{
  "best_metric": 0.6085956692695618,
  "best_model_checkpoint": "outputs/checkpoint-544",
  "epoch": 1.0055452865064696,
  "eval_steps": 136,
  "global_step": 544,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018484288354898336,
      "grad_norm": 0.466289758682251,
      "learning_rate": 0.001,
      "loss": 1.4884,
      "step": 1
    },
    {
      "epoch": 0.0036968576709796672,
      "grad_norm": 0.15260683000087738,
      "learning_rate": 0.001,
      "loss": 1.2641,
      "step": 2
    },
    {
      "epoch": 0.005545286506469501,
      "grad_norm": 2.4310109615325928,
      "learning_rate": 0.001,
      "loss": 0.8826,
      "step": 3
    },
    {
      "epoch": 0.0073937153419593345,
      "grad_norm": 0.3376069664955139,
      "learning_rate": 0.001,
      "loss": 0.9718,
      "step": 4
    },
    {
      "epoch": 0.009242144177449169,
      "grad_norm": 0.5089592337608337,
      "learning_rate": 0.001,
      "loss": 1.0333,
      "step": 5
    },
    {
      "epoch": 0.011090573012939002,
      "grad_norm": 0.7866702079772949,
      "learning_rate": 0.001,
      "loss": 0.7162,
      "step": 6
    },
    {
      "epoch": 0.012939001848428836,
      "grad_norm": 0.2517491579055786,
      "learning_rate": 0.001,
      "loss": 0.7631,
      "step": 7
    },
    {
      "epoch": 0.014787430683918669,
      "grad_norm": 0.306551992893219,
      "learning_rate": 0.001,
      "loss": 0.6545,
      "step": 8
    },
    {
      "epoch": 0.0166358595194085,
      "grad_norm": 0.32659947872161865,
      "learning_rate": 0.001,
      "loss": 0.5165,
      "step": 9
    },
    {
      "epoch": 0.018484288354898338,
      "grad_norm": 0.30095258355140686,
      "learning_rate": 0.001,
      "loss": 0.6372,
      "step": 10
    },
    {
      "epoch": 0.02033271719038817,
      "grad_norm": 0.33985891938209534,
      "learning_rate": 0.001,
      "loss": 0.8448,
      "step": 11
    },
    {
      "epoch": 0.022181146025878003,
      "grad_norm": 0.42997440695762634,
      "learning_rate": 0.001,
      "loss": 0.8519,
      "step": 12
    },
    {
      "epoch": 0.024029574861367836,
      "grad_norm": 0.4363529682159424,
      "learning_rate": 0.001,
      "loss": 0.7915,
      "step": 13
    },
    {
      "epoch": 0.025878003696857672,
      "grad_norm": 0.2837740182876587,
      "learning_rate": 0.001,
      "loss": 0.5573,
      "step": 14
    },
    {
      "epoch": 0.027726432532347505,
      "grad_norm": 0.33749231696128845,
      "learning_rate": 0.001,
      "loss": 0.6843,
      "step": 15
    },
    {
      "epoch": 0.029574861367837338,
      "grad_norm": 0.6295365691184998,
      "learning_rate": 0.001,
      "loss": 0.6791,
      "step": 16
    },
    {
      "epoch": 0.031423290203327174,
      "grad_norm": 0.2831462323665619,
      "learning_rate": 0.001,
      "loss": 0.6832,
      "step": 17
    },
    {
      "epoch": 0.033271719038817,
      "grad_norm": 0.5176781415939331,
      "learning_rate": 0.001,
      "loss": 0.4944,
      "step": 18
    },
    {
      "epoch": 0.03512014787430684,
      "grad_norm": 0.5044294595718384,
      "learning_rate": 0.001,
      "loss": 0.8668,
      "step": 19
    },
    {
      "epoch": 0.036968576709796676,
      "grad_norm": 0.27560847997665405,
      "learning_rate": 0.001,
      "loss": 0.697,
      "step": 20
    },
    {
      "epoch": 0.038817005545286505,
      "grad_norm": 2.1971335411071777,
      "learning_rate": 0.001,
      "loss": 0.6876,
      "step": 21
    },
    {
      "epoch": 0.04066543438077634,
      "grad_norm": 0.4692804217338562,
      "learning_rate": 0.001,
      "loss": 0.6055,
      "step": 22
    },
    {
      "epoch": 0.04251386321626617,
      "grad_norm": 1.2793192863464355,
      "learning_rate": 0.001,
      "loss": 0.8302,
      "step": 23
    },
    {
      "epoch": 0.04436229205175601,
      "grad_norm": 0.7404688000679016,
      "learning_rate": 0.001,
      "loss": 0.4546,
      "step": 24
    },
    {
      "epoch": 0.04621072088724584,
      "grad_norm": 0.2830832600593567,
      "learning_rate": 0.001,
      "loss": 0.6068,
      "step": 25
    },
    {
      "epoch": 0.04805914972273567,
      "grad_norm": 0.3706754744052887,
      "learning_rate": 0.001,
      "loss": 0.5629,
      "step": 26
    },
    {
      "epoch": 0.04990757855822551,
