{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 8.695652173913044e-06,
      "loss": 1.5025,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.739130434782609e-05,
      "loss": 1.2014,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.608695652173913e-05,
      "loss": 1.4252,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.478260869565218e-05,
      "loss": 1.4064,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.347826086956522e-05,
      "loss": 1.6361,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.217391304347826e-05,
      "loss": 1.3016,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.086956521739131e-05,
      "loss": 1.4057,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 6.956521739130436e-05,
      "loss": 1.5792,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 7.82608695652174e-05,
      "loss": 1.442,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.695652173913044e-05,
      "loss": 1.3623,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 9.565217391304348e-05,
      "loss": 1.2958,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00010434782608695653,
      "loss": 1.4166,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011304347826086956,
      "loss": 1.426,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012173913043478263,
      "loss": 1.2285,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013043478260869567,
      "loss": 1.3128,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001391304347826087,
      "loss": 1.2511,
      "step": 16
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014782608695652173,
      "loss": 1.2222,
      "step": 17
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001565217391304348,
      "loss": 1.294,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016521739130434784,
      "loss": 1.447,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017391304347826088,
      "loss": 1.2369,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018260869565217392,
      "loss": 1.469,
      "step": 21
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019130434782608697,
      "loss": 1.2539,
      "step": 22
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.2429,
      "step": 23
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001999990663152786,
      "loss": 1.2823,
      "step": 24
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999626527854967,
      "loss": 1.1539,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999159694211892,
      "loss": 1.1343,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999850613931615,
      "loss": 1.0831,
      "step": 27
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999766587537202,
      "loss": 1.3442,
      "step": 28
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019996638918070336,
      "loss": 1.2974,
      "step": 29
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019995425286588184,
      "loss": 1.2714,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019994025003588548,
      "loss": 1.4062,
      "step": 31
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019992438095219886,
      "loss": 1.2071,
      "step": 32
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019990664591115634,
      "loss": 1.2311,
      "step": 33
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019988704524393676,
      "loss": 1.2589,
      "step": 34
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019986557931655688,
      "loss": 1.2766,
      "step": 35
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019984224852986494,
      "loss": 1.2625,
      "step": 36
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019981705331953293,
      "loss": 1.4641,
      "step": 37
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019978999415604847,
      "loss": 1.4287,
      "step": 38
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001997610715447061,
      "loss": 1.336,
      "step": 39
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019973028602559786,
      "loss": 1.1569,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019969763817360314,
      "loss": 1.1655,
      "step": 41
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019966312859837787,
      "loss": 1.3616,
      "step": 42
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001996267579443434,
      "loss": 1.3017,
      "step": 43
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001995885268906742,
      "loss": 1.3204,
      "step": 44
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001995484361512853,
      "loss": 1.4284,
      "step": 45
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001995064864748188,
      "loss": 1.3212,
      "step": 46
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019946267864463026,
      "loss": 1.2725,
      "step": 47
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019941701347877367,
      "loss": 1.3024,
      "step": 48
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001993694918299864,
      "loss": 1.3055,
      "step": 49
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019932011458567315,
      "loss": 1.2735,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019926888266788955,
      "loss": 1.3213,
      "step": 51
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019921579703332474,
      "loss": 1.243,
      "step": 52
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001991608586732837,
      "loss": 1.3062,
      "step": 53
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019910406861366848,
      "loss": 1.2931,
      "step": 54
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019904542791495937,
      "loss": 1.4384,
      "step": 55
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019898493767219483,
      "loss": 1.2831,
      "step": 56
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001989225990149512,
      "loss": 1.2887,
      "step": 57
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001988584131073215,
      "loss": 1.2165,
      "step": 58
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019879238114789373,
      "loss": 1.1418,
      "step": 59
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019872450436972855,
      "loss": 1.3254,
      "step": 60
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019865478404033617,
      "loss": 1.2422,
      "step": 61
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001985832214616527,
      "loss": 1.2131,
      "step": 62
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019850981797001592,
      "loss": 1.1483,
      "step": 63
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019843457493614014,
      "loss": 1.271,
      "step": 64
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019835749376509082,
      "loss": 1.3895,
      "step": 65
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019827857589625817,
      "loss": 1.3028,
      "step": 66
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019819782280333038,
      "loss": 1.3495,
      "step": 67
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019811523599426602,
      "loss": 1.2658,
      "step": 68
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001980308170112659,
      "loss": 1.1571,
      "step": 69
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001979445674307444,
      "loss": 1.3985,
      "step": 70
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019785648886329972,
      "loss": 1.073,
      "step": 71
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001977665829536842,
      "loss": 1.2254,
      "step": 72
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019767485138077326,
      "loss": 1.4155,
      "step": 73
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001975812958575343,
      "loss": 1.3287,
      "step": 74
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019748591813099456,
      "loss": 1.3901,
      "step": 75
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019738871998220857,
      "loss": 1.1718,
      "step": 76
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019728970322622485,
      "loss": 1.2168,
      "step": 77
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019718886971205205,
      "loss": 1.2009,
      "step": 78
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001970862213226244,
      "loss": 1.2114,
      "step": 79
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019698175997476657,
      "loss": 1.5937,
      "step": 80
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001968754876191578,
      "loss": 1.2369,
      "step": 81
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019676740624029567,
      "loss": 1.2128,
      "step": 82
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019665751785645874,
      "loss": 1.2511,
      "step": 83
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019654582451966913,
      "loss": 1.4469,
      "step": 84
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019643232831565414,
      "loss": 1.2032,
      "step": 85
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019631703136380714,
      "loss": 1.24,
      "step": 86
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019619993581714823,
      "loss": 1.3202,
      "step": 87
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019608104386228378,
      "loss": 1.2662,
      "step": 88
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019596035771936592,
      "loss": 1.1238,
      "step": 89
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019583787964205074,
      "loss": 1.3928,
      "step": 90
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019571361191745646,
      "loss": 1.5508,
      "step": 91
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019558755686612057,
      "loss": 1.2687,
      "step": 92
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019545971684195663,
      "loss": 1.2282,
      "step": 93
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019533009423221013,
      "loss": 1.3355,
      "step": 94
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001951986914574141,
      "loss": 1.1111,
      "step": 95
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019506551097134384,
      "loss": 1.3427,
      "step": 96
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000194930555260971,
      "loss": 1.0872,
      "step": 97
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001947938268464173,
      "loss": 1.1873,
      "step": 98
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019465532828090735,
      "loss": 1.2597,
      "step": 99
