-05,
      "loss": 0.8732,
      "step": 245
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.738819320214669e-05,
      "loss": 0.8479,
      "step": 246
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.7370304114490163e-05,
      "loss": 0.841,
      "step": 247
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.7352415026833632e-05,
      "loss": 0.8621,
      "step": 248
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.73345259391771e-05,
      "loss": 0.8883,
      "step": 249
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.7316636851520573e-05,
      "loss": 0.9141,
      "step": 250
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.7298747763864042e-05,
      "loss": 0.8723,
      "step": 251
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.7280858676207514e-05,
      "loss": 0.8421,
      "step": 252
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.7262969588550986e-05,
      "loss": 0.81,
      "step": 253
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.7245080500894455e-05,
      "loss": 0.8013,
      "step": 254
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.7227191413237927e-05,
      "loss": 0.8855,
      "step": 255
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.7209302325581396e-05,
      "loss": 0.8604,
      "step": 256
    },
    {
      "epoch": 0.63,
      "learning_rate": 1.719141323792487e-05,
      "loss": 0.8795,
      "step": 257
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.7173524150268337e-05,
      "loss": 0.8324,
      "step": 258
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.715563506261181e-05,
      "loss": 0.8615,
      "step": 259
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.7137745974955278e-05,
      "loss": 0.8045,
      "step": 260
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.711985688729875e-05,
      "loss": 0.8664,
      "step": 261
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.710196779964222e-05,
      "loss": 0.848,
      "step": 262
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.708407871198569e-05,
      "loss": 0.8489,
      "step": 263
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.706618962432916e-05,
      "loss": 0.8425,
      "step": 264
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.704830053667263e-05,
      "loss": 0.881,
      "step": 265
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.70304114490161e-05,
      "loss": 0.877,
      "step": 266
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.701252236135957e-05,
      "loss": 0.8441,
      "step": 267
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.6994633273703042e-05,
      "loss": 0.8549,
      "step": 268
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.697674418604651e-05,
      "loss": 0.8613,
      "step": 269
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.6958855098389983e-05,
      "loss": 0.8643,
      "step": 270
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.6940966010733455e-05,
      "loss": 0.87,
      "step": 271
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.6923076923076924e-05,
      "loss": 0.9223,
      "step": 272
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.6905187835420396e-05,
      "loss": 0.8748,
      "step": 273
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.6887298747763865e-05,
      "loss": 0.8234,
      "step": 274
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.6869409660107337e-05,
      "loss": 0.8259,
      "step": 275
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.6851520572450806e-05,
      "loss": 0.8406,
      "step": 276
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.683363148479428e-05,
      "loss": 0.8218,
      "step": 277
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.6815742397137747e-05,
      "loss": 0.8564,
      "step": 278
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.679785330948122e-05,
      "loss": 0.885,
      "step": 279
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.6779964221824688e-05,
      "loss": 0.8218,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.6762075134168157e-05,
      "loss": 0.8206,
      "step": 281
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.674418604651163e-05,
      "loss": 0.8428,
      "step": 282
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.6726296958855098e-05,
      "loss": 0.8816,
      "step": 283
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.670840787119857e-05,
      "loss": 0.8458,
      "step": 284
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.669051878354204e-05,
      "loss": 0.8412,
      "step": 285
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.667262969588551e-05,
      "loss": 0.8458,
      "step": 286
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.665474060822898e-05,
      "loss": 0.854,
      "step": 287
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.6636851520572452e-05,
      "loss": 0.8831,
      "step": 288
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.661896243291592e-05,
      "loss": 0.9012,
      "step": 289
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.6601073345259393e-05,
      "loss": 0.8148,
      "step": 290
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.6583184257602865e-05,
      "loss": 0.8257,
      "step": 291
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.6565295169946334e-05,
      "loss": 0.8451,
      "step": 292
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.6547406082289806e-05,
      "loss": 0.8355,
      "step": 293
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.6529516994633275e-05,
      "loss": 0.8564,
      "step": 294
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.6511627906976747e-05,
      "loss": 0.8922,
      "step": 295
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.6493738819320216e-05,
      "loss": 0.87,
      "step": 296