      "grad_norm": 0.5734543800354004,
      "learning_rate": 0.001,
      "loss": 0.7772,
      "step": 27
    },
    {
      "epoch": 0.051756007393715345,
      "grad_norm": 0.4173612594604492,
      "learning_rate": 0.001,
      "loss": 0.7023,
      "step": 28
    },
    {
      "epoch": 0.053604436229205174,
      "grad_norm": 0.35146352648735046,
      "learning_rate": 0.001,
      "loss": 0.7729,
      "step": 29
    },
    {
      "epoch": 0.05545286506469501,
      "grad_norm": 0.3884046673774719,
      "learning_rate": 0.001,
      "loss": 0.7233,
      "step": 30
    },
    {
      "epoch": 0.05730129390018484,
      "grad_norm": 0.34868955612182617,
      "learning_rate": 0.001,
      "loss": 0.5834,
      "step": 31
    },
    {
      "epoch": 0.059149722735674676,
      "grad_norm": 1.9348665475845337,
      "learning_rate": 0.001,
      "loss": 0.6,
      "step": 32
    },
    {
      "epoch": 0.06099815157116451,
      "grad_norm": 0.49200278520584106,
      "learning_rate": 0.001,
      "loss": 0.4783,
      "step": 33
    },
    {
      "epoch": 0.06284658040665435,
      "grad_norm": 0.4063400626182556,
      "learning_rate": 0.001,
      "loss": 0.5797,
      "step": 34
    },
    {
      "epoch": 0.06469500924214418,
      "grad_norm": 0.4601685702800751,
      "learning_rate": 0.001,
      "loss": 0.5789,
      "step": 35
    },
    {
      "epoch": 0.066543438077634,
      "grad_norm": 0.5618835687637329,
      "learning_rate": 0.001,
      "loss": 0.7446,
      "step": 36
    },
    {
      "epoch": 0.06839186691312385,
      "grad_norm": 0.5381736755371094,
      "learning_rate": 0.001,
      "loss": 1.1037,
      "step": 37
    },
    {
      "epoch": 0.07024029574861368,
      "grad_norm": 0.579923689365387,
      "learning_rate": 0.001,
      "loss": 0.5367,
      "step": 38
    },
    {
      "epoch": 0.07208872458410351,
      "grad_norm": 0.4076865613460541,
      "learning_rate": 0.001,
      "loss": 0.6835,
      "step": 39
    },
    {
      "epoch": 0.07393715341959335,
      "grad_norm": 0.3602221608161926,
      "learning_rate": 0.001,
      "loss": 0.5843,
      "step": 40
    },
    {
      "epoch": 0.07578558225508318,
      "grad_norm": 0.4595842957496643,
      "learning_rate": 0.001,
      "loss": 0.8391,
      "step": 41
    },
    {
      "epoch": 0.07763401109057301,
      "grad_norm": 1.456554651260376,
      "learning_rate": 0.001,
      "loss": 0.8826,
      "step": 42
    },
    {
      "epoch": 0.07948243992606285,
      "grad_norm": 0.40481042861938477,
      "learning_rate": 0.001,
      "loss": 0.6189,
      "step": 43
    },
    {
      "epoch": 0.08133086876155268,
      "grad_norm": 2.4103527069091797,
      "learning_rate": 0.001,
      "loss": 0.7887,
      "step": 44
    },
    {
      "epoch": 0.08317929759704251,
      "grad_norm": 0.42522993683815,
      "learning_rate": 0.001,
      "loss": 0.6804,
      "step": 45
    },
    {
      "epoch": 0.08502772643253234,
      "grad_norm": 0.5652860999107361,
      "learning_rate": 0.001,
      "loss": 0.5217,
      "step": 46
    },
    {
      "epoch": 0.08687615526802218,
      "grad_norm": 0.6977353096008301,
      "learning_rate": 0.001,
      "loss": 0.7222,
      "step": 47
    },
    {
      "epoch": 0.08872458410351201,
      "grad_norm": 0.49619829654693604,
      "learning_rate": 0.001,
      "loss": 0.8871,
      "step": 48
    },
    {
      "epoch": 0.09057301293900184,
      "grad_norm": 0.3837599456310272,
      "learning_rate": 0.001,
      "loss": 0.745,
      "step": 49
    },
    {
      "epoch": 0.09242144177449169,
      "grad_norm": 0.35798409581184387,
      "learning_rate": 0.001,
      "loss": 0.7044,
      "step": 50
    },
    {
      "epoch": 0.09426987060998152,
      "grad_norm": 0.3777969777584076,
      "learning_rate": 0.001,
      "loss": 0.5723,
      "step": 51
    },
    {
      "epoch": 0.09611829944547134,
      "grad_norm": 0.35432809591293335,
      "learning_rate": 0.001,
      "loss": 0.6851,
      "step": 52
    },
    {
      "epoch": 0.09796672828096119,
      "grad_norm": 0.4954202175140381,
      "learning_rate": 0.001,
      "loss": 0.8028,
      "step": 53
    },
    {
      "epoch": 0.09981515711645102,
      "grad_norm": 0.3448912501335144,
      "learning_rate": 0.001,
      "loss": 0.6723,
      "step": 54
