{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1040,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 6.25e-06,
      "loss": 1.354,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.25e-05,
      "loss": 1.4196,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 1.4008,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.5e-05,
      "loss": 1.3531,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.125e-05,
      "loss": 1.2091,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.2213,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.375e-05,
      "loss": 1.18,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.0744,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 1.2032,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.25e-05,
      "loss": 1.0925,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.875e-05,
      "loss": 1.1905,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1024,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.125000000000001e-05,
      "loss": 1.066,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.75e-05,
      "loss": 0.9857,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.375e-05,
      "loss": 1.0583,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.1359,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010625000000000001,
      "loss": 0.3346,
      "step": 17
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011250000000000001,
      "loss": 0.9871,
      "step": 18
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011875,
      "loss": 1.0403,
      "step": 19
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000125,
      "loss": 1.0968,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013125000000000002,
      "loss": 1.0546,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001375,
      "loss": 1.0389,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014375,
      "loss": 1.028,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0471,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015625,
      "loss": 0.9374,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016250000000000002,
      "loss": 1.0271,
      "step": 26
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016875,
      "loss": 0.3417,
      "step": 27
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000175,
      "loss": 0.9645,
      "step": 28
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018125000000000001,
      "loss": 1.0597,
      "step": 29
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001875,
      "loss": 0.9678,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019375000000000002,
      "loss": 0.9314,
      "step": 31
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.04,
      "step": 32
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999951432210904,
      "loss": 1.0053,
      "step": 33
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999805729315381,
      "loss": 0.9822,
      "step": 34
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999956289272873,
      "loss": 0.9289,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999922292480975,
      "loss": 0.9671,
      "step": 36
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019998785828860742,
      "loss": 0.9869,
      "step": 37
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019998251609127464,
      "loss": 0.9501,
      "step": 38
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019997620270799092,
      "loss": 0.8762,
      "step": 39
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019996891820008164,
      "loss": 0.9656,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019996066263830531,
      "loss": 0.9619,
      "step": 41
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019995143610285277,
      "loss": 0.9327,
      "step": 42
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019994123868334655,
      "loss": 0.9848,
      "step": 43
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019993007047883988,
      "loss": 1.0161,
      "step": 44
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019991793159781569,
      "loss": 0.9219,
      "step": 45
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999048221581858,
      "loss": 0.953,
      "step": 46
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001998907422872894,
      "loss": 0.9215,
      "step": 47
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019987569212189224,
      "loss": 0.996,
      "step": 48
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001998596718081849,
      "loss": 0.9969,
      "step": 49
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019984268150178167,
      "loss": 0.9982,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019982472136771882,
      "loss": 0.3213,
      "step": 51
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001998057915804532,
      "loss": 1.0021,
      "step": 52
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019978589232386035,
      "loss": 0.9302,
      "step": 53
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001997650237912329,
      "loss": 0.9078,
      "step": 54
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019974318618527849,
      "loss": 0.9411,
      "step": 55
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019972037971811802,
      "loss": 0.9986,
      "step": 56
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019969660461128342,
      "loss": 0.9609,
      "step": 57
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019967186109571552,
      "loss": 0.935,
      "step": 58
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019964614941176195,
      "loss": 0.9725,
      "step": 59
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019961946980917456,
      "loss": 0.9642,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001995918225471073,
      "loss": 0.9792,
      "step": 61
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019956320789411337,
      "loss": 0.9111,
      "step": 62
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019953362612814296,
      "loss": 0.9991,
      "step": 63
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019950307753654017,
      "loss": 0.9489,
      "step": 64
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001994715624160405,
      "loss": 0.892,
      "step": 65
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019943908107276798,
      "loss": 0.9708,
      "step": 66
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019940563382223197,
      "loss": 0.2971,
      "step": 67
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019937122098932428,
      "loss": 0.9065,
      "step": 68
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001993358429083159,
      "loss": 0.9531,
      "step": 69
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019929949992285396,
      "loss": 0.9471,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001992621923859581,
      "loss": 0.9695,
      "step": 71
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019922392066001722,
      "loss": 0.9679,
      "step": 72
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019918468511678596,
      "loss": 0.9238,
      "step": 73
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.9605,
      "step": 74
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019910332411227758,
      "loss": 0.9854,
      "step": 75
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001990611994413053,
      "loss": 0.9069,
      "step": 76
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019901811253364456,
      "loss": 0.8975,
      "step": 77
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019897406380782261,
      "loss": 0.8872,
      "step": 78
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019892905369170926,
      "loss": 0.9219,
      "step": 79
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019888308262251285,
      "loss": 0.9985,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019883615104677608,
      "loss": 0.9769,
      "step": 81
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019878825942037148,
      "loss": 0.9303,
      "step": 82
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019873940820849714,
      "loss": 0.9734,
      "step": 83
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019868959788567212,
      "loss": 0.9821,
      "step": 84
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019863882893573188,
      "loss": 0.9149,
      "step": 85
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001985871018518236,
      "loss": 0.994,
      "step": 86
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001985344171364012,
      "loss": 0.9824,
      "step": 87
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.938,
      "step": 88
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019842617686733545,
      "loss": 0.9199,
      "step": 89
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019837062236509014,
      "loss": 0.9361,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019831411233411678,
      "loss": 0.8936,
      "step": 91
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019825664732332884,
      "loss": 0.9604,
      "step": 92
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019819822789091598,
      "loss": 0.9126,
      "step": 93
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019813885460433879,
      "loss": 0.3002,
      "step": 94
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.9704,
      "step": 95
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019801724878485438,
      "loss": 0.9617,
      "step": 96
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001979550174331724,
      "loss": 0.9704,
      "step": 97
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019789183458976484,
      "loss": 0.9209,
      "step": 98
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000197827700868362,
      "loss": 0.9234,
      "step": 99
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019776261689193048,
      "loss": 0.9371,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019769658329266718,
      "loss": 1.0014,
      "step": 101
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019762960071199333,
      "loss": 0.9554,
      "step": 102
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019756166980054813,
      "loss": 0.9479,
      "step": 103
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.8958,
      "step": 104
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019742296563395216,
      "loss": 0.9782,
      "step": 105
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019735219372611233,
      "loss": 0.9272,
      "step": 106
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019728047618210995,
      "loss": 0.9196,
      "step": 107
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019720781369857746,
      "loss": 0.9326,
      "step": 108
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019713420698132614,
      "loss": 0.8558,
      "step": 109
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001970596567453391,
      "loss": 0.9383,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019698416371476433,
      "loss": 0.9137,
      "step": 111
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001969077286229078,
      "loss": 0.3247,
      "step": 112
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019683035221222618,
      "loss": 0.9465,
      "step": 113
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019675203523431966,
      "loss": 0.8971,
      "step": 114
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019667277844992475,
      "loss": 0.8971,
      "step": 115
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.8856,
      "step": 116
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019651144855025265,
      "loss": 0.3271,
      "step": 117
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001964293770020628,
      "loss": 0.9045,
      "step": 118
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001963463687815439,
      "loss": 0.9437,
      "step": 119
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001962624246950012,
      "loss": 0.9322,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019617754555783043,
      "loss": 0.9018,
      "step": 121
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019609173219450998,
      "loss": 0.9784,
      "step": 122
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001960049854385929,
      "loss": 0.9623,
      "step": 123
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001959173061326988,
      "loss": 0.3051,
      "step": 124
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019582869512850575,
      "loss": 0.9444,
      "step": 125
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001957391532867418,
      "loss": 0.9439,
      "step": 126
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001956486814771769,
      "loss": 0.931,
      "step": 127
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001955572805786141,
      "loss": 0.9075,
      "step": 128
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019546495147888132,
      "loss": 0.9113,
      "step": 129
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001953716950748227,
      "loss": 0.9328,
      "step": 130
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019527751227228963,
      "loss": 0.9031,
      "step": 131
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019518240398613227,
      "loss": 0.8926,
      "step": 132
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019508637114019038,
      "loss": 0.9489,
      "step": 133
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001949894146672846,
      "loss": 0.2985,
      "step": 134
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019489153550920728,
      "loss": 0.9203,
      "step": 135
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001947927346167132,
      "loss": 0.9452,
      "step": 136
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.9127,
      "step": 137
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001945923714762516,
      "loss": 0.9909,
      "step": 138
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019449081117452302,
      "loss": 0.8861,
      "step": 139
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.9719,
      "step": 140
