{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 601,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 0.547,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 0.5148,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-05,
      "loss": 0.5241,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 0.3872,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 0.3484,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 0.2567,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00014,
      "loss": 0.2197,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016,
      "loss": 0.2134,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00018,
      "loss": 0.188,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.2067,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999858715745195,
      "loss": 0.1878,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019999434866973016,
      "loss": 0.1898,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019998728465660105,
      "loss": 0.1904,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001999773953176713,
      "loss": 0.157,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00019996468093238257,
      "loss": 0.1442,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019994914186000328,
      "loss": 0.1884,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019993077853961872,
      "loss": 0.1518,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019990959149011848,
      "loss": 0.1615,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019988558131018186,
      "loss": 0.1421,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019985874867826096,
      "loss": 0.1438,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019982909435256144,
      "loss": 0.1365,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019979661917102115,
      "loss": 0.127,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019976132405128647,
      "loss": 0.145,
      "step": 23
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019972320999068636,
      "loss": 0.1647,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001996822780662041,
      "loss": 0.137,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019963852943444702,
      "loss": 0.1427,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001995919653316137,
      "loss": 0.1156,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000199542587073459,
      "loss": 0.1295,
      "step": 28
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019949039605525703,
      "loss": 0.1465,
      "step": 29
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019943539375176164,
      "loss": 0.1371,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019937758171716468,
      "loss": 0.1276,
      "step": 31
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019931696158505223,
      "loss": 0.1166,
      "step": 32
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019925353506835826,
      "loss": 0.1194,
      "step": 33
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019918730395931649,
      "loss": 0.1146,
      "step": 34
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019911827012940946,
      "loss": 0.1539,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001990464355293158,
      "loss": 1.9511,
      "step": 36
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019897180218885507,
      "loss": 0.1222,
      "step": 37
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019889437221693053,
      "loss": 0.1223,
      "step": 38
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001988141478014693,
      "loss": 0.1353,
      "step": 39
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019873113120936074,
      "loss": 0.1265,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019864532478639234,
      "loss": 0.1288,
      "step": 41
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019855673095718336,
      "loss": 0.128,
      "step": 42
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001984653522251165,
      "loss": 0.1297,
      "step": 43
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019837119117226688,
      "loss": 0.1265,
      "step": 44
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001982742504593294,
      "loss": 0.1269,
      "step": 45
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019817453282554333,
      "loss": 0.1407,
      "step": 46
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019807204108861502,
      "loss": 0.1311,
      "step": 47
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001979667781446381,
      "loss": 0.1312,
      "step": 48
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019785874696801202,
      "loss": 0.1335,
      "step": 49
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019774795061135752,
      "loss": 0.121,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019763439220543084,
      "loss": 0.1268,
      "step": 51
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019751807495903484,
      "loss": 0.1353,
      "step": 52
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019739900215892867,
      "loss": 0.1242,
      "step": 53
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001972771771697347,
      "loss": 0.1048,
      "step": 54
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019715260343384347,
      "loss": 0.1329,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019702528447131646,
      "loss": 0.1197,
      "step": 56
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019689522387978666,
      "loss": 0.1463,
      "step": 57
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019676242533435678,
      "loss": 0.1296,
      "step": 58
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019662689258749554,
      "loss": 0.1243,
      "step": 59
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019648862946893158,
      "loss": 0.1257,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019634763988554522,
      "loss": 0.1348,
      "step": 61
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001962039278212581,
      "loss": 0.1128,
      "step": 62
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019605749733692064,
      "loss": 0.1227,
      "step": 63
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019590835257019714,
      "loss": 0.1329,
      "step": 64
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019575649773544913,
      "loss": 0.1291,
      "step": 65
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019560193712361596,
      "loss": 0.119,
      "step": 66
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019544467510209388,
      "loss": 0.126,
      "step": 67
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019528471611461235,
      "loss": 0.1158,
      "step": 68
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019512206468110863,
      "loss": 0.1309,
      "step": 69
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019495672539760007,
      "loss": 0.1203,
      "step": 70
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019478870293605416,
      "loss": 0.107,
      "step": 71
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001946180020442565,
      "loss": 0.1249,
      "step": 72
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019444462754567682,
      "loss": 0.1163,
      "step": 73
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019426858433933247,
      "loss": 0.1192,
      "step": 74
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019408987739965005,
      "loss": 0.1205,
      "step": 75
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019390851177632497,
      "loss": 0.1205,
      "step": 76
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019372449259417857,
      "loss": 0.1247,
      "step": 77
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001935378250530135,
      "loss": 0.1195,
      "step": 78
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019334851442746664,
      "loss": 0.1131,
      "step": 79
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019315656606686013,
      "loss": 0.1119,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019296198539505013,
      "loss": 0.1137,
      "step": 81
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019276477791027374,
      "loss": 0.1052,
      "step": 82
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019256494918499346,
