{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9995577178239717,
  "eval_steps": 142,
  "global_step": 565,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 4.6921162605285645,
      "learning_rate": 5e-05,
      "loss": 3.3182,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 3.3362529277801514,
      "eval_runtime": 14.4412,
      "eval_samples_per_second": 33.031,
      "eval_steps_per_second": 8.31,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 4.620742321014404,
      "learning_rate": 0.0001,
      "loss": 3.2788,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 4.650161266326904,
      "learning_rate": 0.00015,
      "loss": 3.2271,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 4.024933815002441,
      "learning_rate": 0.0002,
      "loss": 2.402,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.751981496810913,
      "learning_rate": 0.00025,
      "loss": 1.0544,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.4766970872879028,
      "learning_rate": 0.0003,
      "loss": 0.3549,
      "step": 6
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8064658641815186,
      "learning_rate": 0.00035,
      "loss": 0.1533,
      "step": 7
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.232205390930176,
      "learning_rate": 0.0004,
      "loss": 0.31,
      "step": 8
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.1898847818374634,
      "learning_rate": 0.00045000000000000004,
      "loss": 0.1818,
      "step": 9
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.7394833564758301,
      "learning_rate": 0.0005,
      "loss": 0.1751,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.16317571699619293,
      "learning_rate": 0.0004999995654799487,
      "loss": 0.1411,
      "step": 11
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.10235322266817093,
      "learning_rate": 0.0004999982619213052,
      "loss": 0.1363,
      "step": 12
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.19907887279987335,
      "learning_rate": 0.0004999960893286008,
      "loss": 0.128,
      "step": 13
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.6823816299438477,
      "learning_rate": 0.0004999930477093878,
      "loss": 0.143,
      "step": 14
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.10187644511461258,
      "learning_rate": 0.0004999891370742394,
      "loss": 0.1322,
      "step": 15
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.09401004016399384,
      "learning_rate": 0.0004999843574367498,
      "loss": 0.1361,
      "step": 16
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.17946797609329224,
      "learning_rate": 0.0004999787088135334,
      "loss": 0.1412,
      "step": 17
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.890545666217804,
      "learning_rate": 0.0004999721912242259,
      "loss": 0.1593,
      "step": 18
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.434042751789093,
      "learning_rate": 0.0004999648046914836,
      "loss": 0.1548,
      "step": 19
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.28103551268577576,
      "learning_rate": 0.0004999565492409831,
      "loss": 0.1459,
      "step": 20
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.2690610885620117,
      "learning_rate": 0.0004999474249014217,
      "loss": 0.1248,
      "step": 21
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.37668731808662415,
      "learning_rate": 0.0004999374317045172,
      "loss": 0.1481,
      "step": 22
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.23762015998363495,
      "learning_rate": 0.0004999265696850074,
      "loss": 0.1407,
      "step": 23
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.1988176554441452,
      "learning_rate": 0.0004999148388806504,
      "loss": 0.1398,
      "step": 24
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.3805619776248932,
      "learning_rate": 0.0004999022393322246,
      "loss": 0.1474,
      "step": 25
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.5069771409034729,
      "learning_rate": 0.0004998887710835278,
      "loss": 0.1509,
      "step": 26
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.42066043615341187,
      "learning_rate": 0.0004998744341813779,
      "loss": 0.1341,
      "step": 27
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0944904088973999,
      "learning_rate": 0.0004998592286756123,
      "loss": 0.1233,
      "step": 28
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.849244236946106,
      "learning_rate": 0.0004998431546190875,
      "loss": 0.1999,
      "step": 29
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.09785456210374832,
      "learning_rate": 0.00049982621206768,
      "loss": 0.1272,
      "step": 30
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.38225457072257996,
      "learning_rate": 0.0004998084010802845,
      "loss": 0.1634,
      "step": 31
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.08135183900594711,
      "learning_rate": 0.0004997897217188149,
      "loss": 0.1383,
      "step": 32
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.17299437522888184,
      "learning_rate": 0.0004997701740482036,
      "loss": 0.1427,
      "step": 33
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.11125747114419937,
      "learning_rate": 0.0004997497581364015,
      "loss": 0.1379,
      "step": 34
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.08914893865585327,
      "learning_rate": 0.0004997284740543776,
      "loss": 0.1388,
      "step": 35
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.034590039402246475,
      "learning_rate": 0.0004997063218761188,
      "loss": 0.1387,
      "step": 36
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.08675777167081833,
      "learning_rate": 0.0004996833016786296,
      "loss": 0.1384,
      "step": 37
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.4440009295940399,
      "learning_rate": 0.0004996594135419318,
      "loss": 0.152,
      "step": 38
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0814109519124031,
      "learning_rate": 0.0004996346575490646,
      "loss": 0.1373,
      "step": 39
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.37724560499191284,
      "learning_rate": 0.0004996090337860836,
      "loss": 0.1362,
      "step": 40
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.21177273988723755,
      "learning_rate": 0.0004995825423420613,
      "loss": 0.1423,
      "step": 41
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.12168041616678238,
      "learning_rate": 0.000499555183309086,
      "loss": 0.1381,
      "step": 42
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.21096466481685638,
      "learning_rate": 0.0004995269567822623,
      "loss": 0.139,
      "step": 43
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.49395841360092163,
      "learning_rate": 0.0004994978628597099,
      "loss": 0.1016,
      "step": 44
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.1108216792345047,
      "learning_rate": 0.0004994679016425642,
      "loss": 0.1334,
      "step": 45
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.5518127679824829,
      "learning_rate": 0.000499437073234975,
      "loss": 0.1568,
      "step": 46
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.4762812852859497,
      "learning_rate": 0.0004994053777441069,
      "loss": 0.1543,
      "step": 47
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3477722108364105,
      "learning_rate": 0.0004993728152801384,
      "loss": 0.1464,
      "step": 48
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.4996407628059387,
      "learning_rate": 0.0004993393859562621,
      "loss": 0.154,
      "step": 49
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.20425601303577423,
      "learning_rate": 0.0004993050898886833,
      "loss": 0.1372,
      "step": 50
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.034631408751010895,
      "learning_rate": 0.000499269927196621,
      "loss": 0.137,
      "step": 51
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.24027873575687408,
      "learning_rate": 0.0004992338980023062,
      "loss": 0.1468,
      "step": 52
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.22242723405361176,
      "learning_rate": 0.000499197002430982,
      "loss": 0.1418,
      "step": 53
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6540514826774597,
      "learning_rate": 0.0004991592406109036,
      "loss": 0.1564,
      "step": 54
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.030118577182292938,
      "learning_rate": 0.000499120612673337,
      "loss": 0.1365,
      "step": 55
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.07544097304344177,
      "learning_rate": 0.0004990811187525592,
      "loss": 0.1334,
      "step": 56
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.37415480613708496,
      "learning_rate": 0.0004990407589858572,
      "loss": 0.155,
      "step": 57
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.557809054851532,
      "learning_rate": 0.0004989995335135282,
      "loss": 0.1603,
      "step": 58
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.14802873134613037,
      "learning_rate": 0.0004989574424788787,
      "loss": 0.1387,
      "step": 59
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.3581993281841278,
      "learning_rate": 0.0004989144860282236,
      "loss": 0.1475,
      "step": 60
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.04818522185087204,
      "learning_rate": 0.0004988706643108864,
      "loss": 0.1362,
      "step": 61
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.21908174455165863,
      "learning_rate": 0.0004988259774791987,
      "loss": 0.1386,
      "step": 62
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.1852695643901825,
      "learning_rate": 0.0004987804256884988,
      "loss": 0.1387,
      "step": 63
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.025747304782271385,
      "learning_rate": 0.0004987340090971323,
      "loss": 0.1393,
      "step": 64
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.045346710830926895,
      "learning_rate": 0.0004986867278664504,
      "loss": 0.1354,
      "step": 65
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.34946465492248535,
      "learning_rate": 0.0004986385821608106,
      "loss": 0.152,
      "step": 66
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.2552882432937622,
      "learning_rate": 0.0004985895721475748,
      "loss": 0.1463,
      "step": 67
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0560542456805706,
      "learning_rate": 0.0004985396979971099,
      "loss": 0.1391,
      "step": 68
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.14347511529922485,
      "learning_rate": 0.0004984889598827863,
      "loss": 0.1353,
      "step": 69
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.12386342883110046,
      "learning_rate": 0.0004984373579809778,
      "loss": 0.1343,
      "step": 70
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.03070697747170925,
      "learning_rate": 0.000498384892471061,
      "loss": 0.1356,
      "step": 71
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.0531514473259449,