    },
    {
      "epoch": 0.10166358595194085,
      "grad_norm": 0.4123232960700989,
      "learning_rate": 0.001,
      "loss": 0.6049,
      "step": 55
    },
    {
      "epoch": 0.10351201478743069,
      "grad_norm": 0.37372708320617676,
      "learning_rate": 0.001,
      "loss": 0.5747,
      "step": 56
    },
    {
      "epoch": 0.10536044362292052,
      "grad_norm": 0.4807383120059967,
      "learning_rate": 0.001,
      "loss": 0.6363,
      "step": 57
    },
    {
      "epoch": 0.10720887245841035,
      "grad_norm": 0.8781284093856812,
      "learning_rate": 0.001,
      "loss": 2.1231,
      "step": 58
    },
    {
      "epoch": 0.10905730129390019,
      "grad_norm": 0.5836363434791565,
      "learning_rate": 0.001,
      "loss": 0.7727,
      "step": 59
    },
    {
      "epoch": 0.11090573012939002,
      "grad_norm": 0.41094064712524414,
      "learning_rate": 0.001,
      "loss": 0.6618,
      "step": 60
    },
    {
      "epoch": 0.11275415896487985,
      "grad_norm": 0.4478781521320343,
      "learning_rate": 0.001,
      "loss": 0.73,
      "step": 61
    },
    {
      "epoch": 0.11460258780036968,
      "grad_norm": 0.36589401960372925,
      "learning_rate": 0.001,
      "loss": 0.5947,
      "step": 62
    },
    {
      "epoch": 0.11645101663585952,
      "grad_norm": 0.5363914966583252,
      "learning_rate": 0.001,
      "loss": 0.5481,
      "step": 63
    },
    {
      "epoch": 0.11829944547134935,
      "grad_norm": 0.42670416831970215,
      "learning_rate": 0.001,
      "loss": 0.508,
      "step": 64
    },
    {
      "epoch": 0.12014787430683918,
      "grad_norm": 0.7648505568504333,
      "learning_rate": 0.001,
      "loss": 0.6343,
      "step": 65
    },
    {
      "epoch": 0.12199630314232902,
      "grad_norm": 0.4689379334449768,
      "learning_rate": 0.001,
      "loss": 0.7469,
      "step": 66
    },
    {
      "epoch": 0.12384473197781885,
      "grad_norm": 0.44720444083213806,
      "learning_rate": 0.001,
      "loss": 0.6952,
      "step": 67
    },
    {
      "epoch": 0.1256931608133087,
      "grad_norm": 0.35768693685531616,
      "learning_rate": 0.001,
      "loss": 0.432,
      "step": 68
    },
    {
      "epoch": 0.12754158964879853,
      "grad_norm": 0.4105698764324188,
      "learning_rate": 0.001,
      "loss": 0.6861,
      "step": 69
    },
    {
      "epoch": 0.12939001848428835,
      "grad_norm": 0.38207560777664185,
      "learning_rate": 0.001,
      "loss": 0.5908,
      "step": 70
    },
    {
      "epoch": 0.13123844731977818,
      "grad_norm": 0.46701478958129883,
      "learning_rate": 0.001,
      "loss": 0.6832,
      "step": 71
    },
    {
      "epoch": 0.133086876155268,
      "grad_norm": 0.501502513885498,
      "learning_rate": 0.001,
      "loss": 0.7041,
      "step": 72
    },
    {
      "epoch": 0.13493530499075784,
      "grad_norm": 0.3278079926967621,
      "learning_rate": 0.001,
      "loss": 0.4946,
      "step": 73
    },
    {
      "epoch": 0.1367837338262477,
      "grad_norm": 0.4573265612125397,
      "learning_rate": 0.001,
      "loss": 0.6106,
      "step": 74
    },
    {
      "epoch": 0.13863216266173753,
      "grad_norm": 0.37268367409706116,
      "learning_rate": 0.001,
      "loss": 0.4687,
      "step": 75
    },
    {
      "epoch": 0.14048059149722736,
      "grad_norm": 0.41542476415634155,
      "learning_rate": 0.001,
      "loss": 0.7345,
      "step": 76
    },
    {
      "epoch": 0.1423290203327172,
      "grad_norm": 0.36338284611701965,
      "learning_rate": 0.001,
      "loss": 0.5258,
      "step": 77
    },
    {
      "epoch": 0.14417744916820702,
      "grad_norm": 0.35523292422294617,
      "learning_rate": 0.001,
      "loss": 0.5006,
      "step": 78
    },
    {
      "epoch": 0.14602587800369685,
      "grad_norm": 0.7458345293998718,
      "learning_rate": 0.001,
      "loss": 1.6438,
      "step": 79
    },
    {
      "epoch": 0.1478743068391867,
      "grad_norm": 0.4105502963066101,
      "learning_rate": 0.001,
      "loss": 0.5162,
      "step": 80
    },
    {
      "epoch": 0.14972273567467653,
      "grad_norm": 0.4603978395462036,
      "learning_rate": 0.001,
      "loss": 0.7375,
      "step": 81
    },
    {
      "epoch": 0.15157116451016636,
      "grad_norm": 0.3389419913291931,