      "loss": 0.1204,
      "step": 83
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019236250486573978,
      "loss": 0.1158,
      "step": 84
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019215745067295169,
      "loss": 0.1151,
      "step": 85
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001919497924008149,
      "loss": 0.1274,
      "step": 86
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019173953591709828,
      "loss": 0.1229,
      "step": 87
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000191526687162988,
      "loss": 0.1194,
      "step": 88
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001913112521529195,
      "loss": 0.1409,
      "step": 89
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019109323697440782,
      "loss": 0.1274,
      "step": 90
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019087264778787534,
      "loss": 0.1188,
      "step": 91
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019064949082647786,
      "loss": 0.1149,
      "step": 92
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001904237723959283,
      "loss": 0.115,
      "step": 93
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019019549887431877,
      "loss": 0.1297,
      "step": 94
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018996467671194016,
      "loss": 0.1286,
      "step": 95
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018973131243109988,
      "loss": 0.1061,
      "step": 96
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018949541262593762,
      "loss": 0.1189,
      "step": 97
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018925698396223909,
      "loss": 0.1372,
      "step": 98
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001890160331772474,
      "loss": 0.118,
      "step": 99
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018877256707947306,
      "loss": 0.1109,
      "step": 100
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018852659254850126,
      "loss": 0.1142,
      "step": 101
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018827811653479768,
      "loss": 0.1117,
      "step": 102
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018802714605951199,
      "loss": 0.1251,
      "step": 103
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018777368821427953,
      "loss": 0.1153,
      "step": 104
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018751775016102087,
      "loss": 0.1288,
      "step": 105
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018725933913173938,
      "loss": 0.1261,
      "step": 106
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018699846242831706,
      "loss": 0.1349,
      "step": 107
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018673512742230802,
      "loss": 0.1145,
      "step": 108
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018646934155473022,
      "loss": 0.1206,
      "step": 109
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001862011123358554,
      "loss": 0.1169,
      "step": 110
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018593044734499655,
      "loss": 0.1256,
      "step": 111
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018565735423029404,
      "loss": 0.1233,
      "step": 112
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018538184070849924,
      "loss": 0.1252,
      "step": 113
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018510391456475676,
      "loss": 0.1174,
      "step": 114
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018482358365238413,
      "loss": 0.1205,
      "step": 115
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001845408558926502,
      "loss": 0.1298,
      "step": 116
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018425573927455117,
      "loss": 0.1085,
      "step": 117
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001839682418545848,
      "loss": 0.1363,
      "step": 118
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018367837175652284,
      "loss": 0.1228,
      "step": 119
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001833861371711814,
      "loss": 0.1259,
      "step": 120
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018309154635618965,
      "loss": 0.1246,
      "step": 121
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018279460763575637,
      "loss": 0.1288,
      "step": 122
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001824953294004347,
      "loss": 0.1203,
      "step": 123
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018219372010688515,
      "loss": 0.1166,
      "step": 124
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018188978827763652,
      "loss": 0.1377,
      "step": 125
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018158354250084527,
      "loss": 0.1364,
      "step": 126
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018127499143005268,
      "loss": 0.1179,
      "step": 127
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018096414378394028,
      "loss": 0.1308,
      "step": 128
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00018065100834608377,
      "loss": 0.1359,
      "step": 129
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018033559396470454,
      "loss": 0.1253,
      "step": 130
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018001790955241972,
      "loss": 0.1106,
      "step": 131
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001796979640859904,
      "loss": 0.118,
      "step": 132
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.000179375766606068,
      "loss": 0.1361,
      "step": 133
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001790513262169386,
      "loss": 0.1388,
      "step": 134
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00017872465208626598,
      "loss": 0.1448,
      "step": 135
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017839575344483238,
      "loss": 0.111,
      "step": 136
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017806463958627762,
      "loss": 0.115,
      "step": 137
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017773131986683672,
      "loss": 0.1198,
      "step": 138
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017739580370507532,
      "loss": 0.1347,
      "step": 139
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017705810058162353,
      "loss": 0.12,
      "step": 140
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00017671822003890823,
      "loss": 0.1258,
      "step": 141
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017637617168088325,
      "loss": 0.1357,
      "step": 142
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001760319651727581,
      "loss": 0.132,
      "step": 143
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001756856102407247,
      "loss": 0.1134,
      "step": 144
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001753371166716828,
      "loss": 0.1106,
      "step": 145
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00017498649431296322,
      "loss": 0.1133,
      "step": 146
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001746337530720497,
      "loss": 0.1232,
      "step": 147
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017427890291629893,
      "loss": 0.1249,
      "step": 148
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017392195387265887,
      "loss": 0.1172,
      "step": 149
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017356291602738542,
      "loss": 0.1112,
      "step": 150
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001732017995257575,
      "loss": 0.1124,
      "step": 151
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017283861457179022,
      "loss": 0.124,
      "step": 152
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017247337142794678,
      "loss": 0.1116,
      "step": 153
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001721060804148482,
      "loss": 0.1294,
      "step": 154
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001717367519109819,
      "loss": 0.1185,
      "step": 155
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017136539635240837,
      "loss": 0.1383,
      "step": 156
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001709920242324663,
      "loss": 0.1204,
      "step": 157
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00017061664610147604,
      "loss": 0.1293,