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019451506215072107,
      "loss": 1.3552,
      "step": 100
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001943730310751453,
      "loss": 1.1638,
      "step": 101
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019422923770642494,
      "loss": 1.2076,
      "step": 102
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019408368472971345,
      "loss": 1.3398,
      "step": 103
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019393637486302256,
      "loss": 1.1939,
      "step": 104
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001937873108571718,
      "loss": 1.3124,
      "step": 105
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019363649549573682,
      "loss": 1.5443,
      "step": 106
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019348393159499759,
      "loss": 1.2504,
      "step": 107
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019332962200388577,
      "loss": 1.1387,
      "step": 108
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019317356960393156,
      "loss": 1.2406,
      "step": 109
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019301577730920975,
      "loss": 1.3236,
      "step": 110
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019285624806628543,
      "loss": 1.2134,
      "step": 111
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019269498485415895,
      "loss": 1.4447,
      "step": 112
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019253199068421028,
      "loss": 1.2898,
      "step": 113
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019236726860014268,
      "loss": 1.1405,
      "step": 114
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019220082167792607,
      "loss": 1.0123,
      "step": 115
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019203265302573938,
      "loss": 1.253,
      "step": 116
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019186276578391265,
      "loss": 1.3768,
      "step": 117
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019169116312486834,
      "loss": 1.0697,
      "step": 118
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019151784825306205,
      "loss": 1.1176,
      "step": 119
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019134282440492272,
      "loss": 1.2583,
      "step": 120
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001911660948487922,
      "loss": 1.0209,
      "step": 121
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019098766288486426,
      "loss": 1.2799,
      "step": 122
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019080753184512282,
      "loss": 1.1244,
      "step": 123
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019062570509327992,
      "loss": 1.3889,
      "step": 124
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019044218602471275,
      "loss": 1.2197,
      "step": 125
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019025697806640033,
      "loss": 1.1068,
      "step": 126
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019007008467685944,
      "loss": 1.1628,
      "step": 127
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018988150934608013,
      "loss": 1.2459,
      "step": 128
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018969125559546054,
      "loss": 1.5482,
      "step": 129
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001894993269777411,
      "loss": 1.3619,
      "step": 130
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001893057270769381,
      "loss": 1.2704,
      "step": 131
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018911045950827693,
      "loss": 1.4129,
      "step": 132
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018891352791812452,
      "loss": 1.6589,
      "step": 133
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018871493598392124,
      "loss": 1.1371,
      "step": 134
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001885146874141121,
      "loss": 1.0249,
      "step": 135
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018831278594807783,
      "loss": 1.0886,
      "step": 136
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001881092353560646,
      "loss": 1.2341,
      "step": 137
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.000187904039439114,
      "loss": 1.091,
      "step": 138
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018769720202899194,
      "loss": 1.1046,
      "step": 139
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018748872698811693,
      "loss": 1.2981,
      "step": 140
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001872786182094882,
      "loss": 1.1426,
      "step": 141
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001870668796166129,
      "loss": 1.3405,
      "step": 142
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018685351516343278,
      "loss": 1.4744,
      "step": 143
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018663852883425046,
      "loss": 1.3066,
      "step": 144
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018642192464365497,
      "loss": 1.3448,
      "step": 145
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018620370663644678,
      "loss": 1.2116,
      "step": 146
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018598387888756223,
      "loss": 1.3548,
      "step": 147
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018576244550199758,
      "loss": 1.3036,
      "step": 148
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018553941061473218,
      "loss": 1.2543,
      "step": 149
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001853147783906514,
      "loss": 1.446,
      "step": 150
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018508855302446867,
      "loss": 1.2109,
      "step": 151
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018486073874064745,
      "loss": 1.2498,
      "step": 152
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.000184631339793322,
      "loss": 1.3629,
      "step": 153
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018440036046621816,
      "loss": 1.0992,
      "step": 154
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018416780507257333,
      "loss": 1.204,
      "step": 155
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018393367795505587,
      "loss": 1.331,
      "step": 156
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.000183697983485684,
      "loss": 1.1731,
      "step": 157
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001834607260657443,
      "loss": 1.3034,
      "step": 158
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018322191012570919,
      "loss": 1.2737,
      "step": 159
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001829815401251547,
      "loss": 1.4202,
      "step": 160
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001827396205526767,
      "loss": 1.2023,
      "step": 161
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018249615592580732,
      "loss": 1.6523,
      "step": 162
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001822511507909307,
      "loss": 1.3558,
      "step": 163
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018200460972319786,
      "loss": 1.2573,
      "step": 164
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001817565373264413,
      "loss": 1.4447,
      "step": 165
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018150693823308913,
      "loss": 1.0333,
      "step": 166
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018125581710407864,
      "loss": 1.2761,
      "step": 167
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000181003178628769,
      "loss": 1.2982,
      "step": 168
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001807490275248539,
      "loss": 1.2358,
      "step": 169
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018049336853827343,
      "loss": 1.1648,
      "step": 170
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018023620644312539,
      "loss": 1.2026,
      "step": 171
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017997754604157605,
      "loss": 1.1491,
      "step": 172
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017971739216377089,
      "loss": 1.2765,
      "step": 173
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017945574966774376,
      "loss": 1.3827,
      "step": 174
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017919262343932678,
      "loss": 1.2097,
      "step": 175
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017892801839205867,
      "loss": 1.2611,
      "step": 176
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017866193946709327,
      "loss": 1.179,
      "step": 177
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017839439163310714,
      "loss": 1.0867,
      "step": 178
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017812537988620675,
      "loss": 1.2562,
      "step": 179
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017785490924983525,
      "loss": 1.0158,
      "step": 180
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017758298477467865,
      "loss": 1.1524,
      "step": 181
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017730961153857155,
      "loss": 1.2147,
      "step": 182
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017703479464640216,
      "loss": 1.2079,
      "step": 183
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001767585392300172,
      "loss": 1.1908,
      "step": 184
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001764808504481259,
      "loss": 1.0956,
      "step": 185
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017620173348620368,
      "loss": 1.2362,
      "step": 186
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017592119355639544,
      "loss": 1.3215,
      "step": 187
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017563923589741806,
      "loss": 1.3085,
      "step": 188
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017535586577446276,
      "loss": 1.2376,
      "step": 189
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017507108847909656,
      "loss": 1.4742,
      "step": 190
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001747849093291637,
      "loss": 1.5781,
      "step": 191
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017449733366868618,
      "loss": 1.345,
      "step": 192
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.000174208366867764,
      "loss": 1.2734,
      "step": 193
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017391801432247488,