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001942849380406201,
      "loss": 0.952,
      "step": 141
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019418062720820637,
      "loss": 0.9007,
      "step": 142
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019407540154682472,
      "loss": 0.921,
      "step": 143
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.9232,
      "step": 144
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019386220983449653,
      "loss": 0.9495,
      "step": 145
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019375424585439994,
      "loss": 0.3129,
      "step": 146
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019364537118701542,
      "loss": 0.9249,
      "step": 147
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001935355868899034,
      "loss": 0.9079,
      "step": 148
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019342489402945998,
      "loss": 0.9685,
      "step": 149
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019331329368090666,
      "loss": 0.9026,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019320078692827987,
      "loss": 0.9082,
      "step": 151
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019308737486442045,
      "loss": 0.9867,
      "step": 152
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019297305859096304,
      "loss": 0.9287,
      "step": 153
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019285783921832537,
      "loss": 0.92,
      "step": 154
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001927417178656975,
      "loss": 0.8397,
      "step": 155
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001926246956610309,
      "loss": 0.9437,
      "step": 156
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001925067737410275,
      "loss": 0.902,
      "step": 157
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.9219,
      "step": 158
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019226823534550418,
      "loss": 0.3306,
      "step": 159
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019214762118704076,
      "loss": 0.9146,
      "step": 160
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019202611194733108,
      "loss": 0.9856,
      "step": 161
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019190370880666207,
      "loss": 0.8802,
      "step": 162
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019178041295400382,
      "loss": 0.933,
      "step": 163
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019165622558699763,
      "loss": 0.8891,
      "step": 164
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019153114791194473,
      "loss": 0.9589,
      "step": 165
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019140518114379434,
      "loss": 0.3159,
      "step": 166
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019127832650613189,
      "loss": 0.9367,
      "step": 167
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019115058523116733,
      "loss": 0.8948,
      "step": 168
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019102195855972287,
      "loss": 0.9252,
      "step": 169
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001908924477412211,
      "loss": 0.917,
      "step": 170
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019076205403367285,
      "loss": 0.9382,
      "step": 171
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000190630778703665,
      "loss": 0.9195,
      "step": 172
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000190498623026348,
      "loss": 0.8703,
      "step": 173
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019036558828542367,
      "loss": 0.8912,
      "step": 174
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019023167577313264,
      "loss": 0.8815,
      "step": 175
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.9702,
      "step": 176
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018996122264603203,
      "loss": 0.8715,
      "step": 177
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018982468465828442,
      "loss": 0.9003,
      "step": 178
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.8853,
      "step": 179
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001895489924657301,
      "loss": 0.9172,
      "step": 180
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018940984093887542,
      "loss": 0.9066,
      "step": 181
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018926982092436117,
      "loss": 0.8922,
      "step": 182
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018912893378227985,
      "loss": 0.9051,
      "step": 183
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001889871808811469,
      "loss": 0.8885,
      "step": 184
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018884456359788724,
      "loss": 0.9208,
      "step": 185
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018870108331782217,
      "loss": 0.3049,
      "step": 186
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018855674143465566,
      "loss": 0.9022,
      "step": 187
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018841153935046098,
      "loss": 0.9392,
      "step": 188
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018826547847566693,
      "loss": 0.9543,
      "step": 189
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018811856022904423,
      "loss": 0.9483,
      "step": 190
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018797078603769184,
      "loss": 0.8272,
      "step": 191
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018782215733702286,
      "loss": 0.9363,
      "step": 192
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001876726755707508,
      "loss": 0.8628,
      "step": 193
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018752234219087538,
      "loss": 0.9399,
      "step": 194
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018737115865766863,
      "loss": 0.9488,
      "step": 195
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018721912643966055,
      "loss": 0.9155,
      "step": 196
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018706624701362483,
      "loss": 0.9434,
      "step": 197
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018691252186456465,
      "loss": 0.9321,
      "step": 198
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018675795248569813,
      "loss": 0.9033,
      "step": 199
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.8924,
      "step": 200
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018644628705240636,
      "loss": 0.8941,
      "step": 201
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001862891940253613,
      "loss": 0.9788,
      "step": 202
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018613126282324092,
      "loss": 0.9482,
      "step": 203
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018597249498011903,
      "loss": 0.9189,
      "step": 204
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001858128920381963,
      "loss": 0.971,
      "step": 205
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018565245554778517,
      "loss": 0.928,
      "step": 206
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018549118706729468,
      "loss": 0.8613,
      "step": 207
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018532908816321558,
      "loss": 0.9415,
      "step": 208
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018516616041010494,
      "loss": 0.8505,
      "step": 209
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001850024053905709,
      "loss": 0.9253,
      "step": 210
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018483782469525738,
      "loss": 0.9365,
      "step": 211
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018467241992282843,
      "loss": 0.8936,
      "step": 212
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018450619267995283,
      "loss": 0.9627,
      "step": 213
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001843391445812886,
      "loss": 0.8926,
      "step": 214
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018417127724946702,
      "loss": 0.9064,
      "step": 215
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018400259231507717,
      "loss": 0.9148,
      "step": 216
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001838330914166499,
      "loss": 0.9293,
      "step": 217
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018366277620064197,
      "loss": 0.3,
      "step": 218
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018349164832142013,
      "loss": 0.9553,
      "step": 219
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001833197094412449,
      "loss": 0.865,
      "step": 220
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.9238,
      "step": 221
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018297340536644875,
      "loss": 0.9083,
      "step": 222
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018279904353567253,
      "loss": 0.916,
      "step": 223
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001826238774315995,
      "loss": 0.9253,
      "step": 224
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001824479087557158,
      "loss": 0.9343,
      "step": 225
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018227113921730334,
      "loss": 0.9062,
      "step": 226
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018209357053342325,
      "loss": 0.9876,
      "step": 227
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001819152044288992,
      "loss": 0.9446,
      "step": 228
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018173604263630063,
      "loss": 0.9048,
      "step": 229
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018155608689592604,
      "loss": 0.9808,
      "step": 230
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018137533895578583,
      "loss": 0.9091,
      "step": 231
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018119380057158568,
      "loss": 0.8511,
      "step": 232
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018101147350670907,
      "loss": 0.9621,
      "step": 233
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018082835953220054,
      "loss": 0.89,
      "step": 234
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018064446042674828,
      "loss": 0.9617,
      "step": 235
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018045977797666684,
      "loss": 0.9026,
      "step": 236
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018027431397587992,
      "loss": 0.8714,
      "step": 237
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018008807022590283,
      "loss": 0.9611,
      "step": 238
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017990104853582493,
      "loss": 0.9143,
      "step": 239
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017971325072229226,
      "loss": 0.9591,
      "step": 240
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017952467860948973,
      "loss": 0.8614,
      "step": 241
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.8888,
      "step": 242
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001791452188204031,
      "loss": 0.906,
      "step": 243
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017895433483002354,
      "loss": 0.9466,
      "step": 244
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017876268391214754,
      "loss": 0.9391,
      "step": 245
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017857026792838737,
      "loss": 0.9269,
      "step": 246
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017837708874778683,
      "loss": 0.8756,
      "step": 247
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.000178183148246803,
      "loss": 0.9507,
      "step": 248
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017798844830928817,
      "loss": 0.9492,
      "step": 249
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017779299082647148,
      "loss": 0.9581,
      "step": 250
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001775967776969405,
      "loss": 0.8927,
      "step": 251
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017739981082662276,
      "loss": 0.9197,
      "step": 252
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017720209212876737,
      "loss": 0.8919,
      "step": 253
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001770036235239263,
      "loss": 0.8873,
      "step": 254
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017680440693993585,
      "loss": 0.9195,
      "step": 255
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.9198,
      "step": 256
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017640373758216077,
      "loss": 0.9114,
      "step": 257
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017620228870030108,
      "loss": 0.9289,
      "step": 258
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017600009962310417,
      "loss": 0.9017,
      "step": 259
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001757971723145453,
      "loss": 0.9194,
      "step": 260
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017559350874577065,
      "loss": 0.9143,
      "step": 261
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.000175389110895078,
      "loss": 0.913,
      "step": 262
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.8694,
      "step": 263
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017497812029677344,
      "loss": 0.8792,
      "step": 264
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017477153154134243,
      "loss": 0.9098,
      "step": 265
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017456421648831655,
      "loss": 0.9043,
      "step": 266
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017435617715146263,
      "loss": 0.919,
      "step": 267
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017414741555158266,
      "loss": 0.9182,
      "step": 268
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017393793371649462,
      "loss": 0.9128,
      "step": 269
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001737277336810124,
      "loss": 0.8936,
      "step": 270
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001735168174869262,
      "loss": 0.9161,
      "step": 271