      "learning_rate": 0.001,
      "loss": 0.4315,
      "step": 82
    },
    {
      "epoch": 0.1534195933456562,
      "grad_norm": 0.4641773998737335,
      "learning_rate": 0.001,
      "loss": 0.5741,
      "step": 83
    },
    {
      "epoch": 0.15526802218114602,
      "grad_norm": 0.7335869073867798,
      "learning_rate": 0.001,
      "loss": 0.6726,
      "step": 84
    },
    {
      "epoch": 0.15711645101663585,
      "grad_norm": 0.45697247982025146,
      "learning_rate": 0.001,
      "loss": 0.6194,
      "step": 85
    },
    {
      "epoch": 0.1589648798521257,
      "grad_norm": 0.5353591442108154,
      "learning_rate": 0.001,
      "loss": 0.6411,
      "step": 86
    },
    {
      "epoch": 0.16081330868761554,
      "grad_norm": 0.5396345257759094,
      "learning_rate": 0.001,
      "loss": 0.6453,
      "step": 87
    },
    {
      "epoch": 0.16266173752310537,
      "grad_norm": 0.5480281114578247,
      "learning_rate": 0.001,
      "loss": 0.6838,
      "step": 88
    },
    {
      "epoch": 0.1645101663585952,
      "grad_norm": 0.455941379070282,
      "learning_rate": 0.001,
      "loss": 0.58,
      "step": 89
    },
    {
      "epoch": 0.16635859519408502,
      "grad_norm": 0.8435553312301636,
      "learning_rate": 0.001,
      "loss": 0.8912,
      "step": 90
    },
    {
      "epoch": 0.16820702402957485,
      "grad_norm": 0.44801416993141174,
      "learning_rate": 0.001,
      "loss": 0.6285,
      "step": 91
    },
    {
      "epoch": 0.17005545286506468,
      "grad_norm": 0.4071008563041687,
      "learning_rate": 0.001,
      "loss": 0.6715,
      "step": 92
    },
    {
      "epoch": 0.17190388170055454,
      "grad_norm": 0.41972634196281433,
      "learning_rate": 0.001,
      "loss": 0.453,
      "step": 93
    },
    {
      "epoch": 0.17375231053604437,
      "grad_norm": 0.60628741979599,
      "learning_rate": 0.001,
      "loss": 0.7723,
      "step": 94
    },
    {
      "epoch": 0.1756007393715342,
      "grad_norm": 0.4178489148616791,
      "learning_rate": 0.001,
      "loss": 0.4684,
      "step": 95
    },
    {
      "epoch": 0.17744916820702403,
      "grad_norm": 0.5033894777297974,
      "learning_rate": 0.001,
      "loss": 0.6145,
      "step": 96
    },
    {
      "epoch": 0.17929759704251386,
      "grad_norm": 0.6618285179138184,
      "learning_rate": 0.001,
      "loss": 0.9387,
      "step": 97
    },
    {
      "epoch": 0.18114602587800369,
      "grad_norm": 0.47585925459861755,
      "learning_rate": 0.001,
      "loss": 0.7797,
      "step": 98
    },
    {
      "epoch": 0.18299445471349354,
      "grad_norm": 0.41978687047958374,
      "learning_rate": 0.001,
      "loss": 0.5475,
      "step": 99
    },
    {
      "epoch": 0.18484288354898337,
      "grad_norm": 0.5080726742744446,
      "learning_rate": 0.001,
      "loss": 0.5243,
      "step": 100
    },
    {
      "epoch": 0.1866913123844732,
      "grad_norm": 0.38001152873039246,
      "learning_rate": 0.001,
      "loss": 0.532,
      "step": 101
    },
    {
      "epoch": 0.18853974121996303,
      "grad_norm": 0.5791141986846924,
      "learning_rate": 0.001,
      "loss": 0.7756,
      "step": 102
    },
    {
      "epoch": 0.19038817005545286,
      "grad_norm": 0.42902910709381104,
      "learning_rate": 0.001,
      "loss": 0.6425,
      "step": 103
    },
    {
      "epoch": 0.1922365988909427,
      "grad_norm": 0.5157350301742554,
      "learning_rate": 0.001,
      "loss": 0.819,
      "step": 104
    },
    {
      "epoch": 0.19408502772643252,
      "grad_norm": 12.421481132507324,
      "learning_rate": 0.001,
      "loss": 0.8929,
      "step": 105
    },
    {
      "epoch": 0.19593345656192238,
      "grad_norm": 0.5132973790168762,
      "learning_rate": 0.001,
      "loss": 0.6348,
      "step": 106
    },
    {
      "epoch": 0.1977818853974122,
      "grad_norm": 0.4973335862159729,
      "learning_rate": 0.001,
      "loss": 0.6071,
      "step": 107
    },
    {
      "epoch": 0.19963031423290203,
      "grad_norm": 0.326150119304657,
      "learning_rate": 0.001,
      "loss": 0.6531,
      "step": 108
    },
    {
      "epoch": 0.20147874306839186,
      "grad_norm": 0.4327104985713959,
      "learning_rate": 0.001,
      "loss": 0.6975,
      "step": 109
    },
    {
      "epoch": 0.2033271719038817,