      "loss": 1.2547,
      "step": 194
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017362628145477354,
      "loss": 1.1431,
      "step": 195
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017333317371239044,
      "loss": 1.1941,
      "step": 196
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017303869656872995,
      "loss": 1.231,
      "step": 197
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017274285552276828,
      "loss": 1.2727,
      "step": 198
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017244565609895074,
      "loss": 1.2107,
      "step": 199
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001721471038470885,
      "loss": 1.2548,
      "step": 200
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017184720434225518,
      "loss": 1.2215,
      "step": 201
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001715459631846824,
      "loss": 1.2097,
      "step": 202
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001712433859996555,
      "loss": 1.2819,
      "step": 203
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001709394784374084,
      "loss": 1.157,
      "step": 204
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00017063424617301805,
      "loss": 1.4194,
      "step": 205
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001703276949062985,
      "loss": 1.4027,
      "step": 206
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001700198303616944,
      "loss": 1.1552,
      "step": 207
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016971065828817424,
      "loss": 1.1541,
      "step": 208
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016940018445912272,
      "loss": 1.228,
      "step": 209
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016908841467223336,
      "loss": 1.3562,
      "step": 210
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016877535474939988,
      "loss": 1.2066,
      "step": 211
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016846101053660762,
      "loss": 1.2524,
      "step": 212
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001681453879038243,
      "loss": 1.2474,
      "step": 213
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016782849274489054,
      "loss": 1.4695,
      "step": 214
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016751033097740976,
      "loss": 1.115,
      "step": 215
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016719090854263753,
      "loss": 1.0784,
      "step": 216
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001668702314053708,
      "loss": 1.2242,
      "step": 217
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016654830555383647,
      "loss": 1.2211,
      "step": 218
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016622513699957948,
      "loss": 1.3118,
      "step": 219
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016590073177735065,
      "loss": 1.2726,
      "step": 220
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016557509594499403,
      "loss": 1.1403,
      "step": 221
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016524823558333363,
      "loss": 1.3207,
      "step": 222
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016492015679605993,
      "loss": 1.1014,
      "step": 223
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016459086570961594,
      "loss": 1.2223,
      "step": 224
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016426036847308286,
      "loss": 1.1968,
      "step": 225
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016392867125806504,
      "loss": 1.1946,
      "step": 226
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016359578025857495,
      "loss": 1.227,
      "step": 227
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016326170169091733,
      "loss": 1.3381,
      "step": 228
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016292644179357336,
      "loss": 1.2175,
      "step": 229
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016259000682708385,
      "loss": 1.2369,
      "step": 230
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016225240307393257,
      "loss": 1.443,
      "step": 231
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016191363683842883,
      "loss": 1.2366,
      "step": 232
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001615737144465898,
      "loss": 1.1747,
      "step": 233
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016123264224602245,
      "loss": 1.1084,
      "step": 234
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00016089042660580468,
      "loss": 1.142,
      "step": 235
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001605470739163669,
      "loss": 1.0347,
      "step": 236
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00016020259058937227,
      "loss": 1.2157,
      "step": 237
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015985698305759713,
      "loss": 1.1908,
      "step": 238
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015951025777481096,
      "loss": 1.3981,
      "step": 239
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001591624212156558,
      "loss": 1.1152,
      "step": 240
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015881347987552517,
      "loss": 1.3025,
      "step": 241
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015846344027044306,
      "loss": 1.1785,
      "step": 242
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015811230893694213,
      "loss": 1.232,
      "step": 243
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015776009243194158,
      "loss": 1.2228,
      "step": 244
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001574067973326248,
      "loss": 1.2446,
      "step": 245
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015705243023631652,
      "loss": 1.0289,
      "step": 246
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015669699776035958,
      "loss": 1.193,
      "step": 247
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015634050654199147,
      "loss": 1.0522,
      "step": 248
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015598296323822024,
      "loss": 1.0648,
      "step": 249
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001556243745257003,
      "loss": 1.3198,
      "step": 250
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015526474710060768,
      "loss": 1.2633,
      "step": 251
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015490408767851506,
      "loss": 1.2146,
      "step": 252
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015454240299426627,
      "loss": 1.005,
      "step": 253
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015417969980185053,
      "loss": 1.1544,
      "step": 254
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001538159848742765,
      "loss": 1.114,
      "step": 255
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015345126500344554,
      "loss": 1.0793,
      "step": 256
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001530855470000251,
      "loss": 1.2889,
      "step": 257
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015271883769332143,
      "loss": 1.2251,
      "step": 258
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015235114393115202,
      "loss": 1.1177,
      "step": 259
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015198247257971787,
      "loss": 1.2651,
      "step": 260
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015161283052347516,
      "loss": 0.9811,
      "step": 261
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015124222466500665,
      "loss": 1.28,
      "step": 262
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015087066192489288,
      "loss": 1.058,
      "step": 263
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015049814924158298,
      "loss": 0.8838,
      "step": 264
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015012469357126494,
      "loss": 1.1265,
      "step": 265
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014975030188773585,
      "loss": 1.4656,
      "step": 266
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014937498118227155,
      "loss": 1.3269,
      "step": 267
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014899873846349626,
      "loss": 1.1389,
      "step": 268
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001486215807572515,
      "loss": 1.0299,
      "step": 269
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014824351510646507,
      "loss": 1.1693,
      "step": 270
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014786454857101939,
      "loss": 1.2748,
      "step": 271
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014748468822761975,
      "loss": 1.2396,
      "step": 272
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014710394116966205,
      "loss": 0.9683,
      "step": 273
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014672231450710066,
      "loss": 1.1646,
      "step": 274
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014633981536631512,
      "loss": 1.1627,
      "step": 275
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014595645088997757,
      "loss": 1.1887,
      "step": 276
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014557222823691912,
      "loss": 1.2117,
      "step": 277
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001451871545819961,
      "loss": 1.1973,
      "step": 278
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014480123711595636,
      "loss": 1.2492,
      "step": 279
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014441448304530467,
      "loss": 1.088,
      "step": 280
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014402689959216845,
      "loss": 1.3454,
      "step": 281
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014363849399416255,
      "loss": 1.4685,
      "step": 282
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001432492735042545,
      "loss": 1.2552,
      "step": 283
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014285924539062878,
      "loss": 1.2045,
      "step": 284
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001424684169365512,
      "loss": 1.2046,
      "step": 285
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001420767954402329,
      "loss": 1.315,
      "step": 286
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.000141684388214694,
      "loss": 1.349,
      "step": 287
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001412912025876272,