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017330518718298264,
      "loss": 0.9185,
      "step": 272
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017309284482486495,
      "loss": 0.9087,
      "step": 273
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017287979247517286,
      "loss": 0.9441,
      "step": 274
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001726660322034027,
      "loss": 0.8839,
      "step": 275
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017245156608592727,
      "loss": 0.3174,
      "step": 276
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017223639620597556,
      "loss": 0.8911,
      "step": 277
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017202052465361268,
      "loss": 0.9058,
      "step": 278
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001718039535257194,
      "loss": 0.8988,
      "step": 279
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017158668492597186,
      "loss": 0.9677,
      "step": 280
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001713687209648212,
      "loss": 0.9123,
      "step": 281
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017115006375947303,
      "loss": 0.9187,
      "step": 282
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017093071543386668,
      "loss": 0.9103,
      "step": 283
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.9507,
      "step": 284
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017048995395118252,
      "loss": 0.8716,
      "step": 285
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017026854507546692,
      "loss": 0.3181,
      "step": 286
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017004645364217583,
      "loss": 0.9239,
      "step": 287
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016982368180860728,
      "loss": 0.9222,
      "step": 288
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016960023173866835,
      "loss": 0.9329,
      "step": 289
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016937610560285418,
      "loss": 0.9381,
      "step": 290
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016915130557822695,
      "loss": 0.8579,
      "step": 291
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001689258338483947,
      "loss": 0.8982,
      "step": 292
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016869969260349018,
      "loss": 0.9199,
      "step": 293
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016847288404014935,
      "loss": 0.3165,
      "step": 294
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016824541036149037,
      "loss": 0.8695,
      "step": 295
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016801727377709194,
      "loss": 0.8743,
      "step": 296
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016778847650297197,
      "loss": 0.9202,
      "step": 297
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016755902076156604,
      "loss": 0.858,
      "step": 298
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001673289087817057,
      "loss": 0.9668,
      "step": 299
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016709814279859702,
      "loss": 0.8471,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001668667250537987,
      "loss": 0.8535,
      "step": 301
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001666346577952004,
      "loss": 0.8837,
      "step": 302
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016640194327700086,
      "loss": 0.9569,
      "step": 303
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016616858375968595,
      "loss": 0.9127,
      "step": 304
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.9326,
      "step": 305
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016569993880095806,
      "loss": 0.929,
      "step": 306
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016546465791175496,
      "loss": 0.9183,
      "step": 307
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016522874112781213,
      "loss": 0.9495,
      "step": 308
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016499219074072086,
      "loss": 0.8918,
      "step": 309
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016475500904822706,
      "loss": 0.9207,
      "step": 310
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016451719835420877,
      "loss": 0.9345,
      "step": 311
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.9267,
      "step": 312
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016403969920763788,
      "loss": 0.3331,
      "step": 313
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001638000153933009,
      "loss": 0.9455,
      "step": 314
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016355971185382545,
      "loss": 0.8989,
      "step": 315
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000163318790923414,
      "loss": 0.298,
      "step": 316
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016307725494226584,
      "loss": 0.2894,
      "step": 317
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016283510625655472,
      "loss": 0.9875,
      "step": 318
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016259234721840591,
      "loss": 0.886,
      "step": 319
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.2947,
      "step": 320
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001621050075229168,
      "loss": 0.8589,
      "step": 321
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016186043159937882,
      "loss": 0.8434,
      "step": 322
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016161525479096178,
      "loss": 0.8448,
      "step": 323
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016136947947920476,
      "loss": 0.9115,
      "step": 324
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001611231080514605,
      "loss": 0.8815,
      "step": 325
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.9008,
      "step": 326
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001606285864263498,
      "loss": 0.9077,
      "step": 327
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016038044103254775,
      "loss": 0.8836,
      "step": 328
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016013170912984058,
      "loss": 0.8678,
      "step": 329
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015988239313430004,
      "loss": 0.8614,
      "step": 330
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015963249546767144,
      "loss": 0.8878,
      "step": 331
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015938201855735014,
      "loss": 0.8884,
      "step": 332
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015913096483635824,
      "loss": 0.9089,
      "step": 333
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015887933674332046,
      "loss": 0.884,
      "step": 334
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015862713672244093,
      "loss": 0.9471,
      "step": 335
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000158374367223479,
      "loss": 0.8965,
      "step": 336
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001581210307017259,
      "loss": 0.8936,
      "step": 337
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001578671296179806,
      "loss": 0.9244,
      "step": 338
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015761266643852587,
      "loss": 0.9062,
      "step": 339
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001573576436351046,
      "loss": 0.8906,
      "step": 340
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015710206368489552,
      "loss": 0.8824,
      "step": 341
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015684592907048926,
      "loss": 0.9276,
      "step": 342
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015658924227986414,
      "loss": 0.8786,
      "step": 343
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001563320058063622,
      "loss": 0.8581,
      "step": 344
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001560742221486648,
      "loss": 0.2759,
      "step": 345
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001558158938107684,
      "loss": 0.8955,
      "step": 346
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.8646,
      "step": 347
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015529761313679393,
      "loss": 0.8917,
      "step": 348
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015503766583506524,
      "loss": 0.9241,
      "step": 349
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015477718392178716,
      "loss": 0.9011,
      "step": 350
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001545161699271659,
      "loss": 0.8722,
      "step": 351
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015425462638657595,
      "loss": 0.2777,
      "step": 352
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015399255584053567,
      "loss": 0.8589,
      "step": 353
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001537299608346824,
      "loss": 0.8806,
      "step": 354
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015346684391974794,
      "loss": 0.8985,
      "step": 355
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015320320765153367,
      "loss": 0.8618,
      "step": 356
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015293905459088568,
      "loss": 0.9165,
      "step": 357
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001526743873036701,
      "loss": 0.9175,
      "step": 358
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015240920836074776,
      "loss": 0.822,
      "step": 359
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001521435203379498,
      "loss": 0.8497,
      "step": 360
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015187732581605217,
      "loss": 0.9076,
      "step": 361
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015161062738075067,
      "loss": 0.8994,
      "step": 362
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015134342762263605,
      "loss": 0.878,
      "step": 363
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015107572913716858,
      "loss": 0.2954,
      "step": 364
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015080753452465296,
      "loss": 0.8821,
      "step": 365
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001505388463902131,
      "loss": 0.8977,
      "step": 366
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001502696673437667,
      "loss": 0.8907,
      "step": 367
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8698,
      "step": 368
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001497298469783424,
      "loss": 0.9107,
      "step": 369
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014945921090294076,
      "loss": 0.8447,
      "step": 370
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014918809440263436,
      "loss": 0.8651,
      "step": 371
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014891650011092896,
      "loss": 0.8568,
      "step": 372
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014864443066597139,
      "loss": 0.8937,
      "step": 373
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000148371888710524,
      "loss": 0.9191,
      "step": 374
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014809887689193877,
      "loss": 0.8641,
      "step": 375
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014782539786213183,
      "loss": 0.806,
      "step": 376
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014755145427755754,
      "loss": 0.916,
      "step": 377
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001472770487991827,
      "loss": 0.8781,
      "step": 378
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014700218409246087,
      "loss": 0.8897,
      "step": 379
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001467268628273062,
      "loss": 0.905,
      "step": 380
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014645108767806777,
      "loss": 0.8497,
      "step": 381
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014617486132350343,
      "loss": 0.8647,
      "step": 382
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014589818644675378,
      "loss": 0.9031,
      "step": 383
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001456210657353163,
      "loss": 0.8881,
      "step": 384
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014534350188101904,
      "loss": 0.8955,
      "step": 385
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014506549757999454,
      "loss": 0.8831,
      "step": 386
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014478705553265362,
      "loss": 0.8145,
      "step": 387
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014450817844365921,
      "loss": 0.8334,
      "step": 388
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.9174,
      "step": 389
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001439491299804645,
      "loss": 0.8833,
      "step": 390
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001436689640366137,
      "loss": 0.8729,
      "step": 391
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014338837391175582,
      "loss": 0.8865,
      "step": 392
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014310736233141925,
      "loss": 0.8064,
      "step": 393
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014282593202522627,
      "loss": 0.8814,
      "step": 394
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014254408572686642,
      "loss": 0.8626,
      "step": 395
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014226182617406996,
      "loss": 0.8826,
      "step": 396
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014197915610858144,
      "loss": 0.9192,
      "step": 397
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014169607827613283,
      "loss": 0.8771,
      "step": 398
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014141259542641704,
      "loss": 0.8874,
      "step": 399
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014112871031306119,
      "loss": 0.8448,
      "step": 400
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014084442569359964,
      "loss": 0.9049,
      "step": 401
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014055974432944753,