      "learning_rate": 0.0004983315635354144,
      "loss": 0.1346,
      "step": 72
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.24197503924369812,
      "learning_rate": 0.0004982773713594178,
      "loss": 0.1217,
      "step": 73
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.08417380601167679,
      "learning_rate": 0.0004982223161314522,
      "loss": 0.1223,
      "step": 74
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.40045711398124695,
      "learning_rate": 0.000498166398042898,
      "loss": 0.1513,
      "step": 75
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.12452740222215652,
      "learning_rate": 0.0004981096172881358,
      "loss": 0.1296,
      "step": 76
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.21590262651443481,
      "learning_rate": 0.0004980519740645444,
      "loss": 0.1375,
      "step": 77
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.07704459875822067,
      "learning_rate": 0.0004979934685725011,
      "loss": 0.1299,
      "step": 78
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.28334081172943115,
      "learning_rate": 0.0004979341010153801,
      "loss": 0.1387,
      "step": 79
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.12374007701873779,
      "learning_rate": 0.0004978738715995526,
      "loss": 0.1383,
      "step": 80
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.040613267570734024,
      "learning_rate": 0.000497812780534386,
      "loss": 0.1367,
      "step": 81
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.09974126517772675,
      "learning_rate": 0.0004977508280322423,
      "loss": 0.1248,
      "step": 82
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.2616259753704071,
      "learning_rate": 0.0004976880143084786,
      "loss": 0.1311,
      "step": 83
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.15635579824447632,
      "learning_rate": 0.0004976243395814452,
      "loss": 0.1189,
      "step": 84
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.259250670671463,
      "learning_rate": 0.000497559804072486,
      "loss": 0.1099,
      "step": 85
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.2778699398040771,
      "learning_rate": 0.0004974944080059365,
      "loss": 0.1416,
      "step": 86
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.2155281901359558,
      "learning_rate": 0.000497428151609124,
      "loss": 0.1253,
      "step": 87
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.17533721029758453,
      "learning_rate": 0.0004973610351123664,
      "loss": 0.1446,
      "step": 88
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.07620590180158615,
      "learning_rate": 0.0004972930587489715,
      "loss": 0.1309,
      "step": 89
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.2370779663324356,
      "learning_rate": 0.0004972242227552358,
      "loss": 0.149,
      "step": 90
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.06374065577983856,
      "learning_rate": 0.0004971545273704444,
      "loss": 0.1307,
      "step": 91
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.22728750109672546,
      "learning_rate": 0.0004970839728368697,
      "loss": 0.1438,
      "step": 92
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.16872233152389526,
      "learning_rate": 0.0004970125593997706,
      "loss": 0.1364,
      "step": 93
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.18773947656154633,
      "learning_rate": 0.0004969402873073914,
      "loss": 0.146,
      "step": 94
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.1468167006969452,
      "learning_rate": 0.0004968671568109616,
      "loss": 0.1401,
      "step": 95
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.09030504524707794,
      "learning_rate": 0.0004967931681646948,
      "loss": 0.1318,
      "step": 96
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.061796192079782486,
      "learning_rate": 0.000496718321625787,
      "loss": 0.1244,
      "step": 97
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.045495226979255676,
      "learning_rate": 0.0004966426174544171,
      "loss": 0.1265,
      "step": 98
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08449025452136993,
      "learning_rate": 0.0004965660559137448,
      "loss": 0.1276,
      "step": 99
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.09982559829950333,
      "learning_rate": 0.0004964886372699102,
      "loss": 0.1253,
      "step": 100
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.05831208825111389,
      "learning_rate": 0.0004964103617920332,
      "loss": 0.1271,
      "step": 101
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.20548835396766663,
      "learning_rate": 0.0004963312297522116,
      "loss": 0.1415,
      "step": 102
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.09664470702409744,
      "learning_rate": 0.0004962512414255214,
      "loss": 0.1083,
      "step": 103
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.16931602358818054,
      "learning_rate": 0.0004961703970900145,
      "loss": 0.1431,
      "step": 104
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.10859667509794235,
      "learning_rate": 0.000496088697026719,
      "loss": 0.12,
      "step": 105
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.21958191692829132,
      "learning_rate": 0.0004960061415196374,
      "loss": 0.1492,
      "step": 106
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.06437578052282333,
      "learning_rate": 0.0004959227308557459,
      "loss": 0.1083,
      "step": 107
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.14975550770759583,
      "learning_rate": 0.0004958384653249932,
      "loss": 0.1155,
      "step": 108
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.11868852376937866,
      "learning_rate": 0.0004957533452203,
      "loss": 0.1237,
      "step": 109
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.2610260546207428,
      "learning_rate": 0.0004956673708375574,
      "loss": 0.1264,
      "step": 110
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.378467321395874,
      "learning_rate": 0.000495580542475626,
      "loss": 0.1222,
      "step": 111
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0926096960902214,
      "learning_rate": 0.0004954928604363352,
      "loss": 0.1096,
      "step": 112
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.06858692318201065,
      "learning_rate": 0.0004954043250244819,
      "loss": 0.1144,
      "step": 113
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.3068992495536804,
      "learning_rate": 0.0004953149365478293,
      "loss": 0.1563,
      "step": 114
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.15458936989307404,
      "learning_rate": 0.0004952246953171061,
      "loss": 0.1216,
      "step": 115
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.10287577658891678,
      "learning_rate": 0.0004951336016460053,
      "loss": 0.0893,
      "step": 116
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.1215134710073471,
      "learning_rate": 0.0004950416558511833,
      "loss": 0.1016,
      "step": 117
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.1392650604248047,
      "learning_rate": 0.000494948858252258,
      "loss": 0.1111,
      "step": 118
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.4350431263446808,
      "learning_rate": 0.0004948552091718092,
      "loss": 0.1192,
      "step": 119
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.21448662877082825,
      "learning_rate": 0.0004947607089353758,
      "loss": 0.07,
      "step": 120
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.6086686849594116,
      "learning_rate": 0.0004946653578714559,
      "loss": 0.1352,
      "step": 121
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.25963085889816284,
      "learning_rate": 0.0004945691563115051,
      "loss": 0.1447,
      "step": 122
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.11575956642627716,
      "learning_rate": 0.0004944721045899356,
      "loss": 0.1055,
      "step": 123
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.11230157315731049,
      "learning_rate": 0.0004943742030441145,
      "loss": 0.0917,
      "step": 124
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.3376341760158539,
      "learning_rate": 0.0004942754520143634,
      "loss": 0.1364,
      "step": 125
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.2757412791252136,
      "learning_rate": 0.0004941758518439566,
      "loss": 0.1418,
      "step": 126
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.1438644975423813,
      "learning_rate": 0.0004940754028791205,
      "loss": 0.1162,
      "step": 127
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.14210884273052216,
      "learning_rate": 0.0004939741054690316,
      "loss": 0.1312,
      "step": 128
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.1861649751663208,
      "learning_rate": 0.0004938719599658162,
      "loss": 0.1447,
      "step": 129
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.19665485620498657,
      "learning_rate": 0.0004937689667245481,
      "loss": 0.1439,
      "step": 130
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.22447055578231812,
      "learning_rate": 0.0004936651261032486,
      "loss": 0.1568,
      "step": 131
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.10008269548416138,
      "learning_rate": 0.0004935604384628843,
      "loss": 0.1081,
      "step": 132
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.0549234002828598,
      "learning_rate": 0.0004934549041673661,
      "loss": 0.1216,
      "step": 133
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.11616212874650955,
      "learning_rate": 0.0004933485235835483,
      "loss": 0.1108,
      "step": 134
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.08554813265800476,
      "learning_rate": 0.0004932412970812269,
      "loss": 0.135,
      "step": 135
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.08642842620611191,
      "learning_rate": 0.0004931332250331382,
      "loss": 0.1205,
      "step": 136
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.20417262613773346,
      "learning_rate": 0.0004930243078149582,
      "loss": 0.1169,
      "step": 137
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.11088764667510986,
      "learning_rate": 0.0004929145458053005,
      "loss": 0.1014,
      "step": 138
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.3510516881942749,
      "learning_rate": 0.0004928039393857155,
      "loss": 0.0967,
      "step": 139
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.2401883453130722,
      "learning_rate": 0.0004926924889406888,
      "loss": 0.106,
      "step": 140
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.28403300046920776,
      "learning_rate": 0.0004925801948576402,
      "loss": 0.079,
      "step": 141
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.46027252078056335,
      "learning_rate": 0.0004924670575269217,
      "loss": 0.0899,
      "step": 142
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.09421269595623016,
      "eval_runtime": 14.7696,
      "eval_samples_per_second": 32.296,