      "loss": 1.3101,
      "step": 288
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001408972459012606,
      "loss": 1.0353,
      "step": 289
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00014050252551222115,
      "loss": 1.1797,
      "step": 290
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001401070487913967,
      "loss": 1.1902,
      "step": 291
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013971082312379864,
      "loss": 1.3881,
      "step": 292
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013931385590842412,
      "loss": 1.2216,
      "step": 293
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001389161545581175,
      "loss": 1.1883,
      "step": 294
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013851772649943237,
      "loss": 1.3729,
      "step": 295
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013811857917249253,
      "loss": 1.1422,
      "step": 296
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013771872003085316,
      "loss": 1.1766,
      "step": 297
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013731815654136168,
      "loss": 1.2579,
      "step": 298
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013691689618401835,
      "loss": 1.1001,
      "step": 299
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001365149464518364,
      "loss": 1.1681,
      "step": 300
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013611231485070231,
      "loss": 1.1191,
      "step": 301
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013570900889923565,
      "loss": 1.2803,
      "step": 302
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013530503612864847,
      "loss": 1.1689,
      "step": 303
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001349004040826048,
      "loss": 1.1942,
      "step": 304
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013449512031707986,
      "loss": 1.6546,
      "step": 305
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013408919240021888,
      "loss": 1.0284,
      "step": 306
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013368262791219567,
      "loss": 1.0765,
      "step": 307
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013327543444507134,
      "loss": 1.3107,
      "step": 308
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013286761960265214,
      "loss": 1.2215,
      "step": 309
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013245919100034794,
      "loss": 1.0344,
      "step": 310
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013205015626502957,
      "loss": 1.0257,
      "step": 311
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013164052303488673,
      "loss": 1.0787,
      "step": 312
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013123029895928515,
      "loss": 1.2161,
      "step": 313
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00013081949169862396,
      "loss": 1.0499,
      "step": 314
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001304081089241923,
      "loss": 1.1542,
      "step": 315
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012999615831802647,
      "loss": 1.3226,
      "step": 316
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012958364757276614,
      "loss": 1.2494,
      "step": 317
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012917058439151102,
      "loss": 1.009,
      "step": 318
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012875697648767663,
      "loss": 1.0185,
      "step": 319
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012834283158485063,
      "loss": 1.1762,
      "step": 320
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012792815741664837,
      "loss": 1.3182,
      "step": 321
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012751296172656862,
      "loss": 1.0991,
      "step": 322
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012709725226784873,
      "loss": 0.9753,
      "step": 323
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012668103680332012,
      "loss": 1.4911,
      "step": 324
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001262643231052632,
      "loss": 1.0702,
      "step": 325
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012584711895526226,
      "loss": 1.166,
      "step": 326
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001254294321440601,
      "loss": 1.1387,
      "step": 327
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001250112704714126,
      "loss": 1.12,
      "step": 328
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012459264174594304,
      "loss": 1.2133,
      "step": 329
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001241735537849963,
      "loss": 1.2153,
      "step": 330
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012375401441449294,
      "loss": 1.2934,
      "step": 331
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.000123334031468783,
      "loss": 1.0571,
      "step": 332
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001229136127904996,
      "loss": 1.2117,
      "step": 333
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012249276623041267,
      "loss": 1.1282,
      "step": 334
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012207149964728236,
      "loss": 1.3015,
      "step": 335
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012164982090771202,
      "loss": 1.3017,
      "step": 336
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012122773788600163,
      "loss": 1.3005,
      "step": 337
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012080525846400055,
      "loss": 1.0432,
      "step": 338
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012038239053096038,
      "loss": 1.2335,
      "step": 339
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011995914198338776,
      "loss": 1.0483,
      "step": 340
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011953552072489666,
      "loss": 1.2439,
      "step": 341
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011911153466606104,
      "loss": 1.1537,
      "step": 342
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011868719172426703,
      "loss": 1.2969,
      "step": 343
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011826249982356501,
      "loss": 1.0627,
      "step": 344
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011783746689452177,
      "loss": 1.2375,
      "step": 345
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001174121008740724,
      "loss": 1.1943,
      "step": 346
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011698640970537193,
      "loss": 1.2505,
      "step": 347
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001165604013376472,
      "loss": 1.1273,
      "step": 348
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011613408372604825,
      "loss": 1.2728,
      "step": 349
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011570746483149997,
      "loss": 1.08,
      "step": 350
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011528055262055317,
      "loss": 1.2419,
      "step": 351
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.000114853355065236,
      "loss": 1.0556,
      "step": 352
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011442588014290512,
      "loss": 1.1469,
      "step": 353
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001139981358360966,
      "loss": 1.1669,
      "step": 354
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011357013013237689,
      "loss": 1.0307,
      "step": 355
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011314187102419374,
      "loss": 1.1989,
      "step": 356
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011271336650872685,
      "loss": 1.2265,
      "step": 357
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011228462458773865,
      "loss": 1.1262,
      "step": 358
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011185565326742473,
      "loss": 1.0212,
      "step": 359
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011142646055826442,
      "loss": 1.3271,
      "step": 360
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011099705447487128,
      "loss": 1.0989,
      "step": 361
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011056744303584321,
      "loss": 1.0225,
      "step": 362
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011013763426361303,
      "loss": 1.2502,
      "step": 363
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001097076361842984,
      "loss": 1.1363,
      "step": 364
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010927745682755201,
      "loss": 1.1234,
      "step": 365
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001088471042264118,
      "loss": 1.1054,
      "step": 366
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010841658641715065,
      "loss": 1.1446,
      "step": 367
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001079859114391266,
      "loss": 1.0292,
      "step": 368
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010755508733463265,
      "loss": 1.2314,
      "step": 369
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010712412214874639,
      "loss": 1.1457,
      "step": 370
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010669302392918005,
      "loss": 1.2095,
      "step": 371
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001062618007261301,
      "loss": 1.1903,
      "step": 372
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010583046059212678,
      "loss": 1.1705,
      "step": 373
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010539901158188398,
      "loss": 1.0966,
      "step": 374
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010496746175214868,
      "loss": 1.1144,
      "step": 375
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010453581916155059,
      "loss": 1.14,
      "step": 376
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010410409187045145,
      "loss": 1.1596,
      "step": 377
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010367228794079482,
      "loss": 1.3328,
      "step": 378
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010324041543595535,
      "loss": 1.1764,
      "step": 379
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010280848242058819,
      "loss": 1.1665,
      "step": 380
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001023764969604785,
      "loss": 1.0002,
      "step": 381
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010194446712239076,
      "loss": 1.1748,
      "step": 382