      "loss": 0.8688,
      "step": 402
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014027466898587374,
      "loss": 0.8754,
      "step": 403
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013998920243197407,
      "loss": 0.834,
      "step": 404
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001397033474406445,
      "loss": 0.8895,
      "step": 405
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013941710678855396,
      "loss": 0.88,
      "step": 406
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001391304832561175,
      "loss": 0.9417,
      "step": 407
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013884347962746948,
      "loss": 0.3594,
      "step": 408
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001385560986904362,
      "loss": 0.8719,
      "step": 409
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.000138268343236509,
      "loss": 0.8576,
      "step": 410
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013798021606081714,
      "loss": 0.8475,
      "step": 411
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013769171996210052,
      "loss": 0.2999,
      "step": 412
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013740285774268283,
      "loss": 0.9098,
      "step": 413
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013711363220844379,
      "loss": 0.8808,
      "step": 414
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013682404616879247,
      "loss": 0.2962,
      "step": 415
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013653410243663952,
      "loss": 0.8367,
      "step": 416
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013624380382837016,
      "loss": 0.9031,
      "step": 417
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013595315316381677,
      "loss": 0.8969,
      "step": 418
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001356621532662313,
      "loss": 0.9031,
      "step": 419
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013537080696225814,
      "loss": 0.8838,
      "step": 420
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013507911708190645,
      "loss": 0.8571,
      "step": 421
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013478708645852272,
      "loss": 0.9161,
      "step": 422
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013449471792876334,
      "loss": 0.8864,
      "step": 423
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.8672,
      "step": 424
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013390897851312667,
      "loss": 0.8653,
      "step": 425
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001336156133168631,
      "loss": 0.8862,
      "step": 426
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013332192159339594,
      "loss": 0.9147,
      "step": 427
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013302790619551674,
      "loss": 0.8628,
      "step": 428
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013273356997916104,
      "loss": 0.8262,
      "step": 429
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013243891580338072,
      "loss": 0.8678,
      "step": 430
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.8903,
      "step": 431
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013184866502516845,
      "loss": 0.9309,
      "step": 432
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013155307415617154,
      "loss": 0.8421,
      "step": 433
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013125717679456447,
      "loss": 0.8575,
      "step": 434
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001309609758145633,
      "loss": 0.8858,
      "step": 435
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013066447409333345,
      "loss": 0.9004,
      "step": 436
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013036767451096148,
      "loss": 0.9071,
      "step": 437
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013007057995042732,
      "loss": 0.9333,
      "step": 438
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012977319329757615,
      "loss": 0.8617,
      "step": 439
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012947551744109043,
      "loss": 0.925,
      "step": 440
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012917755527246179,
      "loss": 0.9664,
      "step": 441
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.000128879309685963,
      "loss": 0.894,
      "step": 442
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001285807835786198,
      "loss": 0.8646,
      "step": 443
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012828197985018276,
      "loss": 0.8991,
      "step": 444
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012798290140309923,
      "loss": 0.9965,
      "step": 445
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012768355114248494,
      "loss": 0.8435,
      "step": 446
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012738393197609602,
      "loss": 0.8812,
      "step": 447
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012708404681430053,
      "loss": 0.8779,
      "step": 448
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012678389857005034,
      "loss": 0.863,
      "step": 449
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012648349015885273,
      "loss": 0.9237,
      "step": 450
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012618282449874222,
      "loss": 0.9368,
      "step": 451
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.9207,
      "step": 452
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012558073311638604,
      "loss": 0.8304,
      "step": 453
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012527931324258975,
      "loss": 0.8987,
      "step": 454
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001249776478167227,
      "loss": 0.9162,
      "step": 455
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012467573976902935,
      "loss": 0.8434,
      "step": 456
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012437359203211108,
      "loss": 0.8428,
      "step": 457
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012407120754089732,
      "loss": 0.8859,
      "step": 458
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012376858923261733,
      "loss": 0.9039,
      "step": 459
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012346574004677154,
      "loss": 0.8998,
      "step": 460
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012316266292510306,
      "loss": 0.9422,
      "step": 461
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012285936081156897,
      "loss": 0.329,
      "step": 462
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012255583665231196,
      "loss": 0.7916,
      "step": 463
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012225209339563145,
      "loss": 0.909,
      "step": 464
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012194813399195518,
      "loss": 0.8475,
      "step": 465
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012164396139381029,
      "loss": 0.303,
      "step": 466
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012133957855579501,
      "loss": 0.874,
      "step": 467
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012103498843454959,
      "loss": 0.9269,
      "step": 468
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012073019398872778,
      "loss": 0.9084,
      "step": 469
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012042519817896804,
      "loss": 0.8731,
      "step": 470
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012012000396786485,
      "loss": 0.8178,
      "step": 471
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011981461431993977,
      "loss": 0.8434,
      "step": 472
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.9207,
      "step": 473
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011920326058117364,
      "loss": 0.9476,
      "step": 474
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011889730242875243,
      "loss": 0.9027,
      "step": 475
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011859116071629149,
      "loss": 0.8772,
      "step": 476
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011828483841751596,
      "loss": 0.8397,
      "step": 477
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011797833850790527,
      "loss": 0.9034,
      "step": 478
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011767166396466403,
      "loss": 0.8309,
      "step": 479
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.935,
      "step": 480
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011705780289456068,
      "loss": 0.8743,
      "step": 481
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011675062233047364,
      "loss": 0.8202,
      "step": 482
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011644327905824808,
      "loss": 0.8972,
      "step": 483
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011613577606328068,
      "loss": 0.8696,
      "step": 484
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001158281163325195,
      "loss": 0.8518,
      "step": 485
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011552030285443515,
      "loss": 0.8939,
      "step": 486
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011521233861899167,
      "loss": 0.8419,
      "step": 487
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011490422661761744,
      "loss": 0.8328,
      "step": 488
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011459596984317622,
      "loss": 0.8727,
      "step": 489
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011428757128993802,
      "loss": 0.8926,
      "step": 490
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011397903395354996,
      "loss": 0.9024,
      "step": 491
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011367036083100735,
      "loss": 0.8846,
      "step": 492
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011336155492062439,
      "loss": 0.8723,
      "step": 493
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.858,
      "step": 494
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011274355673601444,
      "loss": 0.896,
      "step": 495
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011243437046474853,
      "loss": 0.8354,
      "step": 496
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011212506341150615,
      "loss": 0.8706,
      "step": 497
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001118156385807593,
      "loss": 0.9189,
      "step": 498
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011150609897812387,
      "loss": 0.8471,
      "step": 499
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011119644761033078,
      "loss": 0.8705,
      "step": 500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011088668748519647,
      "loss": 0.8107,
      "step": 501
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011057682161159379,
      "loss": 0.8993,
      "step": 502
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011026685299942285,
      "loss": 0.8812,
      "step": 503
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010995678465958168,
      "loss": 0.9024,
      "step": 504
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010964661960393703,
      "loss": 0.8895,
      "step": 505
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010933636084529506,
      "loss": 0.8727,
      "step": 506
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010902601139737225,
      "loss": 0.2772,
      "step": 507
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010871557427476583,
      "loss": 0.9014,
      "step": 508
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010840505249292476,
      "loss": 0.7737,
      "step": 509
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010809444906812033,
      "loss": 0.8699,
      "step": 510
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010778376701741689,
      "loss": 0.8054,
      "step": 511
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010747300935864243,
      "loss": 0.8488,
      "step": 512
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010716217911035951,
      "loss": 0.919,
      "step": 513
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010685127929183567,
      "loss": 0.9037,
      "step": 514
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.8981,
      "step": 515
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010622928302448523,
      "loss": 0.876,
      "step": 516
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010591819261745528,
      "loss": 0.8164,
      "step": 517
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010560704472371919,
      "loss": 0.868,
      "step": 518
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010529584236562995,
      "loss": 0.2778,
      "step": 519
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010498458856606972,
      "loss": 0.8673,
      "step": 520
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010467328634842024,
      "loss": 0.9099,
      "step": 521
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010436193873653361,
      "loss": 0.8871,
      "step": 522
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010405054875470286,
      "loss": 0.845,
      "step": 523
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001037391194276326,
      "loss": 0.8649,
      "step": 524
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010342765378040953,
      "loss": 0.8826,
      "step": 525
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010311615483847332,
      "loss": 0.8452,
      "step": 526
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001028046256275869,
      "loss": 0.844,
      "step": 527
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001024930691738073,
      "loss": 0.8781,
      "step": 528
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010218148850345613,
      "loss": 0.8892,
      "step": 529
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010186988664309023,
      "loss": 0.9034,
      "step": 530
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010155826661947231,
      "loss": 0.8881,
      "step": 531
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010124663145954152,