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.647584973166369e-05,
      "loss": 0.8307,
      "step": 297
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.6457960644007157e-05,
      "loss": 0.8233,
      "step": 298
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.6440071556350626e-05,
      "loss": 0.8436,
      "step": 299
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.6422182468694098e-05,
      "loss": 0.8316,
      "step": 300
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.6404293381037567e-05,
      "loss": 0.8468,
      "step": 301
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.638640429338104e-05,
      "loss": 0.851,
      "step": 302
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.6368515205724508e-05,
      "loss": 0.8277,
      "step": 303
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.635062611806798e-05,
      "loss": 0.8296,
      "step": 304
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.633273703041145e-05,
      "loss": 0.8571,
      "step": 305
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.631484794275492e-05,
      "loss": 0.8691,
      "step": 306
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.629695885509839e-05,
      "loss": 0.8477,
      "step": 307
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.6279069767441862e-05,
      "loss": 0.8399,
      "step": 308
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.6261180679785334e-05,
      "loss": 0.8243,
      "step": 309
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.6243291592128803e-05,
      "loss": 0.8439,
      "step": 310
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.6225402504472275e-05,
      "loss": 0.8175,
      "step": 311
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.6207513416815744e-05,
      "loss": 0.8134,
      "step": 312
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.6189624329159216e-05,
      "loss": 0.8575,
      "step": 313
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.6171735241502685e-05,
      "loss": 0.8559,
      "step": 314
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 0.8374,
      "step": 315
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.6135957066189626e-05,
      "loss": 0.7871,
      "step": 316
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.6118067978533095e-05,
      "loss": 0.8712,
      "step": 317
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.6100178890876567e-05,
      "loss": 0.8224,
      "step": 318
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.6082289803220036e-05,
      "loss": 0.8406,
      "step": 319
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.6064400715563508e-05,
      "loss": 0.8155,
      "step": 320
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.6046511627906977e-05,
      "loss": 0.8617,
      "step": 321
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.602862254025045e-05,
      "loss": 0.8328,
      "step": 322
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.6010733452593918e-05,
      "loss": 0.829,
      "step": 323
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.599284436493739e-05,
      "loss": 0.8293,
      "step": 324
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.597495527728086e-05,
      "loss": 0.8227,
      "step": 325
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.595706618962433e-05,
      "loss": 0.8653,
      "step": 326
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.59391771019678e-05,
      "loss": 0.8151,
      "step": 327
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.5921288014311272e-05,
      "loss": 0.7727,
      "step": 328
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.5903398926654744e-05,
      "loss": 0.862,
      "step": 329
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.5885509838998213e-05,
      "loss": 0.7711,
      "step": 330
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.5867620751341682e-05,
      "loss": 0.7793,
      "step": 331
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5849731663685154e-05,
      "loss": 0.8516,
      "step": 332
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5831842576028623e-05,
      "loss": 0.8307,
      "step": 333
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5813953488372095e-05,
      "loss": 0.8396,
      "step": 334
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5796064400715564e-05,
      "loss": 0.8286,
      "step": 335
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5778175313059033e-05,
      "loss": 0.8009,
      "step": 336
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5760286225402505e-05,
      "loss": 0.8019,
      "step": 337
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5742397137745977e-05,
      "loss": 0.8213,
      "step": 338
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5724508050089446e-05,
      "loss": 0.8219,
      "step": 339
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5706618962432918e-05,
      "loss": 0.8349,
      "step": 340
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5688729874776387e-05,
      "loss": 0.8143,
      "step": 341
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.567084078711986e-05,
      "loss": 0.8195,
      "step": 342
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5652951699463328e-05,
      "loss": 0.7934,
      "step": 343
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.56350626118068e-05,
      "loss": 0.8411,
      "step": 344
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.561717352415027e-05,
      "loss": 0.8399,
      "step": 345
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.559928443649374e-05,
      "loss": 0.8198,
      "step": 346
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.558139534883721e-05,
      "loss": 0.8247,
      "step": 347
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.5563506261180682e-05,