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010151240097391819,
      "loss": 1.1904,
      "step": 383
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010108030658333192,
      "loss": 1.2239,
      "step": 384
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010064819201943066,
      "loss": 1.0239,
      "step": 385
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010021606535138965,
      "loss": 1.2411,
      "step": 386
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.978393464861035e-05,
      "loss": 1.1617,
      "step": 387
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.935180798056935e-05,
      "loss": 1.1307,
      "step": 388
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.891969341666809e-05,
      "loss": 1.1023,
      "step": 389
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.848759902608186e-05,
      "loss": 1.0405,
      "step": 390
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.805553287760922e-05,
      "loss": 1.203,
      "step": 391
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.76235030395215e-05,
      "loss": 1.3004,
      "step": 392
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.719151757941184e-05,
      "loss": 1.026,
      "step": 393
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.675958456404467e-05,
      "loss": 1.2303,
      "step": 394
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.632771205920519e-05,
      "loss": 1.0618,
      "step": 395
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.589590812954857e-05,
      "loss": 1.0282,
      "step": 396
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.546418083844943e-05,
      "loss": 1.3016,
      "step": 397
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.503253824785133e-05,
      "loss": 1.2357,
      "step": 398
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.460098841811601e-05,
      "loss": 1.0257,
      "step": 399
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.416953940787324e-05,
      "loss": 1.4958,
      "step": 400
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.373819927386995e-05,
      "loss": 1.1874,
      "step": 401
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.330697607081994e-05,
      "loss": 1.0308,
      "step": 402
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.287587785125364e-05,
      "loss": 1.2861,
      "step": 403
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.24449126653674e-05,
      "loss": 1.2222,
      "step": 404
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.20140885608734e-05,
      "loss": 0.9737,
      "step": 405
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.158341358284939e-05,
      "loss": 1.0326,
      "step": 406
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.115289577358825e-05,
      "loss": 1.1184,
      "step": 407
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.072254317244801e-05,
      "loss": 1.2239,
      "step": 408
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.029236381570161e-05,
      "loss": 1.0769,
      "step": 409
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.986236573638696e-05,
      "loss": 1.1572,
      "step": 410
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.94325569641568e-05,
      "loss": 1.3555,
      "step": 411
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.900294552512877e-05,
      "loss": 1.1645,
      "step": 412
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.857353944173559e-05,
      "loss": 0.9806,
      "step": 413
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.81443467325753e-05,
      "loss": 1.1617,
      "step": 414
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.771537541226139e-05,
      "loss": 1.2285,
      "step": 415
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.728663349127314e-05,
      "loss": 1.0941,
      "step": 416
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.685812897580629e-05,
      "loss": 1.0698,
      "step": 417
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.642986986762315e-05,
      "loss": 0.9959,
      "step": 418
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.600186416390342e-05,
      "loss": 0.9897,
      "step": 419
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.55741198570949e-05,
      "loss": 1.0812,
      "step": 420
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.514664493476401e-05,
      "loss": 1.1732,
      "step": 421
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.471944737944686e-05,
      "loss": 1.1076,
      "step": 422
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.429253516850005e-05,
      "loss": 1.1697,
      "step": 423
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.386591627395173e-05,
      "loss": 1.1698,
      "step": 424
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.343959866235283e-05,
      "loss": 1.0579,
      "step": 425
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.301359029462809e-05,
      "loss": 1.1315,
      "step": 426
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.25878991259276e-05,
      "loss": 1.2361,
      "step": 427
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.216253310547824e-05,
      "loss": 1.0225,
      "step": 428
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.173750017643504e-05,
      "loss": 0.9499,
      "step": 429
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.1312808275733e-05,
      "loss": 1.168,
      "step": 430
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.088846533393899e-05,
      "loss": 1.2618,
      "step": 431
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.046447927510335e-05,
      "loss": 1.0638,
      "step": 432
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.004085801661227e-05,
      "loss": 1.0386,
      "step": 433
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.961760946903963e-05,
      "loss": 0.9807,
      "step": 434
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.919474153599949e-05,
      "loss": 1.0623,
      "step": 435
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.877226211399839e-05,
      "loss": 1.3777,
      "step": 436
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.835017909228802e-05,
      "loss": 1.0209,
      "step": 437
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.792850035271768e-05,
      "loss": 1.1633,
      "step": 438
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.750723376958733e-05,
      "loss": 1.2194,
      "step": 439
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.708638720950044e-05,
      "loss": 1.1162,
      "step": 440
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.666596853121702e-05,
      "loss": 1.1514,
      "step": 441
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.624598558550706e-05,
      "loss": 1.2077,
      "step": 442
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.582644621500368e-05,
      "loss": 1.022,
      "step": 443
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.540735825405699e-05,
      "loss": 1.1484,
      "step": 444
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.498872952858744e-05,
      "loss": 1.3568,
      "step": 445
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.45705678559399e-05,
      "loss": 1.371,
      "step": 446
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.415288104473774e-05,
      "loss": 1.1064,
      "step": 447
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.373567689473683e-05,
      "loss": 1.0975,
      "step": 448
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.33189631966799e-05,
      "loss": 1.1722,
      "step": 449
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.290274773215132e-05,
      "loss": 1.0057,
      "step": 450
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.248703827343142e-05,
      "loss": 1.1114,
      "step": 451
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.207184258335162e-05,
      "loss": 1.1438,
      "step": 452
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.165716841514939e-05,
      "loss": 0.8642,
      "step": 453
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.124302351232336e-05,
      "loss": 1.1709,
      "step": 454
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.0829415608489e-05,
      "loss": 1.1788,
      "step": 455
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.041635242723385e-05,
      "loss": 1.172,
      "step": 456
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.000384168197354e-05,
      "loss": 1.0772,
      "step": 457
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.95918910758077e-05,
      "loss": 1.1322,
      "step": 458
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.918050830137609e-05,
      "loss": 1.0205,
      "step": 459
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.876970104071482e-05,
      "loss": 1.0369,
      "step": 460
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.83594769651133e-05,
      "loss": 1.1918,
      "step": 461
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.794984373497048e-05,
      "loss": 1.3306,
      "step": 462
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.754080899965208e-05,
      "loss": 1.0853,
      "step": 463
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.713238039734788e-05,
      "loss": 1.0349,
      "step": 464
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.67245655549287e-05,
      "loss": 1.2025,
      "step": 465
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.631737208780433e-05,
      "loss": 1.219,
      "step": 466
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.591080759978113e-05,
      "loss": 1.1701,
      "step": 467
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.550487968292012e-05,
      "loss": 1.0878,
      "step": 468
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.509959591739522e-05,
      "loss": 0.983,
      "step": 469
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.469496387135158e-05,
      "loss": 0.9932,
      "step": 470
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.429099110076435e-05,
      "loss": 1.3622,
      "step": 471
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.388768514929768e-05,
      "loss": 1.1379,
      "step": 472
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.348505354816364e-05,
      "loss": 1.1296,
      "step": 473
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.308310381598168e-05,
      "loss": 0.87,
      "step": 474
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.268184345863835e-05,
      "loss": 1.1147,
      "step": 475