      "step": 158
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001702392725664415,
      "loss": 0.1303,
      "step": 159
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016985991429075036,
      "loss": 0.1189,
      "step": 160
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016947858199387294,
      "loss": 0.1431,
      "step": 161
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016909528645105907,
      "loss": 0.1174,
      "step": 162
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016871003849303382,
      "loss": 0.1306,
      "step": 163
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001683228490056913,
      "loss": 0.1086,
      "step": 164
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00016793372892978713,
      "loss": 0.122,
      "step": 165
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016754268926062938,
      "loss": 0.1081,
      "step": 166
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001671497410477676,
      "loss": 0.1184,
      "step": 167
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016675489539468092,
      "loss": 0.1238,
      "step": 168
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001663581634584641,
      "loss": 0.1256,
      "step": 169
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001659595564495124,
      "loss": 0.1242,
      "step": 170
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00016555908563120457,
      "loss": 0.1179,
      "step": 171
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001651567623195849,
      "loss": 0.1173,
      "step": 172
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016475259788304317,
      "loss": 0.1146,
      "step": 173
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016434660374199376,
      "loss": 0.1254,
      "step": 174
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016393879136855248,
      "loss": 0.1263,
      "step": 175
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00016352917228621284,
      "loss": 0.1181,
      "step": 176
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001631177580695202,
      "loss": 0.1213,
      "step": 177
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016270456034374474,
      "loss": 0.1156,
      "step": 178
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016228959078455306,
      "loss": 0.1145,
      "step": 179
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001618728611176781,
      "loss": 0.1385,
      "step": 180
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000161454383118588,
      "loss": 0.1228,
      "step": 181
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016103416861215313,
      "loss": 0.1175,
      "step": 182
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00016061222947231225,
      "loss": 0.1328,
      "step": 183
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001601885776217367,
      "loss": 0.1223,
      "step": 184
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00015976322503149373,
      "loss": 0.1244,
      "step": 185
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00015933618372070805,
      "loss": 0.1356,
      "step": 186
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00015890746575622231,
      "loss": 0.12,
      "step": 187
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00015847708325225618,
      "loss": 0.1254,
      "step": 188
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00015804504837006394,
      "loss": 0.1139,
      "step": 189
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015761137331759084,
      "loss": 0.1251,
      "step": 190
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001571760703491282,
      "loss": 0.1269,
      "step": 191
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015673915176496713,
      "loss": 0.1203,
      "step": 192
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015630062991105098,
      "loss": 0.108,
      "step": 193
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00015586051717862636,
      "loss": 0.1276,
      "step": 194
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001554188260038932,
      "loss": 0.1164,
      "step": 195
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015497556886765316,
      "loss": 0.1212,
      "step": 196
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001545307582949571,
      "loss": 0.1358,
      "step": 197
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015408440685475109,
      "loss": 0.1168,
      "step": 198
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001536365271595212,
      "loss": 0.1237,
      "step": 199
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015318713186493734,
      "loss": 0.136,
      "step": 200
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015273623366949523,
      "loss": 0.1332,
      "step": 201
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001522838453141581,
      "loss": 0.1122,
      "step": 202
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015182997958199617,
      "loss": 0.118,
      "step": 203
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015137464929782586,
      "loss": 0.1277,
      "step": 204
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015091786732784716,
      "loss": 0.1117,
      "step": 205
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015045964657928006,
      "loss": 0.1025,
      "step": 206
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1251,
      "step": 207
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014953894057817188,
      "loss": 0.142,
      "step": 208
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014907648134188304,
      "loss": 0.1322,
      "step": 209
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001486126353587752,
      "loss": 0.1236,
      "step": 210
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014814741573567514,
      "loss": 0.1293,
      "step": 211
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001476808356182245,
      "loss": 0.1157,
      "step": 212
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00014721290819050804,
      "loss": 0.1299,
      "step": 213
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001467436466746814,
      "loss": 0.1052,
      "step": 214
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014627306433059723,
      "loss": 0.1242,
      "step": 215
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014580117445543077,
      "loss": 0.103,
      "step": 216
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014532799038330385,
      "loss": 0.1274,
      "step": 217
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014485352548490826,
      "loss": 0.12,
      "step": 218
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00014437779316712796,
      "loss": 0.1113,
      "step": 219
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014390080687266013,
      "loss": 0.1244,
      "step": 220
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001434225800796354,
      "loss": 0.1111,
      "step": 221
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.000142943126301237,
      "loss": 0.1007,
      "step": 222
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014246245908531882,
      "loss": 0.1175,
      "step": 223
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014198059201402287,
      "loss": 0.1285,
      "step": 224
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00014149753870339507,
      "loss": 0.1523,
      "step": 225
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001410133128030009,
      "loss": 0.1212,
      "step": 226
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014052792799553934,
      "loss": 0.1053,
      "step": 227
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014004139799645668,
      "loss": 0.1356,
      "step": 228
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001395537365535585,
      "loss": 0.1316,
      "step": 229
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00013906495744662157,
      "loss": 0.1316,
      "step": 230
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00013857507448700423,
      "loss": 0.1209,
      "step": 231
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001380841015172563,
      "loss": 0.1191,
      "step": 232
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013759205241072782,
      "loss": 0.1207,