      "grad_norm": 0.5976394414901733,
      "learning_rate": 0.001,
      "loss": 0.7276,
      "step": 110
    },
    {
      "epoch": 0.20517560073937152,
      "grad_norm": 0.35819554328918457,
      "learning_rate": 0.001,
      "loss": 0.5249,
      "step": 111
    },
    {
      "epoch": 0.20702402957486138,
      "grad_norm": 0.35644710063934326,
      "learning_rate": 0.001,
      "loss": 0.4523,
      "step": 112
    },
    {
      "epoch": 0.2088724584103512,
      "grad_norm": 0.45812854170799255,
      "learning_rate": 0.001,
      "loss": 0.7442,
      "step": 113
    },
    {
      "epoch": 0.21072088724584104,
      "grad_norm": 0.5240729451179504,
      "learning_rate": 0.001,
      "loss": 0.6039,
      "step": 114
    },
    {
      "epoch": 0.21256931608133087,
      "grad_norm": 0.6027355790138245,
      "learning_rate": 0.001,
      "loss": 0.7314,
      "step": 115
    },
    {
      "epoch": 0.2144177449168207,
      "grad_norm": 0.4197920560836792,
      "learning_rate": 0.001,
      "loss": 0.644,
      "step": 116
    },
    {
      "epoch": 0.21626617375231053,
      "grad_norm": 0.5917842388153076,
      "learning_rate": 0.001,
      "loss": 0.6872,
      "step": 117
    },
    {
      "epoch": 0.21811460258780038,
      "grad_norm": 0.49236243963241577,
      "learning_rate": 0.001,
      "loss": 0.9002,
      "step": 118
    },
    {
      "epoch": 0.2199630314232902,
      "grad_norm": 0.6250895857810974,
      "learning_rate": 0.001,
      "loss": 0.6905,
      "step": 119
    },
    {
      "epoch": 0.22181146025878004,
      "grad_norm": 0.5853796005249023,
      "learning_rate": 0.001,
      "loss": 0.7602,
      "step": 120
    },
    {
      "epoch": 0.22365988909426987,
      "grad_norm": 0.5543091297149658,
      "learning_rate": 0.001,
      "loss": 0.7356,
      "step": 121
    },
    {
      "epoch": 0.2255083179297597,
      "grad_norm": 0.4340505003929138,
      "learning_rate": 0.001,
      "loss": 0.6715,
      "step": 122
    },
    {
      "epoch": 0.22735674676524953,
      "grad_norm": 0.4405982792377472,
      "learning_rate": 0.001,
      "loss": 0.6898,
      "step": 123
    },
    {
      "epoch": 0.22920517560073936,
      "grad_norm": 0.5105734467506409,
      "learning_rate": 0.001,
      "loss": 0.7762,
      "step": 124
    },
    {
      "epoch": 0.23105360443622922,
      "grad_norm": 0.4798790216445923,
      "learning_rate": 0.001,
      "loss": 0.5982,
      "step": 125
    },
    {
      "epoch": 0.23290203327171904,
      "grad_norm": 0.4916364252567291,
      "learning_rate": 0.001,
      "loss": 0.4894,
      "step": 126
    },
    {
      "epoch": 0.23475046210720887,
      "grad_norm": 0.5022260546684265,
      "learning_rate": 0.001,
      "loss": 0.614,
      "step": 127
    },
    {
      "epoch": 0.2365988909426987,
      "grad_norm": 0.4792012870311737,
      "learning_rate": 0.001,
      "loss": 0.6265,
      "step": 128
    },
    {
      "epoch": 0.23844731977818853,
      "grad_norm": 0.5663838982582092,
      "learning_rate": 0.001,
      "loss": 0.5971,
      "step": 129
    },
    {
      "epoch": 0.24029574861367836,
      "grad_norm": 0.49800997972488403,
      "learning_rate": 0.001,
      "loss": 0.6318,
      "step": 130
    },
    {
      "epoch": 0.24214417744916822,
      "grad_norm": 0.35220399498939514,
      "learning_rate": 0.001,
      "loss": 0.3083,
      "step": 131
    },
    {
      "epoch": 0.24399260628465805,
      "grad_norm": 0.4706744849681854,
      "learning_rate": 0.001,
      "loss": 0.6436,
      "step": 132
    },
    {
      "epoch": 0.24584103512014788,
      "grad_norm": 0.5163246393203735,
      "learning_rate": 0.001,
      "loss": 0.7155,
      "step": 133
    },
    {
      "epoch": 0.2476894639556377,
      "grad_norm": 0.4994561970233917,
      "learning_rate": 0.001,
      "loss": 0.8529,
      "step": 134
    },
    {
      "epoch": 0.24953789279112754,
      "grad_norm": 0.47701308131217957,
      "learning_rate": 0.001,
      "loss": 0.6465,
      "step": 135
    },
    {
      "epoch": 0.2513863216266174,
      "grad_norm": 0.5003355145454407,
      "learning_rate": 0.001,
      "loss": 0.6787,
      "step": 136
    },
    {
      "epoch": 0.2513863216266174,
      "eval_loss": 0.6116308569908142,
      "eval_runtime": 37.1894,