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.228127996914686e-05,
      "loss": 1.034,
      "step": 476
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.18814208275075e-05,
      "loss": 1.1915,
      "step": 477
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.148227350056763e-05,
      "loss": 1.113,
      "step": 478
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.10838454418825e-05,
      "loss": 1.3938,
      "step": 479
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.068614409157591e-05,
      "loss": 1.3238,
      "step": 480
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.028917687620138e-05,
      "loss": 0.9361,
      "step": 481
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.989295120860334e-05,
      "loss": 1.0367,
      "step": 482
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.949747448777889e-05,
      "loss": 1.1468,
      "step": 483
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.9102754098739424e-05,
      "loss": 0.9248,
      "step": 484
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.870879741237285e-05,
      "loss": 1.078,
      "step": 485
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.831561178530602e-05,
      "loss": 0.8219,
      "step": 486
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.792320455976714e-05,
      "loss": 1.014,
      "step": 487
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.7531583063448816e-05,
      "loss": 0.9519,
      "step": 488
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.714075460937125e-05,
      "loss": 1.1882,
      "step": 489
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.675072649574551e-05,
      "loss": 1.0922,
      "step": 490
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6361506005837475e-05,
      "loss": 0.9829,
      "step": 491
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.597310040783161e-05,
      "loss": 1.2343,
      "step": 492
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.5585516954695316e-05,
      "loss": 0.9906,
      "step": 493
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.5198762884043666e-05,
      "loss": 1.1951,
      "step": 494
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.481284541800391e-05,
      "loss": 1.1001,
      "step": 495
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.442777176308089e-05,
      "loss": 0.9636,
      "step": 496
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.404354911002243e-05,
      "loss": 1.2158,
      "step": 497
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.36601846336849e-05,
      "loss": 1.0944,
      "step": 498
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.327768549289934e-05,
      "loss": 1.1395,
      "step": 499
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.289605883033792e-05,
      "loss": 1.0332,
      "step": 500
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.251531177238029e-05,
      "loss": 0.9977,
      "step": 501
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.213545142898061e-05,
      "loss": 1.2525,
      "step": 502
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.175648489353493e-05,
      "loss": 1.3495,
      "step": 503
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.137841924274851e-05,
      "loss": 0.9494,
      "step": 504
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1001261536503787e-05,
      "loss": 1.0448,
      "step": 505
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.06250188177285e-05,
      "loss": 1.1775,
      "step": 506
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.024969811226419e-05,
      "loss": 0.9847,
      "step": 507
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9875306428735094e-05,
      "loss": 1.1366,
      "step": 508
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9501850758417056e-05,
      "loss": 1.1707,
      "step": 509
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.912933807510713e-05,
      "loss": 1.3234,
      "step": 510
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.875777533499339e-05,
      "loss": 1.1704,
      "step": 511
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.838716947652485e-05,
      "loss": 0.9302,
      "step": 512
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8017527420282135e-05,
      "loss": 1.066,
      "step": 513
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7648856068848e-05,
      "loss": 0.9668,
      "step": 514
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.7281162306678585e-05,
      "loss": 1.212,
      "step": 515
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.691445299997491e-05,
      "loss": 1.1384,
      "step": 516
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.6548734996554486e-05,
      "loss": 1.0717,
      "step": 517
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.618401512572351e-05,
      "loss": 1.1552,
      "step": 518
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.582030019814948e-05,
      "loss": 0.9568,
      "step": 519
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.545759700573378e-05,
      "loss": 1.1076,
      "step": 520
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.509591232148495e-05,
      "loss": 1.225,
      "step": 521
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.473525289939233e-05,
      "loss": 0.9351,
      "step": 522
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.437562547429971e-05,
      "loss": 0.8681,
      "step": 523
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.4017036761779787e-05,
      "loss": 1.1195,
      "step": 524
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.365949345800856e-05,
      "loss": 1.1276,
      "step": 525
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.330300223964042e-05,
      "loss": 1.1984,
      "step": 526
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.2947569763683506e-05,
      "loss": 1.0645,
      "step": 527
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.259320266737522e-05,
      "loss": 1.2742,
      "step": 528
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.223990756805841e-05,
      "loss": 1.128,
      "step": 529
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.188769106305787e-05,
      "loss": 1.0449,
      "step": 530
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.1536559729556944e-05,
      "loss": 1.0549,
      "step": 531
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.118652012447486e-05,
      "loss": 1.0476,
      "step": 532
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.083757878434422e-05,
      "loss": 1.2761,
      "step": 533
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.048974222518904e-05,
      "loss": 1.1075,
      "step": 534
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.01430169424029e-05,
      "loss": 1.1601,
      "step": 535
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.9797409410627794e-05,
      "loss": 1.1012,
      "step": 536
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.945292608363313e-05,
      "loss": 1.1574,
      "step": 537
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.910957339419533e-05,
      "loss": 1.0068,
      "step": 538
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.8767357753977596e-05,
      "loss": 1.1855,
      "step": 539
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.842628555341018e-05,
      "loss": 1.1743,
      "step": 540
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.808636316157119e-05,
      "loss": 1.1359,
      "step": 541
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7747596926067484e-05,
      "loss": 0.9914,
      "step": 542
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.740999317291618e-05,
      "loss": 1.1649,
      "step": 543
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.7073558206426675e-05,
      "loss": 0.9311,
      "step": 544
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.673829830908266e-05,
      "loss": 1.0966,
      "step": 545
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.640421974142508e-05,
      "loss": 1.3163,
      "step": 546
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.607132874193499e-05,
      "loss": 1.06,
      "step": 547
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.573963152691715e-05,
      "loss": 1.213,
      "step": 548
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.540913429038407e-05,
      "loss": 1.2059,
      "step": 549
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.507984320394012e-05,
      "loss": 1.0737,
      "step": 550
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.47517644166664e-05,
      "loss": 1.163,
      "step": 551
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.442490405500598e-05,
      "loss": 0.9526,
      "step": 552
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.409926822264937e-05,
      "loss": 1.2319,
      "step": 553
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.377486300042054e-05,
      "loss": 1.1492,
      "step": 554
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.3451694446163553e-05,
      "loss": 1.0427,
      "step": 555
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.3129768594629186e-05,
      "loss": 0.9605,
      "step": 556
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.280909145736246e-05,
      "loss": 1.0737,
      "step": 557
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2489669022590244e-05,
      "loss": 0.9318,
      "step": 558
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.217150725510946e-05,
      "loss": 1.1213,
      "step": 559
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.185461209617571e-05,
      "loss": 0.8458,
      "step": 560
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.153898946339241e-05,
      "loss": 1.1041,
      "step": 561
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.122464525060013e-05,
      "loss": 1.0573,
      "step": 562
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.091158532776666e-05,
      "loss": 1.0406,
      "step": 563
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.059981554087732e-05,
      "loss": 1.2047,
      "step": 564
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0289341711825815e-05,
      "loss": 1.1553,
      "step": 565
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.998016963830562e-05,
      "loss": 0.8904,
      "step": 566
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9672305093701503e-05,
      "loss": 1.1387,
      "step": 567
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9365753826981947e-05,