      "step": 233
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013709894107117698,
      "loss": 0.1234,
      "step": 234
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013660478143237746,
      "loss": 0.1269,
      "step": 235
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013610958745772456,
      "loss": 0.1163,
      "step": 236
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00013561337313984054,
      "loss": 0.1369,
      "step": 237
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001351161525001795,
      "loss": 0.1146,
      "step": 238
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013461793958863087,
      "loss": 0.1078,
      "step": 239
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013411874848312272,
      "loss": 0.1238,
      "step": 240
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001336185932892237,
      "loss": 0.1116,
      "step": 241
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013311748813974453,
      "loss": 0.1365,
      "step": 242
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001326154471943388,
      "loss": 0.1286,
      "step": 243
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013211248463910262,
      "loss": 0.1142,
      "step": 244
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.000131608614686174,
      "loss": 0.1158,
      "step": 245
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001311038515733311,
      "loss": 1.5948,
      "step": 246
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013059820956358998,
      "loss": 0.1267,
      "step": 247
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00013009170294480147,
      "loss": 0.1171,
      "step": 248
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001295843460292477,
      "loss": 0.128,
      "step": 249
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001290761531532374,
      "loss": 0.1455,
      "step": 250
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001285671386767009,
      "loss": 0.1207,
      "step": 251
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012805731698278442,
      "loss": 0.1266,
      "step": 252
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012754670247744354,
      "loss": 0.125,
      "step": 253
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001270353095890363,
      "loss": 0.1238,
      "step": 254
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012652315276791528,
      "loss": 0.125,
      "step": 255
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001260102464860195,
      "loss": 0.1201,
      "step": 256
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012549660523646528,
      "loss": 0.1227,
      "step": 257
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012498224353313684,
      "loss": 0.1205,
      "step": 258
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012446717591027624,
      "loss": 0.1327,
      "step": 259
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012395141692207243,
      "loss": 0.1193,
      "step": 260
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00012343498114225038,
      "loss": 0.114,
      "step": 261
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012291788316365888,
      "loss": 0.1143,
      "step": 262
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012240013759785848,
      "loss": 0.1168,
      "step": 263
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012188175907470847,
      "loss": 0.1348,
      "step": 264
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012136276224195348,
      "loss": 0.1153,
      "step": 265
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012084316176480973,
      "loss": 0.1334,
      "step": 266
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00012032297232555039,
      "loss": 0.1024,
      "step": 267
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011980220862309097,
      "loss": 0.1257,
      "step": 268
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011928088537257375,
      "loss": 0.1145,
      "step": 269
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011875901730495215,
      "loss": 0.1288,
      "step": 270
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001182366191665744,
      "loss": 0.127,
      "step": 271
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011771370571876681,
      "loss": 0.118,
      "step": 272
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00011719029173741676,
      "loss": 0.1216,
      "step": 273
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011666639201255506,
      "loss": 0.1261,
      "step": 274
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011614202134793823,
      "loss": 0.1207,
      "step": 275
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011561719456062994,
      "loss": 0.1165,
      "step": 276
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011509192648058249,
      "loss": 0.1293,
      "step": 277
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011456623195021778,
      "loss": 0.1447,
      "step": 278
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00011404012582400779,
      "loss": 2.074,
      "step": 279
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011351362296805485,
      "loss": 0.1065,
      "step": 280
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011298673825967183,
      "loss": 0.1089,
      "step": 281
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011245948658696126,
      "loss": 0.1108,
      "step": 282
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011193188284839517,
      "loss": 0.1295,
      "step": 283
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011140394195239376,
      "loss": 0.1173,
      "step": 284
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011087567881690422,
      "loss": 0.1269,
      "step": 285
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00011034710836897921,
      "loss": 0.1198,
      "step": 286
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010981824554435518,
      "loss": 0.153,
      "step": 287
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010928910528703007,
      "loss": 0.1144,
      "step": 288
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001087597025488413,
      "loss": 0.1291,
      "step": 289
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010823005228904314,
      "loss": 0.1168,
      "step": 290
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00010770016947388407,
      "loss": 0.1037,
      "step": 291
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010717006907618377,
      "loss": 0.1261,
      "step": 292
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001066397660749102,
      "loss": 0.1297,
      "step": 293
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010610927545475624,
      "loss": 0.1124,
      "step": 294
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010557861220571625,
      "loss": 0.1249,
      "step": 295
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001050477913226626,
      "loss": 0.1205,
      "step": 296
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010451682780492189,
      "loss": 0.1174,
      "step": 297
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010398573665585105,
      "loss": 0.1213,
      "step": 298
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010345453288241356,
      "loss": 0.1079,
      "step": 299
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010292323149475527,
      "loss": 0.1022,
      "step": 300
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001023918475057803,
      "loss": 0.1013,
      "step": 301
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010186039593072685,
      "loss": 0.1288,
      "step": 302
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010132889178674283,
      "loss": 0.1187,
      "step": 303
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010079735009246167,
      "loss": 0.1162,
      "step": 304
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010026578586757778,
      "loss": 0.1128,
      "step": 305
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.973421413242225e-05,
      "loss": 0.1187,
      "step": 306
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.920264990753837e-05,
      "loss": 0.1238,
      "step": 307
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.867110821325717e-05,