      "eval_samples_per_second": 1.479,
      "eval_steps_per_second": 0.188,
      "step": 136
    },
    {
      "epoch": 0.2532347504621072,
      "grad_norm": 0.46851846575737,
      "learning_rate": 0.001,
      "loss": 0.7461,
      "step": 137
    },
    {
      "epoch": 0.25508317929759705,
      "grad_norm": 0.703341007232666,
      "learning_rate": 0.001,
      "loss": 0.709,
      "step": 138
    },
    {
      "epoch": 0.25693160813308685,
      "grad_norm": 0.48569703102111816,
      "learning_rate": 0.001,
      "loss": 0.7207,
      "step": 139
    },
    {
      "epoch": 0.2587800369685767,
      "grad_norm": 0.3450978398323059,
      "learning_rate": 0.001,
      "loss": 0.5599,
      "step": 140
    },
    {
      "epoch": 0.26062846580406657,
      "grad_norm": 0.5488552451133728,
      "learning_rate": 0.001,
      "loss": 0.8029,
      "step": 141
    },
    {
      "epoch": 0.26247689463955637,
      "grad_norm": 0.43643897771835327,
      "learning_rate": 0.001,
      "loss": 0.6259,
      "step": 142
    },
    {
      "epoch": 0.2643253234750462,
      "grad_norm": 0.4441094398498535,
      "learning_rate": 0.001,
      "loss": 0.688,
      "step": 143
    },
    {
      "epoch": 0.266173752310536,
      "grad_norm": 0.40471598505973816,
      "learning_rate": 0.001,
      "loss": 0.666,
      "step": 144
    },
    {
      "epoch": 0.2680221811460259,
      "grad_norm": 0.5318337678909302,
      "learning_rate": 0.001,
      "loss": 0.6774,
      "step": 145
    },
    {
      "epoch": 0.2698706099815157,
      "grad_norm": 0.3838026225566864,
      "learning_rate": 0.001,
      "loss": 0.5882,
      "step": 146
    },
    {
      "epoch": 0.27171903881700554,
      "grad_norm": 757.2123413085938,
      "learning_rate": 0.001,
      "loss": 3.2426,
      "step": 147
    },
    {
      "epoch": 0.2735674676524954,
      "grad_norm": 0.4157928228378296,
      "learning_rate": 0.001,
      "loss": 0.5649,
      "step": 148
    },
    {
      "epoch": 0.2754158964879852,
      "grad_norm": 0.3751083314418793,
      "learning_rate": 0.001,
      "loss": 0.5098,
      "step": 149
    },
    {
      "epoch": 0.27726432532347506,
      "grad_norm": 0.38269737362861633,
      "learning_rate": 0.001,
      "loss": 0.6048,
      "step": 150
    },
    {
      "epoch": 0.27911275415896486,
      "grad_norm": 0.9310194849967957,
      "learning_rate": 0.001,
      "loss": 0.5548,
      "step": 151
    },
    {
      "epoch": 0.2809611829944547,
      "grad_norm": 0.6662898063659668,
      "learning_rate": 0.001,
      "loss": 1.0353,
      "step": 152
    },
    {
      "epoch": 0.2828096118299446,
      "grad_norm": 0.5112884640693665,
      "learning_rate": 0.001,
      "loss": 0.5875,
      "step": 153
    },
    {
      "epoch": 0.2846580406654344,
      "grad_norm": 0.682369589805603,
      "learning_rate": 0.001,
      "loss": 0.7255,
      "step": 154
    },
    {
      "epoch": 0.28650646950092423,
      "grad_norm": 0.37935149669647217,
      "learning_rate": 0.001,
      "loss": 0.453,
      "step": 155
    },
    {
      "epoch": 0.28835489833641403,
      "grad_norm": 0.5815888047218323,
      "learning_rate": 0.001,
      "loss": 0.6359,
      "step": 156
    },
    {
      "epoch": 0.2902033271719039,
      "grad_norm": 0.5233355164527893,
      "learning_rate": 0.001,
      "loss": 0.588,
      "step": 157
    },
    {
      "epoch": 0.2920517560073937,
      "grad_norm": 0.5995686650276184,
      "learning_rate": 0.001,
      "loss": 0.6695,
      "step": 158
    },
    {
      "epoch": 0.29390018484288355,
      "grad_norm": 0.5288013815879822,
      "learning_rate": 0.001,
      "loss": 0.6172,
      "step": 159
    },
    {
      "epoch": 0.2957486136783734,
      "grad_norm": 0.4866679310798645,
      "learning_rate": 0.001,
      "loss": 0.6383,
      "step": 160
    },
    {
      "epoch": 0.2975970425138632,
      "grad_norm": 0.4867928922176361,
      "learning_rate": 0.001,
      "loss": 0.6561,
      "step": 161
    },
    {
      "epoch": 0.29944547134935307,
      "grad_norm": 85.95575714111328,
      "learning_rate": 0.001,
      "loss": 7.2015,
      "step": 162
    },
    {
      "epoch": 0.30129390018484287,
      "grad_norm": 0.9067592620849609,
      "learning_rate": 0.001,
      "loss": 0.7286,
      "step": 163