      "loss": 0.8243,
      "step": 532
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010093498419038394,
      "loss": 0.9244,
      "step": 533
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010062332783920336,
      "loss": 0.8509,
      "step": 534
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010031166543329178,
      "loss": 0.9,
      "step": 535
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 0.8533,
      "step": 536
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.968833456670824e-05,
      "loss": 0.8462,
      "step": 537
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.937667216079665e-05,
      "loss": 0.8059,
      "step": 538
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.90650158096161e-05,
      "loss": 0.8353,
      "step": 539
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.875336854045851e-05,
      "loss": 0.8665,
      "step": 540
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.84417333805277e-05,
      "loss": 0.8581,
      "step": 541
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.813011335690981e-05,
      "loss": 0.9199,
      "step": 542
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.78185114965439e-05,
      "loss": 0.8579,
      "step": 543
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.750693082619273e-05,
      "loss": 0.9114,
      "step": 544
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.719537437241312e-05,
      "loss": 0.8554,
      "step": 545
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.688384516152672e-05,
      "loss": 0.8714,
      "step": 546
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.657234621959051e-05,
      "loss": 0.3176,
      "step": 547
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.626088057236745e-05,
      "loss": 0.914,
      "step": 548
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.594945124529719e-05,
      "loss": 0.8922,
      "step": 549
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.563806126346642e-05,
      "loss": 0.8667,
      "step": 550
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.53267136515798e-05,
      "loss": 0.3195,
      "step": 551
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.501541143393028e-05,
      "loss": 0.8902,
      "step": 552
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.470415763437004e-05,
      "loss": 0.8256,
      "step": 553
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.439295527628081e-05,
      "loss": 0.9084,
      "step": 554
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.408180738254471e-05,
      "loss": 0.7874,
      "step": 555
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.37707169755148e-05,
      "loss": 0.9122,
      "step": 556
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.9025,
      "step": 557
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.314872070816434e-05,
      "loss": 0.8803,
      "step": 558
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.283782088964049e-05,
      "loss": 0.8841,
      "step": 559
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.252699064135758e-05,
      "loss": 0.8256,
      "step": 560
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.221623298258315e-05,
      "loss": 0.9302,
      "step": 561
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.190555093187967e-05,
      "loss": 0.846,
      "step": 562
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.159494750707526e-05,
      "loss": 0.9032,
      "step": 563
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.128442572523417e-05,
      "loss": 0.8943,
      "step": 564
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.097398860262776e-05,
      "loss": 0.8538,
      "step": 565
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.066363915470495e-05,
      "loss": 0.819,
      "step": 566
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.0353380396063e-05,
      "loss": 0.8628,
      "step": 567
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.004321534041835e-05,
      "loss": 0.8669,
      "step": 568
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.973314700057717e-05,
      "loss": 0.929,
      "step": 569
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.942317838840623e-05,
      "loss": 0.903,
      "step": 570
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.911331251480357e-05,
      "loss": 0.9046,
      "step": 571
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.880355238966923e-05,
      "loss": 0.8923,
      "step": 572
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.849390102187614e-05,
      "loss": 0.8832,
      "step": 573
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.818436141924072e-05,
      "loss": 0.8654,
      "step": 574
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.787493658849386e-05,
      "loss": 0.7729,
      "step": 575
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.756562953525152e-05,
      "loss": 0.8695,
      "step": 576
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.725644326398558e-05,
      "loss": 0.858,
      "step": 577
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.8157,
      "step": 578
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.663844507937562e-05,
      "loss": 0.8872,
      "step": 579
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.632963916899268e-05,
      "loss": 0.8417,
      "step": 580
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.602096604645009e-05,
      "loss": 0.8257,
      "step": 581
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.571242871006202e-05,
      "loss": 0.8416,
      "step": 582
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.540403015682381e-05,
      "loss": 0.8232,
      "step": 583
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.509577338238255e-05,
      "loss": 0.8865,
      "step": 584
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.478766138100834e-05,
      "loss": 0.9215,
      "step": 585
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.447969714556484e-05,
      "loss": 0.8856,
      "step": 586
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.417188366748052e-05,
      "loss": 0.8861,
      "step": 587
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.386422393671933e-05,
      "loss": 0.8931,
      "step": 588
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.35567209417519e-05,
      "loss": 0.8967,
      "step": 589
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.324937766952638e-05,
      "loss": 0.8643,
      "step": 590
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.294219710543932e-05,
      "loss": 0.8765,
      "step": 591
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.8973,
      "step": 592
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.2328336035336e-05,
      "loss": 0.9187,
      "step": 593
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.202166149209474e-05,
      "loss": 0.867,
      "step": 594
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.171516158248406e-05,
      "loss": 0.8898,
      "step": 595
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.140883928370855e-05,
      "loss": 0.8804,
      "step": 596
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.11026975712476e-05,
      "loss": 0.8615,
      "step": 597
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.07967394188264e-05,
      "loss": 0.9,
      "step": 598
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.8256,
      "step": 599
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.018538568006027e-05,
      "loss": 0.8613,
      "step": 600
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.987999603213519e-05,
      "loss": 0.8533,
      "step": 601
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.957480182103198e-05,
      "loss": 0.8545,
      "step": 602
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.926980601127225e-05,
      "loss": 0.9173,
      "step": 603
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.896501156545045e-05,
      "loss": 0.8456,
      "step": 604
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.866042144420502e-05,
      "loss": 0.7872,
      "step": 605
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.835603860618972e-05,
      "loss": 0.8519,
      "step": 606
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.805186600804489e-05,
      "loss": 0.8202,
      "step": 607
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.774790660436858e-05,
      "loss": 0.9014,
      "step": 608
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.744416334768808e-05,
      "loss": 0.8634,
      "step": 609
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.714063918843106e-05,
      "loss": 0.8986,
      "step": 610
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.683733707489699e-05,
      "loss": 0.8941,
      "step": 611
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.653425995322851e-05,
      "loss": 0.8697,
      "step": 612
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.623141076738271e-05,
      "loss": 0.2966,
      "step": 613
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.592879245910273e-05,
      "loss": 0.8992,
      "step": 614
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.562640796788892e-05,
      "loss": 0.8272,
      "step": 615
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.532426023097063e-05,
      "loss": 0.8195,
      "step": 616
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.502235218327731e-05,
      "loss": 0.8716,
      "step": 617
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.472068675741025e-05,
      "loss": 0.8775,
      "step": 618
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.4419266883614e-05,
      "loss": 0.8286,
      "step": 619
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.8105,
      "step": 620
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.38171755012578e-05,
      "loss": 0.8623,
      "step": 621
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.351650984114728e-05,
      "loss": 0.8618,
      "step": 622
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.32161014299497e-05,
      "loss": 0.8763,
      "step": 623
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.291595318569951e-05,
      "loss": 0.8745,
      "step": 624
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.2616068023904e-05,
      "loss": 0.868,
      "step": 625
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.231644885751507e-05,
      "loss": 0.8591,
      "step": 626
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.20170985969008e-05,
      "loss": 0.8007,
      "step": 627
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.171802014981726e-05,
      "loss": 0.8453,
      "step": 628
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.141921642138025e-05,
      "loss": 0.8404,
      "step": 629
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.112069031403704e-05,
      "loss": 0.3112,
      "step": 630
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.082244472753822e-05,
      "loss": 0.8688,
      "step": 631
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.052448255890957e-05,
      "loss": 0.9115,
      "step": 632
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.022680670242387e-05,
      "loss": 0.9139,
      "step": 633
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.992942004957271e-05,
      "loss": 0.8984,
      "step": 634
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.963232548903853e-05,
      "loss": 0.8946,
      "step": 635
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.933552590666659e-05,
      "loss": 0.8437,
      "step": 636
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.903902418543671e-05,
      "loss": 0.2748,
      "step": 637
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.874282320543557e-05,
      "loss": 0.8656,
      "step": 638
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.844692584382848e-05,
      "loss": 0.8439,
      "step": 639
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.815133497483157e-05,
      "loss": 0.9071,
      "step": 640
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.785605346968386e-05,
      "loss": 0.8897,
      "step": 641
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.756108419661931e-05,
      "loss": 0.9197,
      "step": 642
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.7266430020839e-05,
      "loss": 0.8341,
      "step": 643
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.697209380448333e-05,
      "loss": 0.8032,
      "step": 644
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.66780784066041e-05,
      "loss": 0.865,
      "step": 645
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.638438668313695e-05,
      "loss": 0.8774,
      "step": 646
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.609102148687333e-05,
      "loss": 0.8925,
      "step": 647
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.579798566743314e-05,
      "loss": 0.8886,
      "step": 648
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.550528207123668e-05,
      "loss": 0.8489,
      "step": 649
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.521291354147727e-05,
      "loss": 0.8443,
      "step": 650
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.492088291809354e-05,
      "loss": 0.8838,
      "step": 651
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.462919303774186e-05,
      "loss": 0.8804,
      "step": 652
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.43378467337687e-05,
      "loss": 0.9203,
      "step": 653
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.404684683618325e-05,
      "loss": 0.8373,
      "step": 654
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.375619617162985e-05,
      "loss": 0.8708,
      "step": 655
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.34658975633605e-05,
      "loss": 0.8661,
      "step": 656
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.317595383120756e-05,
      "loss": 0.7935,
      "step": 657
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.288636779155621e-05,
      "loss": 0.9064,
      "step": 658
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.259714225731718e-05,
      "loss": 0.8391,
      "step": 659
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.230828003789949e-05,