      "loss": 0.128,
      "step": 308
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.813960406927319e-05,
      "loss": 0.1277,
      "step": 309
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.760815249421973e-05,
      "loss": 0.1131,
      "step": 310
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.707676850524473e-05,
      "loss": 0.116,
      "step": 311
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.654546711758645e-05,
      "loss": 0.1076,
      "step": 312
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.601426334414898e-05,
      "loss": 0.1117,
      "step": 313
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.548317219507815e-05,
      "loss": 0.1418,
      "step": 314
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.495220867733738e-05,
      "loss": 0.1216,
      "step": 315
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.442138779428376e-05,
      "loss": 0.1156,
      "step": 316
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.38907245452438e-05,
      "loss": 0.1208,
      "step": 317
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.33602339250898e-05,
      "loss": 0.1244,
      "step": 318
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.282993092381625e-05,
      "loss": 0.124,
      "step": 319
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.229983052611597e-05,
      "loss": 0.1151,
      "step": 320
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.176994771095687e-05,
      "loss": 0.1076,
      "step": 321
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.12402974511587e-05,
      "loss": 0.1269,
      "step": 322
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.071089471296995e-05,
      "loss": 0.1077,
      "step": 323
    },
    {
      "epoch": 0.54,
      "learning_rate": 9.018175445564485e-05,
      "loss": 0.1229,
      "step": 324
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.965289163102078e-05,
      "loss": 0.1107,
      "step": 325
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.912432118309582e-05,
      "loss": 0.1057,
      "step": 326
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.859605804760626e-05,
      "loss": 0.107,
      "step": 327
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.806811715160485e-05,
      "loss": 0.1142,
      "step": 328
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.754051341303875e-05,
      "loss": 0.1188,
      "step": 329
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.70132617403282e-05,
      "loss": 0.1011,
      "step": 330
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.648637703194516e-05,
      "loss": 0.1168,
      "step": 331
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.595987417599225e-05,
      "loss": 0.1239,
      "step": 332
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.543376804978224e-05,
      "loss": 0.1039,
      "step": 333
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.490807351941753e-05,
      "loss": 0.1113,
      "step": 334
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.438280543937011e-05,
      "loss": 0.1179,
      "step": 335
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.385797865206178e-05,
      "loss": 0.1257,
      "step": 336
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.333360798744496e-05,
      "loss": 0.1193,
      "step": 337
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.280970826258329e-05,
      "loss": 0.1265,
      "step": 338
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.228629428123319e-05,
      "loss": 0.1181,
      "step": 339
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.176338083342561e-05,
      "loss": 0.113,
      "step": 340
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.124098269504787e-05,
      "loss": 0.1159,
      "step": 341
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.07191146274263e-05,
      "loss": 0.1301,
      "step": 342
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.019779137690906e-05,
      "loss": 0.1203,
      "step": 343
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.967702767444964e-05,
      "loss": 0.1164,
      "step": 344
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.915683823519031e-05,
      "loss": 0.1198,
      "step": 345
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.863723775804651e-05,
      "loss": 0.1027,
      "step": 346
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.811824092529156e-05,
      "loss": 0.1379,
      "step": 347
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.759986240214155e-05,
      "loss": 0.1112,
      "step": 348
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.708211683634112e-05,
      "loss": 0.1413,
      "step": 349
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.656501885774964e-05,
      "loss": 0.1247,
      "step": 350
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.604858307792758e-05,
      "loss": 0.1168,
      "step": 351
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.553282408972382e-05,
      "loss": 0.1218,
      "step": 352
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.501775646686315e-05,
      "loss": 0.1177,
      "step": 353
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.450339476353474e-05,
      "loss": 0.1244,
      "step": 354
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.398975351398053e-05,
      "loss": 0.1132,
      "step": 355
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.34768472320847e-05,
      "loss": 0.1257,
      "step": 356
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.29646904109637e-05,
      "loss": 0.1247,
      "step": 357
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.245329752255647e-05,
      "loss": 0.1196,
      "step": 358
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.194268301721563e-05,
      "loss": 0.1139,
      "step": 359
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.143286132329912e-05,
      "loss": 0.129,
      "step": 360
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.092384684676262e-05,
      "loss": 0.1164,
      "step": 361
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.041565397075232e-05,
      "loss": 0.1048,
      "step": 362
    },
    {
      "epoch": 0.6,
      "learning_rate": 6.990829705519852e-05,
      "loss": 0.1098,
      "step": 363
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.940179043641005e-05,
      "loss": 0.1129,
      "step": 364
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.889614842666892e-05,
      "loss": 0.1162,
      "step": 365
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.839138531382603e-05,
      "loss": 0.1198,
      "step": 366
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.788751536089739e-05,
      "loss": 0.1107,
      "step": 367
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.738455280566124e-05,
      "loss": 0.1177,
      "step": 368
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.68825118602555e-05,
      "loss": 0.1189,
      "step": 369
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.638140671077633e-05,
      "loss": 0.1105,
      "step": 370
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.58812515168773e-05,
      "loss": 0.1156,
      "step": 371
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.538206041136915e-05,
      "loss": 0.1306,
      "step": 372
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.488384749982053e-05,
      "loss": 0.1218,
      "step": 373
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.438662686015947e-05,
      "loss": 0.1162,
      "step": 374
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.389041254227547e-05,
      "loss": 0.0903,
      "step": 375
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.339521856762254e-05,
      "loss": 0.106,
      "step": 376
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.290105892882303e-05,
      "loss": 0.1147,
      "step": 377
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.240794758927221e-05,
      "loss": 0.1274,
      "step": 378
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.191589848274368e-05,
      "loss": 0.1024,
      "step": 379
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.142492551299576e-05,
      "loss": 0.1056,
      "step": 380
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.093504255337844e-05,
      "loss": 0.1185,
      "step": 381