    },
    {
      "epoch": 0.3031423290203327,
      "grad_norm": 0.8694595098495483,
      "learning_rate": 0.001,
      "loss": 0.5795,
      "step": 164
    },
    {
      "epoch": 0.3049907578558225,
      "grad_norm": 0.5374184846878052,
      "learning_rate": 0.001,
      "loss": 0.5078,
      "step": 165
    },
    {
      "epoch": 0.3068391866913124,
      "grad_norm": 0.42466646432876587,
      "learning_rate": 0.001,
      "loss": 0.5351,
      "step": 166
    },
    {
      "epoch": 0.30868761552680224,
      "grad_norm": 0.707733690738678,
      "learning_rate": 0.001,
      "loss": 0.8727,
      "step": 167
    },
    {
      "epoch": 0.31053604436229204,
      "grad_norm": 0.7297586798667908,
      "learning_rate": 0.001,
      "loss": 0.6873,
      "step": 168
    },
    {
      "epoch": 0.3123844731977819,
      "grad_norm": 0.587944507598877,
      "learning_rate": 0.001,
      "loss": 2.0879,
      "step": 169
    },
    {
      "epoch": 0.3142329020332717,
      "grad_norm": 0.9605491161346436,
      "learning_rate": 0.001,
      "loss": 1.2765,
      "step": 170
    },
    {
      "epoch": 0.31608133086876156,
      "grad_norm": 0.5181152820587158,
      "learning_rate": 0.001,
      "loss": 0.6069,
      "step": 171
    },
    {
      "epoch": 0.3179297597042514,
      "grad_norm": 2.2382378578186035,
      "learning_rate": 0.001,
      "loss": 0.7284,
      "step": 172
    },
    {
      "epoch": 0.3197781885397412,
      "grad_norm": 0.42649027705192566,
      "learning_rate": 0.001,
      "loss": 0.5089,
      "step": 173
    },
    {
      "epoch": 0.32162661737523107,
      "grad_norm": 0.5831953287124634,
      "learning_rate": 0.001,
      "loss": 0.6019,
      "step": 174
    },
    {
      "epoch": 0.3234750462107209,
      "grad_norm": 11.331945419311523,
      "learning_rate": 0.001,
      "loss": 0.7763,
      "step": 175
    },
    {
      "epoch": 0.32532347504621073,
      "grad_norm": 0.4289061725139618,
      "learning_rate": 0.001,
      "loss": 0.4493,
      "step": 176
    },
    {
      "epoch": 0.32717190388170053,
      "grad_norm": 0.7920455932617188,
      "learning_rate": 0.001,
      "loss": 0.7945,
      "step": 177
    },
    {
      "epoch": 0.3290203327171904,
      "grad_norm": 1.0137889385223389,
      "learning_rate": 0.001,
      "loss": 0.7158,
      "step": 178
    },
    {
      "epoch": 0.33086876155268025,
      "grad_norm": 1.1164557933807373,
      "learning_rate": 0.001,
      "loss": 0.7007,
      "step": 179
    },
    {
      "epoch": 0.33271719038817005,
      "grad_norm": 0.5898825526237488,
      "learning_rate": 0.001,
      "loss": 0.7362,
      "step": 180
    },
    {
      "epoch": 0.3345656192236599,
      "grad_norm": 2144.9521484375,
      "learning_rate": 0.001,
      "loss": 5.333,
      "step": 181
    },
    {
      "epoch": 0.3364140480591497,
      "grad_norm": 1.0912034511566162,
      "learning_rate": 0.001,
      "loss": 0.8123,
      "step": 182
    },
    {
      "epoch": 0.33826247689463956,
      "grad_norm": 0.5837512612342834,
      "learning_rate": 0.001,
      "loss": 0.738,
      "step": 183
    },
    {
      "epoch": 0.34011090573012936,
      "grad_norm": 0.5561927556991577,
      "learning_rate": 0.001,
      "loss": 0.5875,
      "step": 184
    },
    {
      "epoch": 0.3419593345656192,
      "grad_norm": 3.1537868976593018,
      "learning_rate": 0.001,
      "loss": 0.8469,
      "step": 185
    },
    {
      "epoch": 0.3438077634011091,
      "grad_norm": 0.751020610332489,
      "learning_rate": 0.001,
      "loss": 0.6567,
      "step": 186
    },
    {
      "epoch": 0.3456561922365989,
      "grad_norm": 2.071126699447632,
      "learning_rate": 0.001,
      "loss": 0.7666,
      "step": 187
    },
    {
      "epoch": 0.34750462107208874,
      "grad_norm": 0.8807157874107361,
      "learning_rate": 0.001,
      "loss": 1.0371,
      "step": 188
    },
    {
      "epoch": 0.34935304990757854,
      "grad_norm": 2.8368020057678223,
      "learning_rate": 0.001,
      "loss": 0.9064,
      "step": 189
    },
    {
      "epoch": 0.3512014787430684,
      "grad_norm": 16.864635467529297,
      "learning_rate": 0.001,
      "loss": 0.9614,
      "step": 190
    },
    {
      "epoch": 0.35304990757855825,
      "grad_norm": 0.7199917435646057,