      "loss": 0.8273,
      "step": 348
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.554561717352415e-05,
      "loss": 0.8559,
      "step": 349
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.5527728085867623e-05,
      "loss": 0.8711,
      "step": 350
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.5509838998211092e-05,
      "loss": 0.7908,
      "step": 351
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.549194991055456e-05,
      "loss": 0.77,
      "step": 352
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.5474060822898033e-05,
      "loss": 0.8534,
      "step": 353
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.5456171735241502e-05,
      "loss": 0.8307,
      "step": 354
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.5438282647584974e-05,
      "loss": 0.833,
      "step": 355
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.5420393559928446e-05,
      "loss": 0.8106,
      "step": 356
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.5402504472271915e-05,
      "loss": 0.8492,
      "step": 357
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.8324,
      "step": 358
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.5366726296958856e-05,
      "loss": 0.7787,
      "step": 359
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.5348837209302328e-05,
      "loss": 0.8056,
      "step": 360
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.5330948121645797e-05,
      "loss": 0.8535,
      "step": 361
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.531305903398927e-05,
      "loss": 0.8351,
      "step": 362
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.5295169946332738e-05,
      "loss": 0.8457,
      "step": 363
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.527728085867621e-05,
      "loss": 0.8336,
      "step": 364
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.525939177101968e-05,
      "loss": 0.8459,
      "step": 365
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.524150268336315e-05,
      "loss": 0.8714,
      "step": 366
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.5223613595706622e-05,
      "loss": 0.8258,
      "step": 367
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.520572450805009e-05,
      "loss": 0.9213,
      "step": 368
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.5187835420393563e-05,
      "loss": 0.8341,
      "step": 369
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.5169946332737031e-05,
      "loss": 0.8022,
      "step": 370
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.5152057245080502e-05,
      "loss": 0.7943,
      "step": 371
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.5134168157423972e-05,
      "loss": 0.852,
      "step": 372
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.5116279069767443e-05,
      "loss": 0.8684,
      "step": 373
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.5098389982110912e-05,
      "loss": 0.8951,
      "step": 374
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.5080500894454384e-05,
      "loss": 0.8065,
      "step": 375
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.5062611806797856e-05,
      "loss": 0.8308,
      "step": 376
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.5044722719141325e-05,
      "loss": 0.8609,
      "step": 377
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.5026833631484795e-05,
      "loss": 0.8266,
      "step": 378
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.5008944543828266e-05,
      "loss": 0.8265,
      "step": 379
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.4991055456171736e-05,
      "loss": 0.8416,
      "step": 380
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.4973166368515207e-05,
      "loss": 0.8167,
      "step": 381
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.4955277280858677e-05,
      "loss": 0.8447,
      "step": 382
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.4937388193202146e-05,
      "loss": 0.8328,
      "step": 383
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4919499105545618e-05,
      "loss": 0.8347,
      "step": 384
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.490161001788909e-05,
      "loss": 0.8552,
      "step": 385
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.488372093023256e-05,
      "loss": 0.8543,
      "step": 386
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.486583184257603e-05,
      "loss": 0.8652,
      "step": 387
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.48479427549195e-05,
      "loss": 0.8058,
      "step": 388
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.4830053667262971e-05,
      "loss": 0.8092,
      "step": 389
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.481216457960644e-05,
      "loss": 0.8588,
      "step": 390
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.4794275491949912e-05,
      "loss": 0.8591,
      "step": 391
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.477638640429338e-05,
      "loss": 0.8499,
      "step": 392
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.4758497316636853e-05,
      "loss": 0.8223,
      "step": 393
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.4740608228980323e-05,
      "loss": 0.8023,
      "step": 394
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.4722719141323794e-05,
      "loss": 0.8077,
      "step": 395
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.4704830053667264e-05,
      "loss": 0.8578,
      "step": 396
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4686940966010735e-05,
      "loss": 0.8287,
      "step": 397
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4669051878354205e-05,
      "loss": 0.8481,
      "step": 398
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4651162790697674e-05,
      "loss": 0.8197,
      "step": 399