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.044626344644151e-05,
      "loss": 0.1125,
      "step": 382
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.995860200354335e-05,
      "loss": 0.118,
      "step": 383
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.9472072004460665e-05,
      "loss": 0.1193,
      "step": 384
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.8986687196999135e-05,
      "loss": 0.1221,
      "step": 385
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.8502461296604935e-05,
      "loss": 0.1215,
      "step": 386
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.801940798597716e-05,
      "loss": 0.1191,
      "step": 387
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.753754091468115e-05,
      "loss": 0.1258,
      "step": 388
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.7056873698763034e-05,
      "loss": 0.1149,
      "step": 389
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6577419920364625e-05,
      "loss": 0.1275,
      "step": 390
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6099193127339864e-05,
      "loss": 0.1203,
      "step": 391
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.562220683287205e-05,
      "loss": 0.1165,
      "step": 392
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.5146474515091754e-05,
      "loss": 0.1248,
      "step": 393
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.467200961669619e-05,
      "loss": 0.0989,
      "step": 394
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.4198825544569234e-05,
      "loss": 0.1127,
      "step": 395
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.372693566940277e-05,
      "loss": 0.1248,
      "step": 396
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.325635332531864e-05,
      "loss": 0.1094,
      "step": 397
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.278709180949195e-05,
      "loss": 0.1194,
      "step": 398
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.2319164381775524e-05,
      "loss": 0.1178,
      "step": 399
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.1852584264324866e-05,
      "loss": 0.123,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.138736464122484e-05,
      "loss": 0.1102,
      "step": 401
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.092351865811698e-05,
      "loss": 0.1215,
      "step": 402
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.046105942182815e-05,
      "loss": 0.115,
      "step": 403
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.1181,
      "step": 404
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.9540353420719946e-05,
      "loss": 0.096,
      "step": 405
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.908213267215287e-05,
      "loss": 0.1176,
      "step": 406
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.8625350702174166e-05,
      "loss": 0.1229,
      "step": 407
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.817002041800388e-05,
      "loss": 0.1177,
      "step": 408
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.7716154685841944e-05,
      "loss": 0.1124,
      "step": 409
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.726376633050479e-05,
      "loss": 0.1325,
      "step": 410
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.68128681350627e-05,
      "loss": 0.1072,
      "step": 411
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.636347284047877e-05,
      "loss": 0.1168,
      "step": 412
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.5915593145248924e-05,
      "loss": 0.105,
      "step": 413
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.546924170504292e-05,
      "loss": 0.1121,
      "step": 414
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.502443113234688e-05,
      "loss": 0.1075,
      "step": 415
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.4581173996106815e-05,
      "loss": 0.1266,
      "step": 416
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.413948282137367e-05,
      "loss": 0.1161,
      "step": 417
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.3699370088949066e-05,
      "loss": 0.114,
      "step": 418
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.326084823503287e-05,
      "loss": 0.1145,
      "step": 419
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.282392965087182e-05,
      "loss": 0.1174,
      "step": 420
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.2388626682409194e-05,
      "loss": 0.1368,
      "step": 421
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.1954951629936065e-05,
      "loss": 0.1133,
      "step": 422
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.152291674774383e-05,
      "loss": 0.1073,
      "step": 423
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.109253424377772e-05,
      "loss": 0.0974,
      "step": 424
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.0663816279292024e-05,
      "loss": 0.1427,
      "step": 425
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.02367749685063e-05,
      "loss": 0.1349,
      "step": 426
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.981142237826332e-05,
      "loss": 0.118,
      "step": 427
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.93877705276878e-05,
      "loss": 0.1023,
      "step": 428
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.896583138784688e-05,
      "loss": 0.0998,
      "step": 429
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.854561688141205e-05,
      "loss": 0.112,
      "step": 430
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.812713888232193e-05,
      "loss": 0.12,
      "step": 431
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.7710409215446986e-05,
      "loss": 0.1135,
      "step": 432
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.729543965625526e-05,
      "loss": 0.1196,
      "step": 433
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.6882241930479824e-05,
      "loss": 0.1124,
      "step": 434
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.6470827713787194e-05,
      "loss": 0.1165,
      "step": 435
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.606120863144753e-05,
      "loss": 0.1031,
      "step": 436
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.5653396258006265e-05,
      "loss": 0.1115,
      "step": 437
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.524740211695683e-05,
      "loss": 0.1261,
      "step": 438
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.4843237680415156e-05,
      "loss": 0.1213,
      "step": 439
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.444091436879545e-05,
      "loss": 0.1236,
      "step": 440
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.4040443550487645e-05,
      "loss": 0.1157,
      "step": 441
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.364183654153592e-05,
      "loss": 0.1072,
      "step": 442
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.32451046053191e-05,
      "loss": 0.0938,
      "step": 443
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.285025895223244e-05,
      "loss": 0.1236,
      "step": 444
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.245731073937068e-05,
      "loss": 0.1369,
      "step": 445
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2066271070212874e-05,
      "loss": 0.1168,
      "step": 446
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.167715099430873e-05,
      "loss": 0.0973,
      "step": 447
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.1289961506966214e-05,
      "loss": 0.0985,
      "step": 448
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0904713548940936e-05,
      "loss": 0.1168,
      "step": 449
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.052141800612709e-05,
      "loss": 0.1115,
      "step": 450
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0140085709249667e-05,
      "loss": 0.1155,
      "step": 451
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.9760727433558522e-05,
      "loss": 0.1223,
      "step": 452
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.938335389852397e-05,
      "loss": 0.1252,
      "step": 453
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.9007975767533714e-05,
      "loss": 0.1272,
      "step": 454
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.863460364759163e-05,
      "loss": 0.114,
      "step": 455