      "loss": 1.1298,
      "step": 568
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9060521562591624e-05,
      "loss": 1.1261,
      "step": 569
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.875661400034452e-05,
      "loss": 1.0706,
      "step": 570
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8454036815317642e-05,
      "loss": 1.1102,
      "step": 571
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.815279565774488e-05,
      "loss": 0.9629,
      "step": 572
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.78528961529115e-05,
      "loss": 1.1748,
      "step": 573
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7554343901049294e-05,
      "loss": 1.0437,
      "step": 574
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.7257144477231756e-05,
      "loss": 1.156,
      "step": 575
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6961303431270068e-05,
      "loss": 1.0216,
      "step": 576
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.666682628760958e-05,
      "loss": 1.0136,
      "step": 577
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6373718545226445e-05,
      "loss": 1.2247,
      "step": 578
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.608198567752512e-05,
      "loss": 1.1009,
      "step": 579
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5791633132236025e-05,
      "loss": 1.0293,
      "step": 580
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.550266633131382e-05,
      "loss": 1.2516,
      "step": 581
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.5215090670836306e-05,
      "loss": 1.2131,
      "step": 582
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4928911520903465e-05,
      "loss": 0.9738,
      "step": 583
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4644134225537264e-05,
      "loss": 1.0539,
      "step": 584
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4360764102581945e-05,
      "loss": 1.0488,
      "step": 585
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4078806443604596e-05,
      "loss": 1.2307,
      "step": 586
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3798266513796317e-05,
      "loss": 1.0795,
      "step": 587
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.351914955187412e-05,
      "loss": 0.9543,
      "step": 588
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.3241460769982814e-05,
      "loss": 1.0224,
      "step": 589
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2965205353597863e-05,
      "loss": 1.2327,
      "step": 590
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2690388461428468e-05,
      "loss": 1.0083,
      "step": 591
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.241701522532136e-05,
      "loss": 1.0704,
      "step": 592
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2145090750164777e-05,
      "loss": 1.1573,
      "step": 593
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1874620113793286e-05,
      "loss": 0.9994,
      "step": 594
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.160560836689286e-05,
      "loss": 1.0597,
      "step": 595
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1338060532906736e-05,
      "loss": 1.2347,
      "step": 596
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.107198160794136e-05,
      "loss": 0.9029,
      "step": 597
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0807376560673254e-05,
      "loss": 1.087,
      "step": 598
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0544250332256276e-05,
      "loss": 1.0703,
      "step": 599
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.028260783622914e-05,
      "loss": 0.9767,
      "step": 600
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0022453958423938e-05,
      "loss": 1.0907,
      "step": 601
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9763793556874655e-05,
      "loss": 1.0953,
      "step": 602
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9506631461726566e-05,
      "loss": 0.8641,
      "step": 603
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.925097247514609e-05,
      "loss": 1.2929,
      "step": 604
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8996821371231022e-05,
      "loss": 0.9507,
      "step": 605
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8744182895921368e-05,
      "loss": 1.3895,
      "step": 606
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.849306176691088e-05,
      "loss": 1.1314,
      "step": 607
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8243462673558755e-05,
      "loss": 1.1839,
      "step": 608
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.799539027680216e-05,
      "loss": 1.1373,
      "step": 609
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7748849209069286e-05,
      "loss": 1.2087,
      "step": 610
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7503844074192653e-05,
      "loss": 1.0104,
      "step": 611
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7260379447323328e-05,
      "loss": 1.1559,
      "step": 612
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.7018459874845326e-05,
      "loss": 1.1308,
      "step": 613
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.677808987429079e-05,
      "loss": 1.0858,
      "step": 614
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6539273934255727e-05,
      "loss": 1.0542,
      "step": 615
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6302016514315998e-05,
      "loss": 1.0631,
      "step": 616
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6066322044944126e-05,
      "loss": 1.0598,
      "step": 617
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5832194927426668e-05,
      "loss": 1.2746,
      "step": 618
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5599639533781853e-05,
      "loss": 1.1003,
      "step": 619
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5368660206678033e-05,
      "loss": 1.2666,
      "step": 620
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5139261259352589e-05,
      "loss": 1.2522,
      "step": 621
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4911446975531328e-05,
      "loss": 0.9772,
      "step": 622
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4685221609348632e-05,
      "loss": 1.0075,
      "step": 623
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4460589385267842e-05,
      "loss": 1.005,
      "step": 624
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4237554498002425e-05,
      "loss": 1.1105,
      "step": 625
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4016121112437786e-05,
      "loss": 1.3069,
      "step": 626
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.379629336355326e-05,
      "loss": 0.9892,
      "step": 627
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3578075356345044e-05,
      "loss": 1.0631,
      "step": 628
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3361471165749562e-05,
      "loss": 1.0555,
      "step": 629
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3146484836567264e-05,
      "loss": 1.1469,
      "step": 630
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2933120383387132e-05,
      "loss": 1.1518,
      "step": 631
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2721381790511832e-05,
      "loss": 1.1602,
      "step": 632
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2511273011883096e-05,
      "loss": 0.9754,
      "step": 633
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2302797971008085e-05,
      "loss": 1.0898,
      "step": 634
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2095960560886e-05,
      "loss": 1.1445,
      "step": 635
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1890764643935393e-05,
      "loss": 1.2429,
      "step": 636
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.168721405192218e-05,
      "loss": 1.1659,
      "step": 637
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1485312585887886e-05,
      "loss": 0.8704,
      "step": 638
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1285064016078784e-05,
      "loss": 1.1806,
      "step": 639
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1086472081875487e-05,
      "loss": 1.1452,
      "step": 640
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0889540491723105e-05,
      "loss": 0.9456,
      "step": 641
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0694272923061932e-05,
      "loss": 1.029,
      "step": 642
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0500673022258922e-05,
      "loss": 1.055,
      "step": 643
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.030874440453944e-05,
      "loss": 1.0806,
      "step": 644
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0118490653919855e-05,
      "loss": 0.9064,
      "step": 645
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.929915323140571e-06,
      "loss": 0.7556,
      "step": 646
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.743021933599695e-06,
      "loss": 1.1699,
      "step": 647
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.557813975287267e-06,
      "loss": 1.217,
      "step": 648
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.374294906720082e-06,
      "loss": 1.0701,
      "step": 649
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.192468154877187e-06,
      "loss": 1.1156,
      "step": 650
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.012337115135772e-06,
      "loss": 1.1668,
      "step": 651
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.833905151207833e-06,
      "loss": 1.0837,
      "step": 652
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.657175595077316e-06,
      "loss": 0.9721,
      "step": 653
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.482151746937982e-06,
      "loss": 1.0993,
      "step": 654
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.308836875131665e-06,
      "loss": 1.0196,
      "step": 655
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.137234216087353e-06,
      "loss": 0.9373,
      "step": 656
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.967346974260625e-06,
      "loss": 0.906,
      "step": 657
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.79917832207394e-06,
      "loss": 1.1333,
      "step": 658
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.63273139985733e-06,
      "loss": 1.0379,
      "step": 659
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.468009315789748e-06,
      "loss": 1.2477,
      "step": 660
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.305015145841054e-06,