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.4633273703041146e-05,
      "loss": 0.811,
      "step": 400
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.4615384615384615e-05,
      "loss": 0.7848,
      "step": 401
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.4597495527728087e-05,
      "loss": 0.7713,
      "step": 402
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.4579606440071556e-05,
      "loss": 0.8476,
      "step": 403
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.4561717352415028e-05,
      "loss": 0.829,
      "step": 404
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.4543828264758499e-05,
      "loss": 0.8703,
      "step": 405
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.452593917710197e-05,
      "loss": 0.8499,
      "step": 406
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.450805008944544e-05,
      "loss": 1.0286,
      "step": 407
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.4490161001788909e-05,
      "loss": 0.817,
      "step": 408
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.4472271914132381e-05,
      "loss": 0.8247,
      "step": 409
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.445438282647585e-05,
      "loss": 0.8081,
      "step": 410
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.4436493738819322e-05,
      "loss": 0.8309,
      "step": 411
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.441860465116279e-05,
      "loss": 0.8615,
      "step": 412
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.4400715563506263e-05,
      "loss": 0.8196,
      "step": 413
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.4382826475849733e-05,
      "loss": 0.8586,
      "step": 414
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.4364937388193202e-05,
      "loss": 0.8293,
      "step": 415
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.4347048300536674e-05,
      "loss": 0.8287,
      "step": 416
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.4329159212880143e-05,
      "loss": 0.8315,
      "step": 417
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.4311270125223615e-05,
      "loss": 0.8359,
      "step": 418
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.4293381037567084e-05,
      "loss": 0.8281,
      "step": 419
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.4275491949910556e-05,
      "loss": 0.8205,
      "step": 420
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.4257602862254025e-05,
      "loss": 0.8177,
      "step": 421
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.4239713774597497e-05,
      "loss": 0.8261,
      "step": 422
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.4221824686940968e-05,
      "loss": 0.8496,
      "step": 423
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.4203935599284437e-05,
      "loss": 0.8056,
      "step": 424
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.4186046511627909e-05,
      "loss": 0.877,
      "step": 425
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.4168157423971378e-05,
      "loss": 0.8444,
      "step": 426
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.415026833631485e-05,
      "loss": 0.8212,
      "step": 427
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.4132379248658319e-05,
      "loss": 0.8268,
      "step": 428
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.4114490161001791e-05,
      "loss": 0.8419,
      "step": 429
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.409660107334526e-05,
      "loss": 0.863,
      "step": 430
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.407871198568873e-05,
      "loss": 0.8222,
      "step": 431
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.4060822898032202e-05,
      "loss": 0.8259,
      "step": 432
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.4042933810375671e-05,
      "loss": 0.7908,
      "step": 433
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.4025044722719143e-05,
      "loss": 0.8292,
      "step": 434
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.4007155635062612e-05,
      "loss": 0.8414,
      "step": 435
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.3989266547406084e-05,
      "loss": 0.8316,
      "step": 436
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.3971377459749553e-05,
      "loss": 0.8278,
      "step": 437
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.3953488372093025e-05,
      "loss": 0.7725,
      "step": 438
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.3935599284436494e-05,
      "loss": 0.8013,
      "step": 439
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.3917710196779965e-05,
      "loss": 0.8475,
      "step": 440
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.3899821109123435e-05,
      "loss": 0.8314,
      "step": 441
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.3881932021466906e-05,
      "loss": 0.8102,
      "step": 442
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.3864042933810378e-05,
      "loss": 0.8208,
      "step": 443
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.3846153846153847e-05,
      "loss": 0.8327,
      "step": 444
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.3828264758497319e-05,
      "loss": 0.8524,
      "step": 445
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.3810375670840788e-05,
      "loss": 0.8201,
      "step": 446
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.379248658318426e-05,
      "loss": 0.8399,
      "step": 447
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.3774597495527729e-05,
      "loss": 0.8894,
      "step": 448
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.37567084078712e-05,
      "loss": 0.8275,
      "step": 449
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.373881932021467e-05,
      "loss": 0.8194,
      "step": 450