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.8263248089018113e-05,
      "loss": 0.0958,
      "step": 456
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.789391958515183e-05,
      "loss": 0.1294,
      "step": 457
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7526628572053227e-05,
      "loss": 0.1126,
      "step": 458
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.7161385428209774e-05,
      "loss": 0.11,
      "step": 459
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.679820047424253e-05,
      "loss": 0.1189,
      "step": 460
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6437083972614572e-05,
      "loss": 0.1115,
      "step": 461
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.6078046127341137e-05,
      "loss": 0.1205,
      "step": 462
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5721097083701084e-05,
      "loss": 0.096,
      "step": 463
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5366246927950286e-05,
      "loss": 0.1064,
      "step": 464
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.5013505687036786e-05,
      "loss": 0.1279,
      "step": 465
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4662883328317222e-05,
      "loss": 0.1124,
      "step": 466
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.4314389759275335e-05,
      "loss": 0.1052,
      "step": 467
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3968034827241925e-05,
      "loss": 0.1103,
      "step": 468
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3623828319116748e-05,
      "loss": 0.1075,
      "step": 469
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.3281779961091775e-05,
      "loss": 0.0996,
      "step": 470
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.2941899418376466e-05,
      "loss": 0.0935,
      "step": 471
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2604196294924694e-05,
      "loss": 0.1096,
      "step": 472
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.2268680133163277e-05,
      "loss": 0.1101,
      "step": 473
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1935360413722395e-05,
      "loss": 0.1223,
      "step": 474
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1604246555167638e-05,
      "loss": 0.1165,
      "step": 475
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.1275347913734022e-05,
      "loss": 0.1182,
      "step": 476
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.0948673783061422e-05,
      "loss": 0.1039,
      "step": 477
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0624233393932024e-05,
      "loss": 0.1117,
      "step": 478
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.03020359140096e-05,
      "loss": 0.1178,
      "step": 479
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9982090447580303e-05,
      "loss": 0.1253,
      "step": 480
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.966440603529549e-05,
      "loss": 0.1079,
      "step": 481
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9348991653916228e-05,
      "loss": 0.101,
      "step": 482
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.9035856216059722e-05,
      "loss": 0.1012,
      "step": 483
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8725008569947365e-05,
      "loss": 0.121,
      "step": 484
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.8416457499154728e-05,
      "loss": 0.1232,
      "step": 485
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.811021172236348e-05,
      "loss": 0.1058,
      "step": 486
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7806279893114875e-05,
      "loss": 0.1078,
      "step": 487
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.750467059956531e-05,
      "loss": 0.1188,
      "step": 488
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.7205392364243623e-05,
      "loss": 0.118,
      "step": 489
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.690845364381034e-05,
      "loss": 0.108,
      "step": 490
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6613862828818628e-05,
      "loss": 0.1035,
      "step": 491
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.6321628243477194e-05,
      "loss": 0.1274,
      "step": 492
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.603175814541522e-05,
      "loss": 0.1184,
      "step": 493
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5744260725448844e-05,
      "loss": 0.1038,
      "step": 494
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.5459144107349787e-05,
      "loss": 0.1059,
      "step": 495
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.5176416347615885e-05,
      "loss": 0.1079,
      "step": 496
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4896085435243279e-05,
      "loss": 0.1169,
      "step": 497
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4618159291500778e-05,
      "loss": 0.1092,
      "step": 498
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.4342645769705977e-05,
      "loss": 0.1362,
      "step": 499
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.406955265500346e-05,
      "loss": 0.1393,
      "step": 500
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.3798887664144633e-05,
      "loss": 0.1252,
      "step": 501
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3530658445269783e-05,
      "loss": 0.1019,
      "step": 502
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3264872577692022e-05,
      "loss": 0.1204,
      "step": 503
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.3001537571682965e-05,
      "loss": 0.1303,
      "step": 504
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2740660868260633e-05,
      "loss": 0.1178,
      "step": 505
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2482249838979142e-05,
      "loss": 0.1066,
      "step": 506
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.2226311785720468e-05,
      "loss": 0.1184,
      "step": 507
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1972853940488015e-05,
      "loss": 0.1062,
      "step": 508
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1721883465202332e-05,
      "loss": 0.1105,
      "step": 509
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1473407451498753e-05,
      "loss": 0.1232,
      "step": 510
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.122743292052697e-05,
      "loss": 0.1225,
      "step": 511
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0983966822752623e-05,
      "loss": 0.1021,
      "step": 512
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.0743016037760945e-05,
      "loss": 0.1062,
      "step": 513
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0504587374062391e-05,
      "loss": 0.116,
      "step": 514
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.026868756890016e-05,
      "loss": 0.1203,
      "step": 515
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.003532328805986e-05,
      "loss": 0.117,
      "step": 516
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.804501125681243e-06,
      "loss": 0.1043,
      "step": 517
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.57622760407173e-06,
      "loss": 0.1162,
      "step": 518
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.350509173522193e-06,
      "loss": 0.1154,
      "step": 519
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.127352212124662e-06,
      "loss": 0.1088,
      "step": 520
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.90676302559219e-06,
      "loss": 0.1187,
      "step": 521
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.688747847080514e-06,
      "loss": 0.1084,
      "step": 522
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.473312837012026e-06,
      "loss": 0.1071,
      "step": 523
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.260464082901732e-06,
      "loss": 0.1241,
      "step": 524
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.050207599185134e-06,
      "loss": 0.1227,
      "step": 525
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.842549327048365e-06,
      "loss": 0.1189,
      "step": 526
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.637495134260242e-06,
      "loss": 0.1025,
      "step": 527
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.435050815006561e-06,
      "loss": 0.1024,
      "step": 528
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.235222089726279e-06,