      "loss": 0.863,
      "step": 660
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.20197839391829e-05,
      "loss": 0.8561,
      "step": 661
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.8073,
      "step": 662
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.144390130956384e-05,
      "loss": 0.8308,
      "step": 663
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.115652037253053e-05,
      "loss": 0.8818,
      "step": 664
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.0869516743882516e-05,
      "loss": 0.8434,
      "step": 665
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.058289321144608e-05,
      "loss": 0.8498,
      "step": 666
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.02966525593555e-05,
      "loss": 0.9072,
      "step": 667
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.001079756802592e-05,
      "loss": 0.8502,
      "step": 668
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.9725331014126294e-05,
      "loss": 0.8717,
      "step": 669
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.944025567055251e-05,
      "loss": 0.8952,
      "step": 670
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.9155574306400395e-05,
      "loss": 0.8307,
      "step": 671
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.887128968693887e-05,
      "loss": 0.3252,
      "step": 672
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.858740457358298e-05,
      "loss": 0.7903,
      "step": 673
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.830392172386723e-05,
      "loss": 0.8551,
      "step": 674
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.802084389141862e-05,
      "loss": 0.8756,
      "step": 675
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.773817382593008e-05,
      "loss": 0.8274,
      "step": 676
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.7455914273133646e-05,
      "loss": 0.8234,
      "step": 677
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.717406797477372e-05,
      "loss": 0.8398,
      "step": 678
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6892637668580716e-05,
      "loss": 0.8431,
      "step": 679
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.8118,
      "step": 680
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6331035963386315e-05,
      "loss": 0.2887,
      "step": 681
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.6050870019535494e-05,
      "loss": 0.8779,
      "step": 682
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.8255,
      "step": 683
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.549182155634076e-05,
      "loss": 0.896,
      "step": 684
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.521294446734637e-05,
      "loss": 0.8906,
      "step": 685
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.493450242000546e-05,
      "loss": 0.8753,
      "step": 686
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.465649811898098e-05,
      "loss": 0.8464,
      "step": 687
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.43789342646837e-05,
      "loss": 0.8555,
      "step": 688
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.410181355324622e-05,
      "loss": 0.8804,
      "step": 689
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.382513867649663e-05,
      "loss": 0.9589,
      "step": 690
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.3548912321932244e-05,
      "loss": 0.8507,
      "step": 691
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.32731371726938e-05,
      "loss": 0.7999,
      "step": 692
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.2997815907539164e-05,
      "loss": 0.8169,
      "step": 693
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.272295120081732e-05,
      "loss": 0.8257,
      "step": 694
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.2448545722442486e-05,
      "loss": 0.8272,
      "step": 695
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.217460213786821e-05,
      "loss": 0.8695,
      "step": 696
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.190112310806126e-05,
      "loss": 0.8687,
      "step": 697
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.162811128947602e-05,
      "loss": 0.8309,
      "step": 698
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.135556933402862e-05,
      "loss": 0.773,
      "step": 699
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.108349988907111e-05,
      "loss": 0.7721,
      "step": 700
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.0811905597365684e-05,
      "loss": 0.8258,
      "step": 701
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.054078909705926e-05,
      "loss": 0.8433,
      "step": 702
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.0270153021657674e-05,
      "loss": 0.3298,
      "step": 703
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.8541,
      "step": 704
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.973033265623332e-05,
      "loss": 0.8208,
      "step": 705
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.946115360978696e-05,
      "loss": 0.2857,
      "step": 706
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.919246547534708e-05,
      "loss": 0.8367,
      "step": 707
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.892427086283147e-05,
      "loss": 0.8102,
      "step": 708
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8656572377363974e-05,
      "loss": 0.8184,
      "step": 709
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8389372619249326e-05,
      "loss": 0.8862,
      "step": 710
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8122674183947836e-05,
      "loss": 0.8097,
      "step": 711
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.78564796620502e-05,
      "loss": 0.8373,
      "step": 712
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.759079163925223e-05,
      "loss": 0.8101,
      "step": 713
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.732561269632992e-05,
      "loss": 0.9126,
      "step": 714
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.706094540911429e-05,
      "loss": 0.7949,
      "step": 715
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6796792348466356e-05,
      "loss": 0.7682,
      "step": 716
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.653315608025207e-05,
      "loss": 0.8947,
      "step": 717
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6270039165317605e-05,
      "loss": 0.2755,
      "step": 718
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.600744415946438e-05,
      "loss": 0.8345,
      "step": 719
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.574537361342407e-05,
      "loss": 0.8849,
      "step": 720
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.548383007283412e-05,
      "loss": 0.933,
      "step": 721
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.522281607821288e-05,
      "loss": 0.8122,
      "step": 722
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.4962334164934806e-05,
      "loss": 0.7714,
      "step": 723
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.470238686320606e-05,
      "loss": 0.8433,
      "step": 724
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.8141,
      "step": 725
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.4184106189231625e-05,
      "loss": 0.7967,
      "step": 726
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3925777851335206e-05,
      "loss": 0.8322,
      "step": 727
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3667994193637796e-05,
      "loss": 0.8329,
      "step": 728
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.341075772013589e-05,
      "loss": 0.831,
      "step": 729
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.315407092951078e-05,
      "loss": 0.8835,
      "step": 730
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.289793631510448e-05,
      "loss": 0.8034,
      "step": 731
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.264235636489542e-05,
      "loss": 0.8084,
      "step": 732
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.238733356147414e-05,
      "loss": 0.8064,
      "step": 733
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.213287038201943e-05,
      "loss": 0.8606,
      "step": 734
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.187896929827414e-05,
      "loss": 0.8635,
      "step": 735
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.1625632776521037e-05,
      "loss": 0.8556,
      "step": 736
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.137286327755913e-05,
      "loss": 0.8133,
      "step": 737
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.112066325667954e-05,
      "loss": 0.8767,
      "step": 738
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.086903516364179e-05,
      "loss": 0.3187,
      "step": 739
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0617981442649855e-05,
      "loss": 0.7819,
      "step": 740
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.03675045323286e-05,
      "loss": 0.8333,
      "step": 741
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0117606865699975e-05,
      "loss": 0.8633,
      "step": 742
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.9868290870159405e-05,
      "loss": 0.8909,
      "step": 743
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.961955896745224e-05,
      "loss": 0.7902,
      "step": 744
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.937141357365023e-05,
      "loss": 0.8443,
      "step": 745
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.8641,
      "step": 746
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.887689194853951e-05,
      "loss": 0.9134,
      "step": 747
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.863052052079528e-05,
      "loss": 0.2913,
      "step": 748
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.838474520903825e-05,
      "loss": 0.8777,
      "step": 749
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.813956840062118e-05,
      "loss": 0.8308,
      "step": 750
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7894992477083224e-05,
      "loss": 0.8855,
      "step": 751
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 0.9062,
      "step": 752
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7407652781594095e-05,
      "loss": 0.8469,
      "step": 753
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.716489374344527e-05,
      "loss": 0.8527,
      "step": 754
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.692274505773419e-05,
      "loss": 0.812,
      "step": 755
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.668120907658603e-05,
      "loss": 0.8586,
      "step": 756
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.644028814617454e-05,
      "loss": 0.8885,
      "step": 757
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.6199984606699155e-05,
      "loss": 0.3097,
      "step": 758
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.596030079236212e-05,
      "loss": 0.8789,
      "step": 759
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.7722,
      "step": 760
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.548280164579126e-05,
      "loss": 0.8457,
      "step": 761
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5244990951772974e-05,
      "loss": 0.9218,
      "step": 762
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.500780925927915e-05,
      "loss": 0.7969,
      "step": 763
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.477125887218792e-05,
      "loss": 0.8946,
      "step": 764
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.453534208824507e-05,
      "loss": 0.8432,
      "step": 765
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.430006119904197e-05,
      "loss": 0.8237,
      "step": 766
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.406541848999312e-05,
      "loss": 0.8608,
      "step": 767
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.383141624031408e-05,
      "loss": 0.9161,
      "step": 768
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.359805672299918e-05,
      "loss": 0.847,
      "step": 769
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.336534220479961e-05,
      "loss": 0.8219,
      "step": 770
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.3133274946201334e-05,
      "loss": 0.8323,
      "step": 771
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.290185720140301e-05,
      "loss": 0.9159,
      "step": 772
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2671091218294284e-05,
      "loss": 0.8473,
      "step": 773
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.244097923843398e-05,
      "loss": 0.7981,
      "step": 774
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.2211523497028015e-05,
      "loss": 0.8305,
      "step": 775
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.198272622290804e-05,
      "loss": 0.8608,
      "step": 776
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.1754589638509644e-05,
      "loss": 0.8392,
      "step": 777
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.152711595985065e-05,
      "loss": 0.8483,
      "step": 778
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.130030739650983e-05,
      "loss": 0.8795,
      "step": 779
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.10741661516053e-05,
      "loss": 0.8519,
      "step": 780
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0848694421773075e-05,
      "loss": 0.8352,
      "step": 781
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.062389439714584e-05,
      "loss": 0.2794,
      "step": 782
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0399768261331662e-05,
      "loss": 0.827,
      "step": 783
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0176318191392726e-05,
      "loss": 0.8537,
      "step": 784
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.995354635782417e-05,
      "loss": 0.8556,
      "step": 785
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9731454924533086e-05,
      "loss": 0.83,
      "step": 786
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9510046048817497e-05,
      "loss": 0.8731,
      "step": 787
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.8531,
      "step": 788