      "eval_steps_per_second": 8.125,
      "step": 142
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.29767730832099915,
      "learning_rate": 0.0004923530773418169,
      "loss": 0.1265,
      "step": 143
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.37391072511672974,
      "learning_rate": 0.0004922382546985394,
      "loss": 0.1244,
      "step": 144
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.8874172568321228,
      "learning_rate": 0.0004921225899962308,
      "loss": 0.1796,
      "step": 145
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.2554258704185486,
      "learning_rate": 0.0004920060836369603,
      "loss": 0.0528,
      "step": 146
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.1981816440820694,
      "learning_rate": 0.0004918887360257228,
      "loss": 0.1159,
      "step": 147
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.14500874280929565,
      "learning_rate": 0.0004917705475704373,
      "loss": 0.0992,
      "step": 148
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.1315220594406128,
      "learning_rate": 0.000491651518681946,
      "loss": 0.1248,
      "step": 149
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0798826813697815,
      "learning_rate": 0.0004915316497740121,
      "loss": 0.1151,
      "step": 150
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.10213784873485565,
      "learning_rate": 0.0004914109412633194,
      "loss": 0.1098,
      "step": 151
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.23167072236537933,
      "learning_rate": 0.00049128939356947,
      "loss": 0.1236,
      "step": 152
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.173340305685997,
      "learning_rate": 0.0004911670071149831,
      "loss": 0.1098,
      "step": 153
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.1079009547829628,
      "learning_rate": 0.0004910437823252937,
      "loss": 0.1014,
      "step": 154
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.320765882730484,
      "learning_rate": 0.0004909197196287509,
      "loss": 0.1285,
      "step": 155
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.40041017532348633,
      "learning_rate": 0.0004907948194566166,
      "loss": 0.1421,
      "step": 156
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.4091287851333618,
      "learning_rate": 0.0004906690822430638,
      "loss": 0.1451,
      "step": 157
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.39893922209739685,
      "learning_rate": 0.0004905425084251753,
      "loss": 0.1289,
      "step": 158
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.14173893630504608,
      "learning_rate": 0.0004904150984429419,
      "loss": 0.0712,
      "step": 159
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.4723054766654968,
      "learning_rate": 0.0004902868527392611,
      "loss": 0.2141,
      "step": 160
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.13493523001670837,
      "learning_rate": 0.0004901577717599355,
      "loss": 0.0881,
      "step": 161
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.10770414024591446,
      "learning_rate": 0.0004900278559536716,
      "loss": 0.0746,
      "step": 162
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.5121994614601135,
      "learning_rate": 0.0004898971057720773,
      "loss": 0.1705,
      "step": 163
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.09419309347867966,
      "learning_rate": 0.0004897655216696612,
      "loss": 0.1085,
      "step": 164
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.3557867407798767,
      "learning_rate": 0.0004896331041038309,
      "loss": 0.1027,
      "step": 165
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.082126185297966,
      "learning_rate": 0.000489499853534891,
      "loss": 0.1113,
      "step": 166
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.8520584106445312,
      "learning_rate": 0.0004893657704260419,
      "loss": 0.1291,
      "step": 167
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.4607222080230713,
      "learning_rate": 0.000489230855243378,
      "loss": 0.1241,
      "step": 168
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.5181136727333069,
      "learning_rate": 0.0004890951084558859,
      "loss": 0.0957,
      "step": 169
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.42894089221954346,
      "learning_rate": 0.0004889585305354435,
      "loss": 0.0895,
      "step": 170
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.14509521424770355,
      "learning_rate": 0.0004888211219568175,
      "loss": 0.0732,
      "step": 171
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.24262909591197968,
      "learning_rate": 0.0004886828831976621,
      "loss": 0.0917,
      "step": 172
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.44387635588645935,
      "learning_rate": 0.0004885438147385175,
      "loss": 0.0636,
      "step": 173
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.1804012507200241,
      "learning_rate": 0.0004884039170628077,
      "loss": 0.0295,
      "step": 174
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.5566735863685608,
      "learning_rate": 0.0004882631906568398,
      "loss": 0.1104,
      "step": 175
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.9653083682060242,
      "learning_rate": 0.0004881216360098012,
      "loss": 0.2236,
      "step": 176
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.27046507596969604,
      "learning_rate": 0.0004879792536137585,
      "loss": 0.1082,
      "step": 177
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.47974228858947754,
      "learning_rate": 0.00048783604396365586,
      "loss": 0.0884,
      "step": 178
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.23638087511062622,
      "learning_rate": 0.0004876920075573129,
      "loss": 0.0968,
      "step": 179
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.12476328015327454,
      "learning_rate": 0.0004875471448954234,
      "loss": 0.1078,
      "step": 180
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.2455732375383377,
      "learning_rate": 0.00048740145648155307,
      "loss": 0.1124,
      "step": 181
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.2744804620742798,
      "learning_rate": 0.0004872549428221384,
      "loss": 0.0797,
      "step": 182
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.19536937773227692,
      "learning_rate": 0.00048710760442648415,
      "loss": 0.1091,
      "step": 183
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5277348160743713,
      "learning_rate": 0.0004869594418067623,
      "loss": 0.1261,
      "step": 184
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.13960392773151398,
      "learning_rate": 0.00048681045547801003,
      "loss": 0.0879,
      "step": 185
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.2567049562931061,
      "learning_rate": 0.00048666064595812746,
      "loss": 0.083,
      "step": 186
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.3075740337371826,
      "learning_rate": 0.00048651001376787676,
      "loss": 0.1167,
      "step": 187
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.5257586240768433,
      "learning_rate": 0.0004863585594308794,
      "loss": 0.1019,
      "step": 188
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.41611766815185547,
      "learning_rate": 0.00048620628347361496,
      "loss": 0.1392,
      "step": 189
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.30399614572525024,
      "learning_rate": 0.00048605318642541917,
      "loss": 0.1339,
      "step": 190
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.41276878118515015,
      "learning_rate": 0.00048589926881848194,
      "loss": 0.1028,
      "step": 191
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.19717253744602203,
      "learning_rate": 0.0004857445311878456,
      "loss": 0.1032,
      "step": 192
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.3766873776912689,
      "learning_rate": 0.0004855889740714028,
      "loss": 0.1486,
      "step": 193
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.17443525791168213,
      "learning_rate": 0.0004854325980098951,
      "loss": 0.096,
      "step": 194
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.1278471201658249,
      "learning_rate": 0.0004852754035469109,
      "loss": 0.0746,
      "step": 195
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.14356929063796997,
      "learning_rate": 0.0004851173912288833,
      "loss": 0.0857,
      "step": 196
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.20514866709709167,
      "learning_rate": 0.0004849585616050884,
      "loss": 0.0833,
      "step": 197
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.4683605134487152,
      "learning_rate": 0.0004847989152276435,
      "loss": 0.1538,
      "step": 198
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.29194721579551697,
      "learning_rate": 0.00048463845265150495,
      "loss": 0.1035,
      "step": 199
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.22838515043258667,
      "learning_rate": 0.0004844771744344666,
      "loss": 0.0762,
      "step": 200
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.3635599911212921,
      "learning_rate": 0.0004843150811371572,
      "loss": 0.1165,
      "step": 201
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.2508073151111603,
      "learning_rate": 0.0004841521733230391,
      "loss": 0.0736,
      "step": 202
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.24161550402641296,
      "learning_rate": 0.000483988451558406,
      "loss": 0.1309,
      "step": 203
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.4697308838367462,
      "learning_rate": 0.0004838239164123811,
      "loss": 0.1731,
      "step": 204
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.17773008346557617,
      "learning_rate": 0.0004836585684569148,
      "loss": 0.1158,
      "step": 205
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.21285519003868103,
      "learning_rate": 0.0004834924082667833,
      "loss": 0.0949,
      "step": 206
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.2403111308813095,
      "learning_rate": 0.0004833254364195859,
      "loss": 0.0801,
      "step": 207
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.2033465951681137,
      "learning_rate": 0.0004831576534957437,
      "loss": 0.069,
      "step": 208
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.5510303378105164,
      "learning_rate": 0.000482989060078497,
      "loss": 0.1766,
      "step": 209
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.32342344522476196,
      "learning_rate": 0.0004828196567539034,
      "loss": 0.1229,
      "step": 210
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.3102104663848877,
      "learning_rate": 0.00048264944411083625,
      "loss": 0.1297,
      "step": 211
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.32639122009277344,
      "learning_rate": 0.00048247842274098187,
      "loss": 0.1011,
      "step": 212
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.4720034897327423,
      "learning_rate": 0.00048230659323883804,
      "loss": 0.1282,
      "step": 213