      "loss": 0.0958,
      "step": 529
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.038014604949883e-06,
      "loss": 0.1155,
      "step": 530
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.843433933139909e-06,
      "loss": 0.1107,
      "step": 531
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.651485572533378e-06,
      "loss": 0.1109,
      "step": 532
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.46217494698651e-06,
      "loss": 0.1211,
      "step": 533
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.275507405821435e-06,
      "loss": 0.121,
      "step": 534
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.091488223675057e-06,
      "loss": 0.114,
      "step": 535
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.910122600349965e-06,
      "loss": 0.1285,
      "step": 536
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.7314156606675496e-06,
      "loss": 0.0938,
      "step": 537
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.5553724543231825e-06,
      "loss": 0.1107,
      "step": 538
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.381997955743501e-06,
      "loss": 0.1255,
      "step": 539
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.2112970639458745e-06,
      "loss": 0.1278,
      "step": 540
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.043274602399939e-06,
      "loss": 0.1134,
      "step": 541
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.87793531889138e-06,
      "loss": 0.1072,
      "step": 542
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.715283885387678e-06,
      "loss": 0.1115,
      "step": 543
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.555324897906132e-06,
      "loss": 0.1012,
      "step": 544
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.398062876384046e-06,
      "loss": 0.1145,
      "step": 545
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.2435022645509025e-06,
      "loss": 0.1079,
      "step": 546
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.091647429802869e-06,
      "loss": 0.1133,
      "step": 547
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.942502663079395e-06,
      "loss": 0.1078,
      "step": 548
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.796072178741916e-06,
      "loss": 0.1113,
      "step": 549
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.6523601144548003e-06,
      "loss": 3.1026,
      "step": 550
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5113705310684363e-06,
      "loss": 0.1238,
      "step": 551
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.3731074125044726e-06,
      "loss": 0.1266,
      "step": 552
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.2375746656432284e-06,
      "loss": 0.1344,
      "step": 553
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.1047761202133597e-06,
      "loss": 0.1211,
      "step": 554
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.974715528683547e-06,
      "loss": 0.1223,
      "step": 555
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8473965661565347e-06,
      "loss": 0.1148,
      "step": 556
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.7228228302653034e-06,
      "loss": 0.1238,
      "step": 557
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.600997841071329e-06,
      "loss": 0.0977,
      "step": 558
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.4819250409651607e-06,
      "loss": 0.1203,
      "step": 559
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.3656077945691803e-06,
      "loss": 0.1029,
      "step": 560
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.2520493886424743e-06,
      "loss": 0.1305,
      "step": 561
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1412530319879887e-06,
      "loss": 0.1208,
      "step": 562
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.0332218553618885e-06,
      "loss": 0.1234,
      "step": 563
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9279589113850084e-06,
      "loss": 0.1387,
      "step": 564
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.825467174456652e-06,
      "loss": 0.1313,
      "step": 565
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.725749540670596e-06,
      "loss": 0.1135,
      "step": 566
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.6288088277331304e-06,
      "loss": 0.101,
      "step": 567
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5346477748835354e-06,
      "loss": 0.1131,
      "step": 568
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4432690428166528e-06,
      "loss": 0.1117,
      "step": 569
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3546752136076923e-06,
      "loss": 0.1107,
      "step": 570
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.268868790639277e-06,
      "loss": 0.115,
      "step": 571
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.1858521985307125e-06,
      "loss": 0.1163,
      "step": 572
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.105627783069485e-06,
      "loss": 0.1131,
      "step": 573
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0281978111449375e-06,
      "loss": 0.1085,
      "step": 574
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.535644706842317e-07,
      "loss": 0.1257,
      "step": 575
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.817298705905641e-07,
      "loss": 0.1188,
      "step": 576
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.126960406835249e-07,
      "loss": 0.1101,
      "step": 577
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.464649316417438e-07,
      "loss": 0.1075,
      "step": 578
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.830384149478008e-07,
      "loss": 0.0966,
      "step": 579
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.224182828353242e-07,
      "loss": 0.1244,
      "step": 580
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.64606248238364e-07,
      "loss": 0.1137,
      "step": 581
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.096039447429534e-07,
      "loss": 0.1087,
      "step": 582
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.57412926541001e-07,
      "loss": 0.1022,
      "step": 583
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.0803466838631455e-07,
      "loss": 0.1104,
      "step": 584
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.614705655529682e-07,
      "loss": 0.1169,
      "step": 585
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.177219337958892e-07,
      "loss": 0.1176,
      "step": 586
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.767900093136544e-07,
      "loss": 0.1273,
      "step": 587
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.3867594871352926e-07,
      "loss": 0.1032,
      "step": 588
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.0338082897886079e-07,
      "loss": 0.1342,
      "step": 589
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.709056474385795e-07,
      "loss": 0.1124,
      "step": 590
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.412513217390554e-07,
      "loss": 0.1231,
      "step": 591
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.1441868981815207e-07,
      "loss": 0.1221,
      "step": 592
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.040850988153438e-08,
      "loss": 0.1088,
      "step": 593
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.922146038129684e-08,
      "loss": 0.1155,
      "step": 594
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.08581399967345e-08,
      "loss": 0.1103,
      "step": 595
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.53190676174453e-08,
      "loss": 0.1189,
      "step": 596
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.260468232869739e-08,
      "loss": 0.1202,
      "step": 597
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.2715343398972402e-08,
      "loss": 0.1187,
      "step": 598
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.651330269840216e-09,
      "loss": 0.0985,
      "step": 599
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.4128425480763874e-09,
      "loss": 0.1111,
      "step": 600
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.1056,
      "step": 601
    }
  ],
  "logging_steps": 1,
  "max_steps": 601,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 188987860844544.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}