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.906928456613336e-05,
      "loss": 0.8603,
      "step": 789
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8849936240527008e-05,
      "loss": 0.8553,
      "step": 790
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8631279035178793e-05,
      "loss": 0.8384,
      "step": 791
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8413315074028158e-05,
      "loss": 0.8604,
      "step": 792
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8196046474280667e-05,
      "loss": 0.8735,
      "step": 793
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.797947534638736e-05,
      "loss": 0.8304,
      "step": 794
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.776360379402445e-05,
      "loss": 0.8339,
      "step": 795
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7548433914072734e-05,
      "loss": 0.8729,
      "step": 796
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7333967796597315e-05,
      "loss": 0.8982,
      "step": 797
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7120207524827168e-05,
      "loss": 0.8141,
      "step": 798
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.690715517513508e-05,
      "loss": 0.8074,
      "step": 799
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.669481281701739e-05,
      "loss": 0.8095,
      "step": 800
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6483182513073835e-05,
      "loss": 0.8131,
      "step": 801
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6272266318987603e-05,
      "loss": 0.301,
      "step": 802
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6062066283505403e-05,
      "loss": 0.8453,
      "step": 803
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5852584448417328e-05,
      "loss": 0.8641,
      "step": 804
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.564382284853738e-05,
      "loss": 0.859,
      "step": 805
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5435783511683443e-05,
      "loss": 0.8272,
      "step": 806
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5228468458657584e-05,
      "loss": 0.8128,
      "step": 807
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.502187970322657e-05,
      "loss": 0.8507,
      "step": 808
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.8377,
      "step": 809
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.461088910492202e-05,
      "loss": 0.8904,
      "step": 810
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.440649125422937e-05,
      "loss": 0.8466,
      "step": 811
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.420282768545469e-05,
      "loss": 0.8064,
      "step": 812
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3999900376895845e-05,
      "loss": 0.8307,
      "step": 813
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3797711299698923e-05,
      "loss": 0.8666,
      "step": 814
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3596262417839255e-05,
      "loss": 0.8841,
      "step": 815
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.8866,
      "step": 816
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.319559306006417e-05,
      "loss": 0.8206,
      "step": 817
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2996376476073723e-05,
      "loss": 0.8701,
      "step": 818
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.279790787123267e-05,
      "loss": 0.2702,
      "step": 819
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.260018917337726e-05,
      "loss": 0.7411,
      "step": 820
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.240322230305951e-05,
      "loss": 0.9003,
      "step": 821
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2207009173528527e-05,
      "loss": 0.8311,
      "step": 822
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.201155169071184e-05,
      "loss": 0.8651,
      "step": 823
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.181685175319702e-05,
      "loss": 0.8779,
      "step": 824
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1622911252213197e-05,
      "loss": 0.8515,
      "step": 825
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.142973207161265e-05,
      "loss": 0.8093,
      "step": 826
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.1237316087852466e-05,
      "loss": 0.837,
      "step": 827
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.1045665169976468e-05,
      "loss": 0.3116,
      "step": 828
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0854781179596938e-05,
      "loss": 0.8511,
      "step": 829
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.8117,
      "step": 830
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.047532139051026e-05,
      "loss": 0.8685,
      "step": 831
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0286749277707782e-05,
      "loss": 0.8709,
      "step": 832
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.009895146417512e-05,
      "loss": 0.8471,
      "step": 833
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9911929774097215e-05,
      "loss": 0.8662,
      "step": 834
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9725686024120095e-05,
      "loss": 0.8608,
      "step": 835
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9540222023333166e-05,
      "loss": 0.853,
      "step": 836
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9355539573251734e-05,
      "loss": 0.8789,
      "step": 837
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.917164046779948e-05,
      "loss": 0.8602,
      "step": 838
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.898852649329095e-05,
      "loss": 0.8645,
      "step": 839
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.880619942841435e-05,
      "loss": 0.8072,
      "step": 840
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8624661044214152e-05,
      "loss": 0.8481,
      "step": 841
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8443913104073983e-05,
      "loss": 0.7949,
      "step": 842
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.826395736369937e-05,
      "loss": 0.8679,
      "step": 843
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.808479557110081e-05,
      "loss": 0.8335,
      "step": 844
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7906429466576767e-05,
      "loss": 0.3107,
      "step": 845
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7728860782696664e-05,
      "loss": 0.8665,
      "step": 846
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7552091244284197e-05,
      "loss": 0.2925,
      "step": 847
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7376122568400532e-05,
      "loss": 0.8225,
      "step": 848
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.720095646432751e-05,
      "loss": 0.8583,
      "step": 849
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.702659463355125e-05,
      "loss": 0.8405,
      "step": 850
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.8011,
      "step": 851
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.668029055875512e-05,
      "loss": 0.8382,
      "step": 852
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6508351678579882e-05,
      "loss": 0.8465,
      "step": 853
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6337223799358026e-05,
      "loss": 0.7947,
      "step": 854
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.616690858335014e-05,
      "loss": 0.8132,
      "step": 855
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5997407684922862e-05,
      "loss": 0.8854,
      "step": 856
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5828722750533008e-05,
      "loss": 0.878,
      "step": 857
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.566085541871145e-05,
      "loss": 0.7978,
      "step": 858
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.549380732004718e-05,
      "loss": 0.8901,
      "step": 859
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 0.8652,
      "step": 860
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5162175304742632e-05,
      "loss": 0.8608,
      "step": 861
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4997594609429088e-05,
      "loss": 0.7125,
      "step": 862
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4833839589895071e-05,
      "loss": 0.8811,
      "step": 863
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.467091183678444e-05,
      "loss": 0.8627,
      "step": 864
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4508812932705363e-05,
      "loss": 0.8571,
      "step": 865
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4347544452214868e-05,
      "loss": 0.8631,
      "step": 866
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4187107961803703e-05,
      "loss": 0.8395,
      "step": 867
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.402750501988097e-05,
      "loss": 0.3013,
      "step": 868
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3868737176759106e-05,
      "loss": 0.8407,
      "step": 869
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3710805974638696e-05,
      "loss": 0.8315,
      "step": 870
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3553712947593656e-05,
      "loss": 0.8442,
      "step": 871
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.8315,
      "step": 872
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3242047514301858e-05,
      "loss": 0.8043,
      "step": 873
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.308747813543536e-05,
      "loss": 0.8817,
      "step": 874
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.293375298637518e-05,
      "loss": 0.812,
      "step": 875
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2780873560339468e-05,
      "loss": 0.832,
      "step": 876
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2628841342331388e-05,
      "loss": 0.284,
      "step": 877
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2477657809124631e-05,
      "loss": 0.8757,
      "step": 878
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2327324429249232e-05,
      "loss": 0.9018,
      "step": 879
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2177842662977135e-05,
      "loss": 0.8504,
      "step": 880
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2029213962308172e-05,
      "loss": 0.8857,
      "step": 881
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.188143977095576e-05,
      "loss": 0.8646,
      "step": 882
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1734521524333086e-05,
      "loss": 0.7393,
      "step": 883
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1588460649539035e-05,
      "loss": 0.824,
      "step": 884
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1443258565344329e-05,
      "loss": 0.8312,
      "step": 885
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.129891668217783e-05,
      "loss": 0.826,
      "step": 886
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1155436402112785e-05,
      "loss": 0.8526,
      "step": 887
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1012819118853147e-05,
      "loss": 0.8498,
      "step": 888
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0871066217720172e-05,
      "loss": 0.8111,
      "step": 889
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0730179075638868e-05,
      "loss": 0.7918,
      "step": 890
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0590159061124605e-05,
      "loss": 0.8257,
      "step": 891
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0451007534269907e-05,
      "loss": 0.8581,
      "step": 892
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 0.8336,
      "step": 893
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0175315341715597e-05,
      "loss": 0.8532,
      "step": 894
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.003877735396801e-05,
      "loss": 0.8009,
      "step": 895
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.903113209758096e-06,
      "loss": 0.8773,
      "step": 896
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.768324226867353e-06,
      "loss": 0.8002,
      "step": 897
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.634411714576353e-06,
      "loss": 0.8647,
      "step": 898
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.501376973651999e-06,
      "loss": 0.8663,
      "step": 899
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.369221296335006e-06,
      "loss": 0.868,
      "step": 900
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.237945966327133e-06,
      "loss": 0.8456,
      "step": 901
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.107552258778907e-06,
      "loss": 0.885,
      "step": 902
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.978041440277163e-06,
      "loss": 0.8014,
      "step": 903
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.849414768832687e-06,
      "loss": 0.2948,
      "step": 904
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.72167349386811e-06,
      "loss": 0.8277,
      "step": 905
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.5948188562057e-06,
      "loss": 0.8294,
      "step": 906
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.46885208805529e-06,
      "loss": 0.9009,
      "step": 907
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.343774413002381e-06,
      "loss": 0.7945,
      "step": 908
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.219587045996203e-06,
      "loss": 0.776,
      "step": 909
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.096291193337934e-06,
      "loss": 0.8616,
      "step": 910
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.973888052668943e-06,
      "loss": 0.8768,
      "step": 911
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.852378812959227e-06,
      "loss": 0.9217,
      "step": 912
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.731764654495832e-06,
      "loss": 0.8185,
      "step": 913
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.8605,
      "step": 914
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.493226258972519e-06,
      "loss": 0.7954,
      "step": 915
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.375304338969136e-06,
      "loss": 0.8045,
      "step": 916