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.5249712467193604,
      "learning_rate": 0.00048213395620171166,
      "loss": 0.1376,
      "step": 214
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.3953443467617035,
      "learning_rate": 0.00048196051222971673,
      "loss": 0.1186,
      "step": 215
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.15697738528251648,
      "learning_rate": 0.0004817862619257723,
      "loss": 0.1079,
      "step": 216
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.32511651515960693,
      "learning_rate": 0.0004816112058956005,
      "loss": 0.1052,
      "step": 217
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.1850031018257141,
      "learning_rate": 0.00048143534474772397,
      "loss": 0.1236,
      "step": 218
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.10901057720184326,
      "learning_rate": 0.0004812586790934645,
      "loss": 0.1094,
      "step": 219
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.23395784199237823,
      "learning_rate": 0.00048108120954694014,
      "loss": 0.0556,
      "step": 220
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.21469372510910034,
      "learning_rate": 0.00048090293672506347,
      "loss": 0.0594,
      "step": 221
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.17289988696575165,
      "learning_rate": 0.00048072386124753944,
      "loss": 0.0219,
      "step": 222
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.21490757167339325,
      "learning_rate": 0.0004805439837368631,
      "loss": 0.0203,
      "step": 223
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1259506940841675,
      "learning_rate": 0.0004803633048183176,
      "loss": 0.1576,
      "step": 224
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.2934038639068604,
      "learning_rate": 0.00048018182511997185,
      "loss": 0.1233,
      "step": 225
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.4250846207141876,
      "learning_rate": 0.0004799995452726783,
      "loss": 0.1023,
      "step": 226
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.4675579071044922,
      "learning_rate": 0.000479816465910071,
      "loss": 0.1242,
      "step": 227
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.7030429840087891,
      "learning_rate": 0.0004796325876685632,
      "loss": 0.0514,
      "step": 228
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.5683910846710205,
      "learning_rate": 0.00047944791118734517,
      "loss": 0.0923,
      "step": 229
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.8425244092941284,
      "learning_rate": 0.0004792624371083819,
      "loss": 0.0976,
      "step": 230
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.21189981698989868,
      "learning_rate": 0.00047907616607641113,
      "loss": 0.1016,
      "step": 231
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.36100390553474426,
      "learning_rate": 0.0004788890987389408,
      "loss": 0.1015,
      "step": 232
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.42600420117378235,
      "learning_rate": 0.000478701235746247,
      "loss": 0.1401,
      "step": 233
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.649318516254425,
      "learning_rate": 0.0004785125777513716,
      "loss": 0.1012,
      "step": 234
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.3490477204322815,
      "learning_rate": 0.00047832312541012007,
      "loss": 0.1015,
      "step": 235
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.6937799453735352,
      "learning_rate": 0.0004781328793810592,
      "loss": 0.1188,
      "step": 236
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.0924077033996582,
      "learning_rate": 0.0004779418403255146,
      "loss": 0.1093,
      "step": 237
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.36075183749198914,
      "learning_rate": 0.0004777500089075687,
      "loss": 0.0971,
      "step": 238
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.41673243045806885,
      "learning_rate": 0.00047755738579405836,
      "loss": 0.0953,
      "step": 239
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.13159583508968353,
      "learning_rate": 0.0004773639716545723,
      "loss": 0.0571,
      "step": 240
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.9338862895965576,
      "learning_rate": 0.00047716976716144917,
      "loss": 0.202,
      "step": 241
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.3190581798553467,
      "learning_rate": 0.0004769747729897749,
      "loss": 0.1071,
      "step": 242
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.23796042799949646,
      "learning_rate": 0.0004767789898173806,
      "loss": 0.0659,
      "step": 243
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.19194231927394867,
      "learning_rate": 0.0004765824183248399,
      "loss": 0.0611,
      "step": 244
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.16703608632087708,
      "learning_rate": 0.0004763850591954668,
      "loss": 0.0855,
      "step": 245
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.3395439684391022,
      "learning_rate": 0.0004761869131153135,
      "loss": 0.0926,
      "step": 246
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.2820179760456085,
      "learning_rate": 0.0004759879807731673,
      "loss": 0.0508,
      "step": 247
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.20656561851501465,
      "learning_rate": 0.00047578826286054897,
      "loss": 0.068,
      "step": 248
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.4477837383747101,
      "learning_rate": 0.00047558776007171024,
      "loss": 0.0918,
      "step": 249
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.18997950851917267,
      "learning_rate": 0.0004753864731036307,
      "loss": 0.0734,
      "step": 250
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.2841518521308899,
      "learning_rate": 0.0004751844026560163,
      "loss": 0.1194,
      "step": 251
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.29770052433013916,
      "learning_rate": 0.0004749815494312963,
      "loss": 0.0996,
      "step": 252
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.2982254922389984,
      "learning_rate": 0.00047477791413462104,
      "loss": 0.0945,
      "step": 253
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.4625980854034424,
      "learning_rate": 0.00047457349747385936,
      "loss": 0.131,
      "step": 254
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.29756709933280945,
      "learning_rate": 0.00047436830015959653,
      "loss": 0.1057,
      "step": 255
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.19971434772014618,
      "learning_rate": 0.00047416232290513127,
      "loss": 0.0794,
      "step": 256
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.12171836197376251,
      "learning_rate": 0.0004739555664264736,
      "loss": 0.0527,
      "step": 257
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.23848529160022736,
      "learning_rate": 0.00047374803144234213,
      "loss": 0.134,
      "step": 258
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.12673752009868622,
      "learning_rate": 0.0004735397186741618,
      "loss": 0.0774,
      "step": 259
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.11961629241704941,
      "learning_rate": 0.00047333062884606116,
      "loss": 0.0661,
      "step": 260
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.18004140257835388,
      "learning_rate": 0.00047312076268487,
      "loss": 0.1132,
      "step": 261
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.1698005348443985,
      "learning_rate": 0.00047291012092011685,
      "loss": 0.057,
      "step": 262
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.1949334442615509,
      "learning_rate": 0.0004726987042840263,
      "loss": 0.0703,
      "step": 263
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.4016534686088562,
      "learning_rate": 0.0004724865135115163,
      "loss": 0.1178,
      "step": 264
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.36885496973991394,
      "learning_rate": 0.00047227354934019605,
      "loss": 0.1303,
      "step": 265
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.3214585483074188,
      "learning_rate": 0.00047205981251036334,
      "loss": 0.1019,
      "step": 266
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.15313082933425903,
      "learning_rate": 0.0004718453037650016,
      "loss": 0.0581,
      "step": 267
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.3251878321170807,
      "learning_rate": 0.0004716300238497775,
      "loss": 0.099,
      "step": 268
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.20356950163841248,
      "learning_rate": 0.0004714139735130388,
      "loss": 0.0767,
      "step": 269
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.2644464373588562,
      "learning_rate": 0.00047119715350581095,
      "loss": 0.1003,
      "step": 270
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.22035302221775055,
      "learning_rate": 0.000470979564581795,
      "loss": 0.0722,
      "step": 271
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5284466743469238,
      "learning_rate": 0.0004707612074973653,
      "loss": 0.1282,
      "step": 272
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.34032565355300903,
      "learning_rate": 0.0004705420830115658,
      "loss": 0.099,
      "step": 273
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.26527565717697144,
      "learning_rate": 0.00047032219188610836,
      "loss": 0.0911,
      "step": 274
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.2254990190267563,
      "learning_rate": 0.0004701015348853699,
      "loss": 0.0667,
      "step": 275
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.21334387362003326,
      "learning_rate": 0.0004698801127763895,
      "loss": 0.0659,
      "step": 276
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.2917044758796692,
      "learning_rate": 0.0004696579263288661,
      "loss": 0.1159,
      "step": 277
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.14027804136276245,
      "learning_rate": 0.00046943497631515526,
      "loss": 0.0323,
      "step": 278
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.3988366425037384,
      "learning_rate": 0.00046921126351026697,
      "loss": 0.0887,
      "step": 279
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.36629319190979004,
      "learning_rate": 0.00046898678869186297,
      "loss": 0.1079,
      "step": 280
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.35548141598701477,
      "learning_rate": 0.0004687615526402536,
      "loss": 0.1056,
      "step": 281
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.21030637621879578,
      "learning_rate": 0.0004685355561383956,
      "loss": 0.0717,
      "step": 282
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.24192889034748077,
      "learning_rate": 0.000468308799971889,
      "loss": 0.1047,
      "step": 283
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.16289295256137848,
      "learning_rate": 0.00046808128492897464,
      "loss": 0.0519,
      "step": 284