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.372093023255814e-05,
      "loss": 0.7857,
      "step": 451
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.3703041144901612e-05,
      "loss": 0.7948,
      "step": 452
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.3685152057245081e-05,
      "loss": 0.832,
      "step": 453
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.3667262969588553e-05,
      "loss": 0.7991,
      "step": 454
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.3649373881932022e-05,
      "loss": 0.8105,
      "step": 455
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.3631484794275493e-05,
      "loss": 0.8577,
      "step": 456
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.3613595706618963e-05,
      "loss": 0.7955,
      "step": 457
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.3595706618962434e-05,
      "loss": 0.827,
      "step": 458
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.3577817531305904e-05,
      "loss": 0.8027,
      "step": 459
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.3559928443649375e-05,
      "loss": 0.8225,
      "step": 460
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.3542039355992847e-05,
      "loss": 0.8167,
      "step": 461
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.3524150268336316e-05,
      "loss": 0.8369,
      "step": 462
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.3506261180679788e-05,
      "loss": 0.7537,
      "step": 463
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.3488372093023257e-05,
      "loss": 0.817,
      "step": 464
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.3470483005366727e-05,
      "loss": 0.7976,
      "step": 465
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.3452593917710198e-05,
      "loss": 0.8305,
      "step": 466
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.3434704830053668e-05,
      "loss": 0.7939,
      "step": 467
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.3416815742397137e-05,
      "loss": 0.8733,
      "step": 468
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.339892665474061e-05,
      "loss": 0.8397,
      "step": 469
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.3381037567084081e-05,
      "loss": 0.7967,
      "step": 470
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.336314847942755e-05,
      "loss": 0.8074,
      "step": 471
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.334525939177102e-05,
      "loss": 0.8251,
      "step": 472
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.3327370304114491e-05,
      "loss": 0.8205,
      "step": 473
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.3309481216457962e-05,
      "loss": 0.8295,
      "step": 474
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.3291592128801432e-05,
      "loss": 0.7885,
      "step": 475
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.3273703041144903e-05,
      "loss": 0.7987,
      "step": 476
    },
    {
      "epoch": 1.17,
      "learning_rate": 1.3255813953488372e-05,
      "loss": 0.7914,
      "step": 477
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.3237924865831844e-05,
      "loss": 0.8191,
      "step": 478
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.3220035778175316e-05,
      "loss": 0.8328,
      "step": 479
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.3202146690518785e-05,
      "loss": 0.7961,
      "step": 480
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.3184257602862255e-05,
      "loss": 0.8636,
      "step": 481
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.3166368515205726e-05,
      "loss": 0.8132,
      "step": 482
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.3148479427549196e-05,
      "loss": 0.7955,
      "step": 483
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.3130590339892667e-05,
      "loss": 0.7777,
      "step": 484
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.3112701252236137e-05,
      "loss": 0.797,
      "step": 485
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3094812164579606e-05,
      "loss": 0.7756,
      "step": 486
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3076923076923078e-05,
      "loss": 0.7983,
      "step": 487
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.3059033989266547e-05,
      "loss": 0.8013,
      "step": 488
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.304114490161002e-05,
      "loss": 0.8122,
      "step": 489
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.302325581395349e-05,
      "loss": 0.8039,
      "step": 490
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.300536672629696e-05,
      "loss": 0.791,
      "step": 491
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.298747763864043e-05,
      "loss": 0.7874,
      "step": 492
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.29695885509839e-05,
      "loss": 0.8043,
      "step": 493
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.2951699463327372e-05,
      "loss": 0.848,
      "step": 494
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.293381037567084e-05,
      "loss": 0.8273,
      "step": 495
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.2915921288014313e-05,
      "loss": 0.8292,
      "step": 496
    },
    {
      "epoch": 1.22,
      "learning_rate": 1.2898032200357782e-05,
      "loss": 0.8332,
      "step": 497
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.2880143112701254e-05,
      "loss": 0.8476,
      "step": 498
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.2862254025044724e-05,
      "loss": 0.7687,
      "step": 499
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.2844364937388195e-05,
      "loss": 0.8023,
      "step": 500
    }
  ],
  "max_steps": 1218,
  "num_train_epochs": 3,
  "total_flos": 6.5007963669214e+17,
  "trial_name": null,
  "trial_params": null
}