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.258282134302519e-06,
      "loss": 0.88,
      "step": 917
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.142160781674645e-06,
      "loss": 0.8009,
      "step": 918
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.026941409036991e-06,
      "loss": 0.8587,
      "step": 919
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.9126251355795864e-06,
      "loss": 0.3098,
      "step": 920
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.7992130717201564e-06,
      "loss": 0.8006,
      "step": 921
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.68670631909335e-06,
      "loss": 0.8399,
      "step": 922
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.5751059705400295e-06,
      "loss": 0.8155,
      "step": 923
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.464413110096601e-06,
      "loss": 0.7898,
      "step": 924
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.354628812984576e-06,
      "loss": 0.833,
      "step": 925
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.245754145600091e-06,
      "loss": 0.8139,
      "step": 926
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.137790165503499e-06,
      "loss": 0.8778,
      "step": 927
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.8698,
      "step": 928
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.9245984531752784e-06,
      "loss": 0.8491,
      "step": 929
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.8193727917936536e-06,
      "loss": 0.8826,
      "step": 930
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.715061959379875e-06,
      "loss": 0.8765,
      "step": 931
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.611666969163243e-06,
      "loss": 0.8123,
      "step": 932
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.509188825476963e-06,
      "loss": 0.8342,
      "step": 933
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.4076285237483984e-06,
      "loss": 0.9165,
      "step": 934
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.306987050489442e-06,
      "loss": 0.3141,
      "step": 935
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.20726538328683e-06,
      "loss": 0.785,
      "step": 936
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.1084644907927526e-06,
      "loss": 0.8165,
      "step": 937
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.0105853327154e-06,
      "loss": 0.8333,
      "step": 938
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.913628859809638e-06,
      "loss": 0.8787,
      "step": 939
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.817596013867764e-06,
      "loss": 0.8619,
      "step": 940
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.722487727710368e-06,
      "loss": 0.8821,
      "step": 941
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.628304925177318e-06,
      "loss": 0.8327,
      "step": 942
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.5350485211186675e-06,
      "loss": 0.308,
      "step": 943
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.442719421385922e-06,
      "loss": 0.8425,
      "step": 944
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.351318522823133e-06,
      "loss": 0.8183,
      "step": 945
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.260846713258193e-06,
      "loss": 0.8255,
      "step": 946
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.171304871494264e-06,
      "loss": 0.8506,
      "step": 947
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.082693867301224e-06,
      "loss": 0.8721,
      "step": 948
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.99501456140714e-06,
      "loss": 0.9019,
      "step": 949
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.908267805490051e-06,
      "loss": 0.2917,
      "step": 950
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.822454442169576e-06,
      "loss": 0.2966,
      "step": 951
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.7375753049987973e-06,
      "loss": 0.8575,
      "step": 952
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.6536312184560993e-06,
      "loss": 0.8433,
      "step": 953
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.570622997937234e-06,
      "loss": 0.8301,
      "step": 954
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.488551449747357e-06,
      "loss": 0.8446,
      "step": 955
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.8303,
      "step": 956
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.3272215500752658e-06,
      "loss": 0.8115,
      "step": 957
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.247964765680389e-06,
      "loss": 0.8307,
      "step": 958
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.169647787773866e-06,
      "loss": 0.8876,
      "step": 959
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.092271377092215e-06,
      "loss": 0.8771,
      "step": 960
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.0158362852356626e-06,
      "loss": 0.854,
      "step": 961
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.9403432546609043e-06,
      "loss": 0.8442,
      "step": 962
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8657930186738567e-06,
      "loss": 0.8397,
      "step": 963
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7921863014225503e-06,
      "loss": 0.8023,
      "step": 964
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7195238178900684e-06,
      "loss": 0.7843,
      "step": 965
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.647806273887665e-06,
      "loss": 0.7725,
      "step": 966
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.577034366047848e-06,
      "loss": 0.8278,
      "step": 967
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 0.8379,
      "step": 968
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.438330199451877e-06,
      "loss": 0.8656,
      "step": 969
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3703992880066638e-06,
      "loss": 0.2981,
      "step": 970
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3034167073328284e-06,
      "loss": 0.8223,
      "step": 971
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.237383108069546e-06,
      "loss": 0.8424,
      "step": 972
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1722991316380003e-06,
      "loss": 0.8296,
      "step": 973
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1081654102351635e-06,
      "loss": 0.8222,
      "step": 974
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0449825668276244e-06,
      "loss": 0.7831,
      "step": 975
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9827512151456173e-06,
      "loss": 0.8514,
      "step": 976
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.816,
      "step": 977
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8611453956612347e-06,
      "loss": 0.9289,
      "step": 978
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8017721090840322e-06,
      "loss": 0.7767,
      "step": 979
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.7433526766711728e-06,
      "loss": 0.8143,
      "step": 980
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6858876658832233e-06,
      "loss": 0.837,
      "step": 981
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6293776349098677e-06,
      "loss": 0.3026,
      "step": 982
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5738231326645758e-06,
      "loss": 0.8983,
      "step": 983
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 0.8715,
      "step": 984
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.465582863598791e-06,
      "loss": 0.8796,
      "step": 985
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4128981481764115e-06,
      "loss": 0.7794,
      "step": 986
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3611710642681076e-06,
      "loss": 0.9197,
      "step": 987
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3104021143278911e-06,
      "loss": 0.8703,
      "step": 988
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2605917915028742e-06,
      "loss": 0.9204,
      "step": 989
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2117405796285286e-06,
      "loss": 0.8409,
      "step": 990
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.163848953223934e-06,
      "loss": 0.838,
      "step": 991
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1169173774871478e-06,
      "loss": 0.7999,
      "step": 992
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0709463082907545e-06,
      "loss": 0.8404,
      "step": 993
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0259361921774013e-06,
      "loss": 0.8348,
      "step": 994
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.818874663554357e-07,
      "loss": 0.8589,
      "step": 995
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.388005586947191e-07,
      "loss": 0.7929,
      "step": 996
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.966758877224201e-07,
      "loss": 0.8093,
      "step": 997
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.8276,
      "step": 998
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.153148832140466e-07,
      "loss": 0.3251,
      "step": 999
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.760793399827937e-07,
      "loss": 0.8685,
      "step": 1000
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.378076140419187e-07,
      "loss": 0.8518,
      "step": 1001
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.00500077146038e-07,
      "loss": 0.8802,
      "step": 1002
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.641570916840922e-07,
      "loss": 0.8251,
      "step": 1003
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.287790106757396e-07,
      "loss": 0.8853,
      "step": 1004
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.943661777680354e-07,
      "loss": 0.822,
      "step": 1005
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.609189272320237e-07,
      "loss": 0.7566,
      "step": 1006
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.284375839594957e-07,
      "loss": 0.8198,
      "step": 1007
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.969224634598591e-07,
      "loss": 0.7951,
      "step": 1008
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.6637387185706206e-07,
      "loss": 0.8869,
      "step": 1009
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.3679210588661866e-07,
      "loss": 0.8629,
      "step": 1010
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.081774528927218e-07,
      "loss": 0.8464,
      "step": 1011
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.805301908254455e-07,
      "loss": 0.7668,
      "step": 1012
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.5385058823809156e-07,
      "loss": 0.8875,
      "step": 1013
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.281389042844918e-07,
      "loss": 0.8502,
      "step": 1014
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.0339538871660965e-07,
      "loss": 0.8048,
      "step": 1015
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.7962028188198706e-07,
      "loss": 0.8466,
      "step": 1016
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.5681381472151267e-07,
      "loss": 0.8698,
      "step": 1017
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.3497620876711257e-07,
      "loss": 0.8727,
      "step": 1018
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.9219,
      "step": 1019
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9420841954681525e-07,
      "loss": 0.8588,
      "step": 1020
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.752786322811839e-07,
      "loss": 0.8077,
      "step": 1021
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.5731849821833954e-07,
      "loss": 0.8445,
      "step": 1022
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.403281918150978e-07,
      "loss": 0.2915,
      "step": 1023
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.2430787810776555e-07,
      "loss": 0.8511,
      "step": 1024
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0925771271058649e-07,
      "loss": 0.8297,
      "step": 1025
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.517784181422019e-08,
      "loss": 0.8965,
      "step": 1026
    },
    {
      "epoch": 0.99,
      "learning_rate": 8.206840218430989e-08,
      "loss": 0.8259,
      "step": 1027
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.992952116013918e-08,
      "loss": 0.3133,
      "step": 1028
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.8761316653455076e-08,
      "loss": 0.8463,
      "step": 1029
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.856389714723575e-08,
      "loss": 0.8733,
      "step": 1030
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.933736169471347e-08,
      "loss": 0.8935,
      "step": 1031
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.1081799918375454e-08,
      "loss": 0.8309,
      "step": 1032
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.379729200908676e-08,
      "loss": 0.8611,
      "step": 1033
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.7483908725357545e-08,
      "loss": 0.823,
      "step": 1034
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.2141711392588129e-08,
      "loss": 0.8602,
      "step": 1035
    },
    {
      "epoch": 1.0,
      "learning_rate": 7.770751902513862e-09,
      "loss": 0.842,
      "step": 1036
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.371072712727742e-09,
      "loss": 0.8857,
      "step": 1037
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.9427068461808083e-09,
      "loss": 0.8334,
      "step": 1038
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.856778909601012e-10,
      "loss": 0.3639,
      "step": 1039
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.5759,
      "step": 1040
    },
    {
      "epoch": 1.0,
      "step": 1040,
      "total_flos": 1494862192181248.0,
      "train_loss": 0.8496783473457281,
      "train_runtime": 12739.3979,
      "train_samples_per_second": 10.445,
      "train_steps_per_second": 0.082
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 1040,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "total_flos": 1494862192181248.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}