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.08938124030828476,
      "eval_runtime": 14.7518,
      "eval_samples_per_second": 32.335,
      "eval_steps_per_second": 8.135,
      "step": 284
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.23021583259105682,
      "learning_rate": 0.00046785301180053126,
      "loss": 0.1161,
      "step": 285
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.3577558398246765,
      "learning_rate": 0.0004676239813800729,
      "loss": 0.1239,
      "step": 286
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.15293735265731812,
      "learning_rate": 0.0004673941944637461,
      "loss": 0.0401,
      "step": 287
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.342631459236145,
      "learning_rate": 0.00046716365185032696,
      "loss": 0.1358,
      "step": 288
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.4987104833126068,
      "learning_rate": 0.0004669323543412186,
      "loss": 0.1312,
      "step": 289
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.21678434312343597,
      "learning_rate": 0.0004667003027404483,
      "loss": 0.0791,
      "step": 290
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.2781723141670227,
      "learning_rate": 0.00046646749785466464,
      "loss": 0.0809,
      "step": 291
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.3997693359851837,
      "learning_rate": 0.00046623394049313474,
      "loss": 0.0938,
      "step": 292
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.2478984147310257,
      "learning_rate": 0.00046599963146774136,
      "loss": 0.0671,
      "step": 293
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.35655421018600464,
      "learning_rate": 0.0004657645715929805,
      "loss": 0.107,
      "step": 294
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.41986069083213806,
      "learning_rate": 0.0004655287616859577,
      "loss": 0.1381,
      "step": 295
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.2831580340862274,
      "learning_rate": 0.00046529220256638626,
      "loss": 0.1012,
      "step": 296
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.2183172106742859,
      "learning_rate": 0.0004650548950565835,
      "loss": 0.0883,
      "step": 297
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.1485687792301178,
      "learning_rate": 0.0004648168399814684,
      "loss": 0.094,
      "step": 298
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.3192533552646637,
      "learning_rate": 0.0004645780381685586,
      "loss": 0.1144,
      "step": 299
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.20768460631370544,
      "learning_rate": 0.0004643384904479675,
      "loss": 0.1119,
      "step": 300
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.16704390943050385,
      "learning_rate": 0.00046409819765240147,
      "loss": 0.0852,
      "step": 301
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.33123648166656494,
      "learning_rate": 0.0004638571606171567,
      "loss": 0.1608,
      "step": 302
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.408978134393692,
      "learning_rate": 0.0004636153801801167,
      "loss": 0.0906,
      "step": 303
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.29201096296310425,
      "learning_rate": 0.00046337285718174896,
      "loss": 0.1237,
      "step": 304
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.45836058259010315,
      "learning_rate": 0.00046312959246510237,
      "loss": 0.0926,
      "step": 305
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.5405777096748352,
      "learning_rate": 0.0004628855868758041,
      "loss": 0.0727,
      "step": 306
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.3068138062953949,
      "learning_rate": 0.00046264084126205676,
      "loss": 0.1006,
      "step": 307
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.2990975081920624,
      "learning_rate": 0.00046239535647463534,
      "loss": 0.1033,
      "step": 308
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.2938540279865265,
      "learning_rate": 0.00046214913336688424,
      "loss": 0.1084,
      "step": 309
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.49840983748435974,
      "learning_rate": 0.00046190217279471466,
      "loss": 0.1066,
      "step": 310
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.4558626711368561,
      "learning_rate": 0.000461654475616601,
      "loss": 0.121,
      "step": 311
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.20964759588241577,
      "learning_rate": 0.0004614060426935786,
      "loss": 0.0843,
      "step": 312
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.2254151701927185,
      "learning_rate": 0.00046115687488923983,
      "loss": 0.0781,
      "step": 313
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.6117066740989685,
      "learning_rate": 0.0004609069730697322,
      "loss": 0.1208,
      "step": 314
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.5352897644042969,
      "learning_rate": 0.0004606563381037544,
      "loss": 0.1056,
      "step": 315
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.31001269817352295,
      "learning_rate": 0.00046040497086255385,
      "loss": 0.1213,
      "step": 316
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.22637054324150085,
      "learning_rate": 0.0004601528722199234,
      "loss": 0.105,
      "step": 317
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.20077432692050934,
      "learning_rate": 0.0004599000430521984,
      "loss": 0.0837,
      "step": 318
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.24702684581279755,
      "learning_rate": 0.0004596464842382534,
      "loss": 0.0695,
      "step": 319
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.253387987613678,
      "learning_rate": 0.0004593921966594997,
      "loss": 0.1184,
      "step": 320
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.2703799605369568,
      "learning_rate": 0.0004591371811998817,
      "loss": 0.117,
      "step": 321
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.23513701558113098,
      "learning_rate": 0.00045888143874587396,
      "loss": 0.1359,
      "step": 322
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.25604313611984253,
      "learning_rate": 0.00045862497018647833,
      "loss": 0.1018,
      "step": 323
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.16947636008262634,
      "learning_rate": 0.0004583677764132207,
      "loss": 0.0958,
      "step": 324
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.20054908096790314,
      "learning_rate": 0.0004581098583201478,
      "loss": 0.0803,
      "step": 325
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.12656472623348236,
      "learning_rate": 0.00045785121680382436,
      "loss": 0.0679,
      "step": 326
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.1423499882221222,
      "learning_rate": 0.0004575918527633297,
      "loss": 0.0959,
      "step": 327
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.36370569467544556,
      "learning_rate": 0.0004573317671002549,
      "loss": 0.1088,
      "step": 328
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.18775340914726257,
      "learning_rate": 0.0004570709607186995,
      "loss": 0.0905,
      "step": 329
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.14833571016788483,
      "learning_rate": 0.0004568094345252681,
      "loss": 0.0661,
      "step": 330
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.2987270653247833,
      "learning_rate": 0.00045654718942906794,
      "loss": 0.0872,
      "step": 331
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.21985827386379242,
      "learning_rate": 0.000456284226341705,
      "loss": 0.0882,
      "step": 332
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.2726268470287323,
      "learning_rate": 0.00045602054617728093,
      "loss": 0.0864,
      "step": 333
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.2882244884967804,
      "learning_rate": 0.00045575614985239057,
      "loss": 0.1032,
      "step": 334
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.427500456571579,
      "learning_rate": 0.0004554910382861178,
      "loss": 0.1309,
      "step": 335
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.43029338121414185,
      "learning_rate": 0.000455225212400033,
      "loss": 0.1071,
      "step": 336
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.2297673523426056,
      "learning_rate": 0.0004549586731181896,
      "loss": 0.0526,
      "step": 337
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4533613920211792,
      "learning_rate": 0.0004546914213671209,
      "loss": 0.1154,
      "step": 338
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3973630666732788,
      "learning_rate": 0.0004544234580758367,
      "loss": 0.0707,
      "step": 339
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.40036290884017944,
      "learning_rate": 0.0004541547841758207,
      "loss": 0.0932,
      "step": 340
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.4273395240306854,
      "learning_rate": 0.0004538854006010262,
      "loss": 0.1112,
      "step": 341
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.28109779953956604,
      "learning_rate": 0.0004536153082878738,
      "loss": 0.1003,
      "step": 342
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.21950216591358185,
      "learning_rate": 0.00045334450817524776,
      "loss": 0.0538,
      "step": 343
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.2968471646308899,
      "learning_rate": 0.00045307300120449263,
      "loss": 0.0775,
      "step": 344
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.1488364040851593,
      "learning_rate": 0.00045280078831941024,
      "loss": 0.0513,
      "step": 345
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.22750218212604523,
      "learning_rate": 0.00045252787046625624,
      "loss": 0.0943,
      "step": 346
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.3048767149448395,
      "learning_rate": 0.0004522542485937369,
      "loss": 0.079,
      "step": 347
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.33520030975341797,
      "learning_rate": 0.0004519799236530057,
      "loss": 0.1584,
      "step": 348
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.20777581632137299,
      "learning_rate": 0.00045170489659766003,
      "loss": 0.0903,
      "step": 349
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.1602245271205902,
      "learning_rate": 0.00045142916838373826,
      "loss": 0.0446,
      "step": 350
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.2512218952178955,
      "learning_rate": 0.0004511527399697158,
      "loss": 0.069,
      "step": 351
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.17349962890148163,
      "learning_rate": 0.0004508756123165021,
      "loss": 0.0765,
      "step": 352
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.26563215255737305,
      "learning_rate": 0.00045059778638743744,
      "loss": 0.0966,
      "step": 353
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.23987066745758057,
      "learning_rate": 0.00045031926314828926,
      "loss": 0.0702,
      "step": 354