      "loss": 0.9208,
      "step": 661
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.143751933714582e-06,
      "loss": 1.15,
      "step": 662
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.9842226907902766e-06,
      "loss": 1.2247,
      "step": 663
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.8264303960684506e-06,
      "loss": 1.0735,
      "step": 664
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.67037799611423e-06,
      "loss": 0.8792,
      "step": 665
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.51606840500244e-06,
      "loss": 1.0715,
      "step": 666
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.3635045042632066e-06,
      "loss": 0.9893,
      "step": 667
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.212689142828232e-06,
      "loss": 1.2205,
      "step": 668
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.063625136977447e-06,
      "loss": 1.2093,
      "step": 669
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.916315270286588e-06,
      "loss": 1.0735,
      "step": 670
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.770762293575083e-06,
      "loss": 1.0884,
      "step": 671
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.626968924854714e-06,
      "loss": 1.064,
      "step": 672
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.4849378492789374e-06,
      "loss": 1.0008,
      "step": 673
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.344671719092664e-06,
      "loss": 1.2432,
      "step": 674
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.206173153582705e-06,
      "loss": 0.9597,
      "step": 675
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.069444739029006e-06,
      "loss": 0.9729,
      "step": 676
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.934489028656164e-06,
      "loss": 0.937,
      "step": 677
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.801308542585892e-06,
      "loss": 0.999,
      "step": 678
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.669905767789884e-06,
      "loss": 0.9253,
      "step": 679
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.540283158043391e-06,
      "loss": 1.0677,
      "step": 680
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.41244313387944e-06,
      "loss": 1.1795,
      "step": 681
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.286388082543569e-06,
      "loss": 1.0223,
      "step": 682
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.162120357949284e-06,
      "loss": 1.0694,
      "step": 683
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.0396422806341036e-06,
      "loss": 1.0328,
      "step": 684
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.918956137716235e-06,
      "loss": 0.974,
      "step": 685
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.8000641828518036e-06,
      "loss": 1.0735,
      "step": 686
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.682968636192863e-06,
      "loss": 1.0635,
      "step": 687
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.567671684345875e-06,
      "loss": 1.0855,
      "step": 688
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.454175480330857e-06,
      "loss": 1.2279,
      "step": 689
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.342482143541281e-06,
      "loss": 0.8907,
      "step": 690
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.23259375970435e-06,
      "loss": 1.1258,
      "step": 691
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.124512380842204e-06,
      "loss": 0.9176,
      "step": 692
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.018240025233465e-06,
      "loss": 1.2405,
      "step": 693
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.9137786773756117e-06,
      "loss": 1.0521,
      "step": 694
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8111302879479717e-06,
      "loss": 0.9603,
      "step": 695
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.710296773775167e-06,
      "loss": 1.0522,
      "step": 696
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.6112800177914398e-06,
      "loss": 1.2222,
      "step": 697
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.514081869005458e-06,
      "loss": 1.103,
      "step": 698
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.418704142465722e-06,
      "loss": 1.1205,
      "step": 699
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3251486192267578e-06,
      "loss": 0.8992,
      "step": 700
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.233417046315822e-06,
      "loss": 1.046,
      "step": 701
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1435111367002824e-06,
      "loss": 0.9887,
      "step": 702
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.055432569255622e-06,
      "loss": 0.9442,
      "step": 703
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9691829887340864e-06,
      "loss": 0.9405,
      "step": 704
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8847640057339965e-06,
      "loss": 0.9889,
      "step": 705
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.8021771966696189e-06,
      "loss": 1.1377,
      "step": 706
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.721424103741831e-06,
      "loss": 1.0913,
      "step": 707
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6425062349091913e-06,
      "loss": 0.9902,
      "step": 708
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.56542506385986e-06,
      "loss": 1.2601,
      "step": 709
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4901820299840997e-06,
      "loss": 1.0899,
      "step": 710
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4167785383472854e-06,
      "loss": 1.0721,
      "step": 711
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.345215959663837e-06,
      "loss": 0.9274,
      "step": 712
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2754956302714615e-06,
      "loss": 1.061,
      "step": 713
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.2076188521062847e-06,
      "loss": 1.0961,
      "step": 714
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1415868926785256e-06,
      "loss": 1.2141,
      "step": 715
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.0774009850488153e-06,
      "loss": 1.124,
      "step": 716
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0150623278051718e-06,
      "loss": 1.1232,
      "step": 717
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.545720850406504e-07,
      "loss": 1.1324,
      "step": 718
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.959313863315389e-07,
      "loss": 1.0871,
      "step": 719
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.391413267163417e-07,
      "loss": 1.135,
      "step": 720
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.842029666752626e-07,
      "loss": 0.9644,
      "step": 721
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.311173321104647e-07,
      "loss": 1.3016,
      "step": 722
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.798854143268641e-07,
      "loss": 1.2784,
      "step": 723
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.305081700136328e-07,
      "loss": 1.0005,
      "step": 724
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.829865212263474e-07,
      "loss": 1.0055,
      "step": 725
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.373213553697576e-07,
      "loss": 1.0099,
      "step": 726
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.935135251811996e-07,
      "loss": 1.1788,
      "step": 727
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.515638487147311e-07,
      "loss": 1.1793,
      "step": 728
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.114731093257884e-07,
      "loss": 1.136,
      "step": 729
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.732420556565752e-07,
      "loss": 1.0169,
      "step": 730
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.368714016221186e-07,
      "loss": 1.0661,
      "step": 731
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.023618263968797e-07,
      "loss": 1.0488,
      "step": 732
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.697139744021415e-07,
      "loss": 1.1705,
      "step": 733
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.389284552939075e-07,
      "loss": 1.1367,
      "step": 734
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.1000584395155509e-07,
      "loss": 0.8443,
      "step": 735
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.8294668046708873e-07,
      "loss": 0.9826,
      "step": 736
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.577514701350591e-07,
      "loss": 1.1442,
      "step": 737
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3442068344312608e-07,
      "loss": 1.1088,
      "step": 738
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.129547560632771e-07,
      "loss": 0.9073,
      "step": 739
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.33540888436668e-08,
      "loss": 1.1139,
      "step": 740
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.561904780116758e-08,
      "loss": 0.9704,
      "step": 741
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.97499641145416e-08,
      "loss": 0.9565,
      "step": 742
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.574713411816811e-08,
      "loss": 1.0933,
      "step": 743
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.361081929664778e-08,
      "loss": 1.0756,
      "step": 744
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.3341246279806607e-08,
      "loss": 1.0339,
      "step": 745
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.4938606838510448e-08,
      "loss": 1.1196,
      "step": 746
    },
    {
      "epoch": 1.0,
      "learning_rate": 8.403057881067877e-09,
      "loss": 1.0981,
      "step": 747
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.734721450343592e-09,
      "loss": 1.0525,
      "step": 748
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.336847214269639e-10,
      "loss": 1.0861,
      "step": 749
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.1944,
      "step": 750
    },
    {
      "epoch": 1.0,
      "step": 750,
      "total_flos": 2.2873055182821786e+17,
      "train_loss": 1.167799865881602,
      "train_runtime": 10360.645,
      "train_samples_per_second": 1.158,
      "train_steps_per_second": 0.072
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "total_flos": 2.2873055182821786e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}