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.21901372075080872,
      "learning_rate": 0.000450040043567249,
      "loss": 0.0457,
      "step": 355
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.24179872870445251,
      "learning_rate": 0.00044976012861492877,
      "loss": 0.0651,
      "step": 356
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.3544818162918091,
      "learning_rate": 0.0004494795192643578,
      "loss": 0.0622,
      "step": 357
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.4363332986831665,
      "learning_rate": 0.00044919821649097916,
      "loss": 0.0972,
      "step": 358
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.43788430094718933,
      "learning_rate": 0.0004489162212726465,
      "loss": 0.0843,
      "step": 359
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5084832906723022,
      "learning_rate": 0.00044863353458962044,
      "loss": 0.0888,
      "step": 360
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.44660842418670654,
      "learning_rate": 0.0004483501574245652,
      "loss": 0.113,
      "step": 361
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.7528813481330872,
      "learning_rate": 0.0004480660907625452,
      "loss": 0.0512,
      "step": 362
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9723535776138306,
      "learning_rate": 0.0004477813355910219,
      "loss": 0.1154,
      "step": 363
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.2641480565071106,
      "learning_rate": 0.0004474958928998498,
      "loss": 0.0575,
      "step": 364
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.12234170734882355,
      "learning_rate": 0.00044720976368127355,
      "loss": 0.0441,
      "step": 365
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.26976636052131653,
      "learning_rate": 0.00044692294892992416,
      "loss": 0.0676,
      "step": 366
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.22729526460170746,
      "learning_rate": 0.00044663544964281573,
      "loss": 0.098,
      "step": 367
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.2270442545413971,
      "learning_rate": 0.0004463472668193419,
      "loss": 0.0842,
      "step": 368
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.19249562919139862,
      "learning_rate": 0.0004460584014612724,
      "loss": 0.0537,
      "step": 369
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.22312623262405396,
      "learning_rate": 0.0004457688545727496,
      "loss": 0.0547,
      "step": 370
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.281658411026001,
      "learning_rate": 0.0004454786271602849,
      "loss": 0.089,
      "step": 371
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.49952250719070435,
      "learning_rate": 0.00044518772023275526,
      "loss": 0.1298,
      "step": 372
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.186232328414917,
      "learning_rate": 0.0004448961348013999,
      "loss": 0.0628,
      "step": 373
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.2980823814868927,
      "learning_rate": 0.0004446038718798166,
      "loss": 0.0828,
      "step": 374
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.3794187605381012,
      "learning_rate": 0.00044431093248395806,
      "loss": 0.0776,
      "step": 375
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.29262277483940125,
      "learning_rate": 0.0004440173176321287,
      "loss": 0.0924,
      "step": 376
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.30543988943099976,
      "learning_rate": 0.0004437230283449808,
      "loss": 0.1264,
      "step": 377
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.3436485826969147,
      "learning_rate": 0.0004434280656455111,
      "loss": 0.1066,
      "step": 378
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.23679965734481812,
      "learning_rate": 0.0004431324305590572,
      "loss": 0.075,
      "step": 379
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.4399561882019043,
      "learning_rate": 0.0004428361241132943,
      "loss": 0.1445,
      "step": 380
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.39203163981437683,
      "learning_rate": 0.0004425391473382309,
      "loss": 0.0995,
      "step": 381
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.4687665104866028,
      "learning_rate": 0.0004422415012662061,
      "loss": 0.1489,
      "step": 382
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.2634904086589813,
      "learning_rate": 0.00044194318693188526,
      "loss": 0.1164,
      "step": 383
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.23031170666217804,
      "learning_rate": 0.0004416442053722569,
      "loss": 0.0742,
      "step": 384
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.30467960238456726,
      "learning_rate": 0.00044134455762662894,
      "loss": 0.0984,
      "step": 385
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.16692829132080078,
      "learning_rate": 0.0004410442447366249,
      "loss": 0.0732,
      "step": 386
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.20100833475589752,
      "learning_rate": 0.00044074326774618065,
      "loss": 0.1082,
      "step": 387
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.29799607396125793,
      "learning_rate": 0.0004404416277015404,
      "loss": 0.0761,
      "step": 388
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.647639274597168,
      "learning_rate": 0.0004401393256512534,
      "loss": 0.1218,
      "step": 389
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.2610540986061096,
      "learning_rate": 0.00043983636264617013,
      "loss": 0.0923,
      "step": 390
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.4049086570739746,
      "learning_rate": 0.0004395327397394384,
      "loss": 0.1091,
      "step": 391
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.36092105507850647,
      "learning_rate": 0.00043922845798650034,
      "loss": 0.0927,
      "step": 392
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.542421281337738,
      "learning_rate": 0.00043892351844508805,
      "loss": 0.1014,
      "step": 393
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.291595995426178,
      "learning_rate": 0.0004386179221752202,
      "loss": 0.0902,
      "step": 394
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.17152707278728485,
      "learning_rate": 0.0004383116702391987,
      "loss": 0.0651,
      "step": 395
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.16654878854751587,
      "learning_rate": 0.00043800476370160416,
      "loss": 0.0824,
      "step": 396
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.18530108034610748,
      "learning_rate": 0.000437697203629293,
      "loss": 0.0549,
      "step": 397
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.5760988593101501,
      "learning_rate": 0.0004373889910913934,
      "loss": 0.0803,
      "step": 398
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.4253963232040405,
      "learning_rate": 0.00043708012715930154,
      "loss": 0.0728,
      "step": 399
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.7932385206222534,
      "learning_rate": 0.00043677061290667805,
      "loss": 0.1442,
      "step": 400
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.5904709696769714,
      "learning_rate": 0.00043646044940944407,
      "loss": 0.0999,
      "step": 401
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.9570127129554749,
      "learning_rate": 0.0004361496377457777,
      "loss": 0.1298,
      "step": 402
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.5049470663070679,
      "learning_rate": 0.00043583817899611017,
      "loss": 0.0263,
      "step": 403
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.589408814907074,
      "learning_rate": 0.00043552607424312195,
      "loss": 0.1051,
      "step": 404
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.43722283840179443,
      "learning_rate": 0.0004352133245717393,
      "loss": 0.0715,
      "step": 405
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.3537758588790894,
      "learning_rate": 0.00043489993106913036,
      "loss": 0.0322,
      "step": 406
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3382836580276489,
      "learning_rate": 0.000434585894824701,
      "loss": 0.0818,
      "step": 407
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.9946733713150024,
      "learning_rate": 0.00043427121693009164,
      "loss": 0.1536,
      "step": 408
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.9138526320457458,
      "learning_rate": 0.0004339558984791732,
      "loss": 0.1299,
      "step": 409
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.35993850231170654,
      "learning_rate": 0.0004336399405680432,
      "loss": 0.0654,
      "step": 410
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.30418309569358826,
      "learning_rate": 0.0004333233442950219,
      "loss": 0.1026,
      "step": 411
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.256728857755661,
      "learning_rate": 0.00043300611076064886,
      "loss": 0.083,
      "step": 412
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.3472314774990082,
      "learning_rate": 0.00043268824106767865,
      "loss": 0.0637,
      "step": 413
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.5615578293800354,
      "learning_rate": 0.00043236973632107735,
      "loss": 0.1028,
      "step": 414
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.35775747895240784,
      "learning_rate": 0.00043205059762801854,
      "loss": 0.0829,
      "step": 415
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.287270724773407,
      "learning_rate": 0.0004317308260978795,
      "loss": 0.0718,
      "step": 416
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.3237059414386749,
      "learning_rate": 0.00043141042284223737,
      "loss": 0.0797,
      "step": 417
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.2153153419494629,
      "learning_rate": 0.0004310893889748653,
      "loss": 0.0778,
      "step": 418
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.33600860834121704,
      "learning_rate": 0.00043076772561172845,
      "loss": 0.0594,
      "step": 419
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.8778895139694214,
      "learning_rate": 0.00043044543387098027,
      "loss": 0.1722,
      "step": 420
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.503434419631958,
      "learning_rate": 0.0004301225148729586,
      "loss": 0.1228,
      "step": 421
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3694842457771301,
      "learning_rate": 0.00042979896974018166,
      "loss": 0.1033,
      "step": 422
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.329818457365036,
      "learning_rate": 0.00042947479959734423,
      "loss": 0.0471,
      "step": 423
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.19436267018318176,
      "learning_rate": 0.0004291500055713138,
      "loss": 0.0409,
      "step": 424
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3269858658313751,
      "learning_rate": 0.0004288245887911263,
      "loss": 0.096,
      "step": 425
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3542991578578949,
      "learning_rate": 0.00042849855038798283,
      "loss": 0.0986,
      "step": 426
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.07792978733778,
      "eval_runtime": 14.8115,
      "eval_samples_per_second": 32.205,
      "eval_steps_per_second": 8.102,
      "step": 426
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.29685521125793457,
      "learning_rate": 0.00042817189149524517,
      "loss": 0.11,
      "step": 427
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.2116887867450714,
      "learning_rate": 0.00042784461324843194,
      "loss": 0.0686,
      "step": 428
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.4866883456707001,
      "learning_rate": 0.00042751671678521486,
      "loss": 0.0824,
      "step": 429
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.1293468475341797,
      "learning_rate": 0.00042718820324541475,
      "loss": 0.0464,
      "step": 430
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.3253125250339508,
      "learning_rate": 0.0004268590737709972,
      "loss": 0.0996,
      "step": 431
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.25559771060943604,
      "learning_rate": 0.00042652932950606917,
      "loss": 0.0545,
      "step": 432
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.2788093686103821,
      "learning_rate": 0.0004261989715968746,
      "loss": 0.0502,
      "step": 433
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.6902124285697937,
      "learning_rate": 0.00042586800119179046,
      "loss": 0.1598,
      "step": 434
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.4788605570793152,
      "learning_rate": 0.00042553641944132316,
      "loss": 0.1552,
      "step": 435
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.43495067954063416,
      "learning_rate": 0.00042520422749810395,
      "loss": 0.0907,
      "step": 436
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.3549440801143646,
      "learning_rate": 0.0004248714265168853,
      "loss": 0.1152,
      "step": 437
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.7210204601287842,
      "learning_rate": 0.00042453801765453687,
      "loss": 0.1891,
      "step": 438
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.4578750729560852,
      "learning_rate": 0.00042420400207004126,
      "loss": 0.1383,
      "step": 439
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.3323976993560791,
      "learning_rate": 0.00042386938092449036,
      "loss": 0.0936,
      "step": 440
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.15145371854305267,
      "learning_rate": 0.00042353415538108076,
      "loss": 0.0608,
      "step": 441
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.10744435340166092,
      "learning_rate": 0.00042319832660511037,
      "loss": 0.0865,
      "step": 442
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.13599476218223572,
      "learning_rate": 0.0004228618957639738,
      "loss": 0.0763,
      "step": 443
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.18250028789043427,
      "learning_rate": 0.00042252486402715865,
      "loss": 0.0813,
      "step": 444
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.5180188417434692,
      "learning_rate": 0.00042218723256624136,
      "loss": 0.1603,
      "step": 445
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.2943187355995178,
      "learning_rate": 0.000421849002554883,
      "loss": 0.1031,
      "step": 446
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.14898087084293365,
      "learning_rate": 0.0004215101751688253,
      "loss": 0.071,
      "step": 447
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.2951905131340027,
      "learning_rate": 0.00042117075158588663,
      "loss": 0.0772,
      "step": 448
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.39807453751564026,
      "learning_rate": 0.00042083073298595787,
      "loss": 0.0561,
      "step": 449
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.45217999815940857,
      "learning_rate": 0.0004204901205509981,
      "loss": 0.1076,
      "step": 450
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.24114732444286346,
      "learning_rate": 0.000420148915465031,
      "loss": 0.1169,
      "step": 451
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.6120204329490662,
      "learning_rate": 0.00041980711891413994,
      "loss": 0.1144,
      "step": 452
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.3900619447231293,
      "learning_rate": 0.0004194647320864646,
      "loss": 0.0806,
      "step": 453
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.3331635296344757,
      "learning_rate": 0.0004191217561721967,
      "loss": 0.0655,
      "step": 454
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.29893186688423157,
      "learning_rate": 0.0004187781923635753,
      "loss": 0.0482,
      "step": 455
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.20024164021015167,
      "learning_rate": 0.00041843404185488346,
      "loss": 0.0773,
      "step": 456
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.3644329905509949,
      "learning_rate": 0.0004180893058424435,
      "loss": 0.1062,
      "step": 457
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.5457159280776978,
      "learning_rate": 0.0004177439855246132,
      "loss": 0.1901,
      "step": 458
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.282032310962677,
      "learning_rate": 0.0004173980821017812,
      "loss": 0.0656,
      "step": 459
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.1957680881023407,
      "learning_rate": 0.00041705159677636334,
      "loss": 0.0725,
      "step": 460
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.2736223042011261,
      "learning_rate": 0.00041670453075279827,
      "loss": 0.0897,
      "step": 461
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.2145017832517624,
      "learning_rate": 0.0004163568852375431,
      "loss": 0.046,
      "step": 462
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.1434750258922577,
      "learning_rate": 0.00041600866143906947,
      "loss": 0.0483,
      "step": 463
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.2438279092311859,
      "learning_rate": 0.000415659860567859,
      "loss": 0.0935,
      "step": 464
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.24830487370491028,
      "learning_rate": 0.00041531048383639966,
      "loss": 0.1061,
      "step": 465
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.25185227394104004,
      "learning_rate": 0.000414960532459181,
      "loss": 0.082,
      "step": 466
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.391631156206131,
      "learning_rate": 0.00041461000765269,
      "loss": 0.1274,
      "step": 467
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.30484774708747864,
      "learning_rate": 0.0004142589106354071,
      "loss": 0.0672,
      "step": 468
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.2584599554538727,
      "learning_rate": 0.0004139072426278021,
      "loss": 0.0863,
      "step": 469
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.27182772755622864,
      "learning_rate": 0.0004135550048523292,
      "loss": 0.0996,
      "step": 470
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.2670001685619354,
      "learning_rate": 0.00041320219853342347,
      "loss": 0.0592,
      "step": 471
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.19571639597415924,
      "learning_rate": 0.0004128488248974962,
      "loss": 0.0618,
      "step": 472
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.436814546585083,
      "learning_rate": 0.00041249488517293095,
      "loss": 0.1131,
      "step": 473
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.21684250235557556,
      "learning_rate": 0.0004121403805900789,
      "loss": 0.0759,
      "step": 474
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.39313605427742004,
      "learning_rate": 0.0004117853123812549,
      "loss": 0.0992,
      "step": 475
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.3653202950954437,
      "learning_rate": 0.00041142968178073294,
      "loss": 0.099,
      "step": 476
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.36615628004074097,
      "learning_rate": 0.00041107349002474206,
      "loss": 0.06,
      "step": 477
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.2431243658065796,
      "learning_rate": 0.00041071673835146194,
      "loss": 0.0689,
      "step": 478
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.7869367599487305,
      "learning_rate": 0.00041035942800101864,
      "loss": 0.1308,
      "step": 479
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.2831230163574219,
      "learning_rate": 0.0004100015602154802,
      "loss": 0.087,
      "step": 480
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.3709629774093628,
      "learning_rate": 0.0004096431362388525,
      "loss": 0.0822,
      "step": 481
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.4082586467266083,
      "learning_rate": 0.0004092841573170748,
      "loss": 0.1114,
      "step": 482
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.2919554114341736,
      "learning_rate": 0.0004089246246980154,
      "loss": 0.1059,
      "step": 483
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.3750731945037842,
      "learning_rate": 0.0004085645396314673,
      "loss": 0.082,
      "step": 484
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.21013659238815308,
      "learning_rate": 0.000408203903369144,
      "loss": 0.0819,
      "step": 485
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.20771674811840057,
      "learning_rate": 0.00040784271716467503,
      "loss": 0.0687,
      "step": 486
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.157434344291687,
      "learning_rate": 0.00040748098227360154,
      "loss": 0.0826,
      "step": 487
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.40467727184295654,
      "learning_rate": 0.000407118699953372,
      "loss": 0.1131,
      "step": 488
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.17521728575229645,
      "learning_rate": 0.0004067558714633378,
      "loss": 0.116,
      "step": 489
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.2975709140300751,
      "learning_rate": 0.0004063924980647492,
      "loss": 0.0787,
      "step": 490
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.22513332962989807,
      "learning_rate": 0.0004060285810207503,
      "loss": 0.0754,
      "step": 491
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.2939409613609314,
      "learning_rate": 0.00040566412159637514,
      "loss": 0.0505,
      "step": 492
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.21415212750434875,
      "learning_rate": 0.000405299121058543,
      "loss": 0.0486,
      "step": 493
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.24846945703029633,
      "learning_rate": 0.00040493358067605445,
      "loss": 0.0645,
      "step": 494
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.42928287386894226,
      "learning_rate": 0.00040456750171958655,
      "loss": 0.1455,
      "step": 495
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.30920714139938354,
      "learning_rate": 0.0004042008854616883,
      "loss": 0.0743,
      "step": 496
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.43211719393730164,
      "learning_rate": 0.00040383373317677687,
      "loss": 0.1037,
      "step": 497
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.49942275881767273,
      "learning_rate": 0.00040346604614113215,
      "loss": 0.123,
      "step": 498
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.18615621328353882,
      "learning_rate": 0.00040309782563289353,
      "loss": 0.0783,
      "step": 499
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.22238926589488983,
      "learning_rate": 0.0004027290729320545,
      "loss": 0.0698,
      "step": 500
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.31746548414230347,
      "learning_rate": 0.0004023597893204586,
      "loss": 0.1682,
      "step": 501
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.19328100979328156,
      "learning_rate": 0.00040198997608179477,
      "loss": 0.1028,
      "step": 502
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.15466806292533875,
      "learning_rate": 0.00040161963450159333,
      "loss": 0.065,
      "step": 503
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.3000398874282837,
      "learning_rate": 0.00040124876586722103,
      "loss": 0.1071,
      "step": 504
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.16753748059272766,
      "learning_rate": 0.00040087737146787654,
      "loss": 0.056,
      "step": 505
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.17570586502552032,
      "learning_rate": 0.00040050545259458654,
      "loss": 0.0732,
      "step": 506
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.19240190088748932,
      "learning_rate": 0.00040013301054020055,
      "loss": 0.0444,
      "step": 507
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.23935984075069427,
      "learning_rate": 0.00039976004659938714,
      "loss": 0.0583,
      "step": 508
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.22633028030395508,
      "learning_rate": 0.00039938656206862857,
      "loss": 0.065,
      "step": 509
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.18621531128883362,
      "learning_rate": 0.000399012558246217,
      "loss": 0.0489,
      "step": 510
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.37711310386657715,
      "learning_rate": 0.0003986380364322498,
      "loss": 0.1367,
      "step": 511
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.26448771357536316,
      "learning_rate": 0.00039826299792862475,
      "loss": 0.076,
      "step": 512
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.22461633384227753,
      "learning_rate": 0.00039788744403903604,
      "loss": 0.0734,
      "step": 513
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.23908165097236633,
      "learning_rate": 0.00039751137606896907,
      "loss": 0.0718,
      "step": 514
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.37807080149650574,
      "learning_rate": 0.00039713479532569646,
      "loss": 0.1495,
      "step": 515
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.16840259730815887,
      "learning_rate": 0.00039675770311827337,
      "loss": 0.0491,
      "step": 516
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.35179728269577026,
      "learning_rate": 0.00039638010075753274,
      "loss": 0.0839,
      "step": 517
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.3631207048892975,
      "learning_rate": 0.00039600198955608084,
      "loss": 0.1348,
      "step": 518
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.38650691509246826,
      "learning_rate": 0.00039562337082829304,
      "loss": 0.15,
      "step": 519
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.2523843050003052,
      "learning_rate": 0.00039524424589030866,
      "loss": 0.1172,
      "step": 520
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.2690166234970093,
      "learning_rate": 0.00039486461606002686,
      "loss": 0.0619,
      "step": 521
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.31193405389785767,
      "learning_rate": 0.0003944844826571018,
      "loss": 0.0834,
      "step": 522
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.21751855313777924,
      "learning_rate": 0.00039410384700293814,
      "loss": 0.068,
      "step": 523
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.34191232919692993,
      "learning_rate": 0.0003937227104206865,
      "loss": 0.1337,
      "step": 524
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.34457269310951233,
      "learning_rate": 0.0003933410742352388,
      "loss": 0.0929,
      "step": 525
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.22599942982196808,
      "learning_rate": 0.0003929589397732236,
      "loss": 0.0899,
      "step": 526
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.23162932693958282,
      "learning_rate": 0.0003925763083630017,
      "loss": 0.0869,
      "step": 527
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.19502510130405426,
      "learning_rate": 0.00039219318133466104,
      "loss": 0.0834,
      "step": 528
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.2539670169353485,
      "learning_rate": 0.0003918095600200128,
      "loss": 0.0589,
      "step": 529
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.15578749775886536,
      "learning_rate": 0.00039142544575258614,
      "loss": 0.0471,
      "step": 530
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.41006144881248474,
      "learning_rate": 0.00039104083986762396,
      "loss": 0.1215,
      "step": 531
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.3161672055721283,
      "learning_rate": 0.00039065574370207785,
      "loss": 0.0599,
      "step": 532
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.2556127607822418,
      "learning_rate": 0.00039027015859460394,
      "loss": 0.0882,
      "step": 533
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.5484500527381897,
      "learning_rate": 0.000389884085885558,
      "loss": 0.1342,
      "step": 534
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.3688224256038666,
      "learning_rate": 0.0003894975269169906,
      "loss": 0.062,
      "step": 535
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.6328185796737671,
      "learning_rate": 0.0003891104830326427,
      "loss": 0.1068,
      "step": 536
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.5094593167304993,
      "learning_rate": 0.00038872295557794103,
      "loss": 0.0593,
      "step": 537
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.44920942187309265,
      "learning_rate": 0.0003883349458999931,
      "loss": 0.1134,
      "step": 538
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.25559201836586,
      "learning_rate": 0.0003879464553475828,
      "loss": 0.0842,
      "step": 539
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.24992522597312927,
      "learning_rate": 0.0003875574852711656,
      "loss": 0.0684,
      "step": 540
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.7482407093048096,
      "learning_rate": 0.0003871680370228639,
      "loss": 0.1698,
      "step": 541
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.42716777324676514,
      "learning_rate": 0.00038677811195646233,
      "loss": 0.1335,
      "step": 542
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5867021083831787,
      "learning_rate": 0.0003863877114274029,
      "loss": 0.153,
      "step": 543
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.14882822334766388,
      "learning_rate": 0.0003859968367927805,
      "loss": 0.0548,
      "step": 544
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.16213174164295197,
      "learning_rate": 0.0003856054894113381,
      "loss": 0.0859,
      "step": 545
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.13216906785964966,
      "learning_rate": 0.0003852136706434619,
      "loss": 0.0837,
      "step": 546
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.28230682015419006,
      "learning_rate": 0.00038482138185117685,
      "loss": 0.0746,
      "step": 547
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.15776745975017548,
      "learning_rate": 0.0003844286243981417,
      "loss": 0.0758,
      "step": 548
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.38748612999916077,
      "learning_rate": 0.0003840353996496444,
      "loss": 0.0946,
      "step": 549
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.4377779960632324,
      "learning_rate": 0.0003836417089725971,
      "loss": 0.078,
      "step": 550
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.4776962101459503,
      "learning_rate": 0.0003832475537355319,
      "loss": 0.0996,
      "step": 551
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.16078083217144012,
      "learning_rate": 0.00038285293530859553,
      "loss": 0.0813,
      "step": 552
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.19620949029922485,
      "learning_rate": 0.00038245785506354514,
      "loss": 0.0716,
      "step": 553
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.23539945483207703,
      "learning_rate": 0.0003820623143737427,
      "loss": 0.0727,
      "step": 554
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.2797366678714752,
      "learning_rate": 0.0003816663146141514,
      "loss": 0.0307,
      "step": 555
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.31704849004745483,
      "learning_rate": 0.00038126985716132976,
      "loss": 0.0522,
      "step": 556
    },
    {
      "epoch": 0.99,
      "grad_norm": 1.038294792175293,
      "learning_rate": 0.00038087294339342765,
      "loss": 0.1602,
      "step": 557
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.39535316824913025,
      "learning_rate": 0.00038047557469018077,
      "loss": 0.0672,
      "step": 558
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.5337291359901428,
      "learning_rate": 0.00038007775243290666,
      "loss": 0.238,
      "step": 559
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.7618711590766907,
      "learning_rate": 0.0003796794780044992,
      "loss": 0.0741,
      "step": 560
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.3507292568683624,
      "learning_rate": 0.0003792807527894242,
      "loss": 0.1035,
      "step": 561
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.29699352383613586,
      "learning_rate": 0.00037888157817371455,
      "loss": 0.0732,
      "step": 562
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1690889596939087,
      "learning_rate": 0.0003784819555449651,
      "loss": 0.0625,
      "step": 563
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.28516581654548645,
      "learning_rate": 0.0003780818862923284,
      "loss": 0.0705,
      "step": 564
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3408360481262207,
      "learning_rate": 0.00037768137180650913,
      "loss": 0.1025,
      "step": 565
    }
  ],
  "logging_steps": 1,
  "max_steps": 1695,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 565,
  "total_flos": 5.169945694856806e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}