      "learning_rate": 0.001,
      "loss": 0.7248,
      "step": 191
    },
    {
      "epoch": 0.35489833641404805,
      "grad_norm": 0.6968075633049011,
      "learning_rate": 0.001,
      "loss": 0.6518,
      "step": 192
    },
    {
      "epoch": 0.3567467652495379,
      "grad_norm": 0.7219743728637695,
      "learning_rate": 0.001,
      "loss": 0.7583,
      "step": 193
    },
    {
      "epoch": 0.3585951940850277,
      "grad_norm": 0.5318032503128052,
      "learning_rate": 0.001,
      "loss": 0.638,
      "step": 194
    },
    {
      "epoch": 0.36044362292051757,
      "grad_norm": 0.740088701248169,
      "learning_rate": 0.001,
      "loss": 0.6744,
      "step": 195
    },
    {
      "epoch": 0.36229205175600737,
      "grad_norm": 0.743021547794342,
      "learning_rate": 0.001,
      "loss": 0.6755,
      "step": 196
    },
    {
      "epoch": 0.36414048059149723,
      "grad_norm": 4.2798004150390625,
      "learning_rate": 0.001,
      "loss": 0.6902,
      "step": 197
    },
    {
      "epoch": 0.3659889094269871,
      "grad_norm": 0.7763252854347229,
      "learning_rate": 0.001,
      "loss": 0.7363,
      "step": 198
    },
    {
      "epoch": 0.3678373382624769,
      "grad_norm": 0.8664296865463257,
      "learning_rate": 0.001,
      "loss": 0.9194,
      "step": 199
    },
    {
      "epoch": 0.36968576709796674,
      "grad_norm": 1.4949946403503418,
      "learning_rate": 0.001,
      "loss": 0.6825,
      "step": 200
    },
    {
      "epoch": 0.37153419593345655,
      "grad_norm": 0.47144782543182373,
      "learning_rate": 0.001,
      "loss": 0.4892,
      "step": 201
    },
    {
      "epoch": 0.3733826247689464,
      "grad_norm": 2.078660249710083,
      "learning_rate": 0.001,
      "loss": 0.9382,
      "step": 202
    },
    {
      "epoch": 0.3752310536044362,
      "grad_norm": 0.8569644689559937,
      "learning_rate": 0.001,
      "loss": 0.6567,
      "step": 203
    },
    {
      "epoch": 0.37707948243992606,
      "grad_norm": 0.7167682647705078,
      "learning_rate": 0.001,
      "loss": 0.8144,
      "step": 204
    },
    {
      "epoch": 0.3789279112754159,
      "grad_norm": 2.2069590091705322,
      "learning_rate": 0.001,
      "loss": 0.8378,
      "step": 205
    },
    {
      "epoch": 0.3807763401109057,
      "grad_norm": 4.755973815917969,
      "learning_rate": 0.001,
      "loss": 0.6908,
      "step": 206
    },
    {
      "epoch": 0.3826247689463956,
      "grad_norm": 0.6981136202812195,
      "learning_rate": 0.001,
      "loss": 0.5822,
      "step": 207
    },
    {
      "epoch": 0.3844731977818854,
      "grad_norm": 0.7765632271766663,
      "learning_rate": 0.001,
      "loss": 0.8156,
      "step": 208
    },
    {
      "epoch": 0.38632162661737524,
      "grad_norm": 2.0891387462615967,
      "learning_rate": 0.001,
      "loss": 0.558,
      "step": 209
    },
    {
      "epoch": 0.38817005545286504,
      "grad_norm": 0.7609770894050598,
      "learning_rate": 0.001,
      "loss": 0.6879,
      "step": 210
    },
    {
      "epoch": 0.3900184842883549,
      "grad_norm": 0.6121675372123718,
      "learning_rate": 0.001,
      "loss": 0.8023,
      "step": 211
    },
    {
      "epoch": 0.39186691312384475,
      "grad_norm": 1.2764517068862915,
      "learning_rate": 0.001,
      "loss": 0.671,
      "step": 212
    },
    {
      "epoch": 0.39371534195933455,
      "grad_norm": 0.9839686155319214,
      "learning_rate": 0.001,
      "loss": 0.6025,
      "step": 213
    },
    {
      "epoch": 0.3955637707948244,
      "grad_norm": 0.8942749500274658,
      "learning_rate": 0.001,
      "loss": 0.7837,
      "step": 214
    },
    {
      "epoch": 0.3974121996303142,
      "grad_norm": 8.554291725158691,
      "learning_rate": 0.001,
      "loss": 0.9271,
      "step": 215
    },
    {
      "epoch": 0.39926062846580407,
      "grad_norm": 36.47178649902344,
      "learning_rate": 0.001,
      "loss": 1.0102,
      "step": 216
    },
    {
      "epoch": 0.4011090573012939,
      "grad_norm": 4.423219203948975,
      "learning_rate": 0.001,
      "loss": 0.614,
      "step": 217
    },
    {
      "epoch": 0.4029574861367837,
      "grad_norm": 0.673527181148529,
      "learning_rate": 0.001,
      "loss": 0.6804,
      "step": 218
    },
    {
      "epoch": 0.4048059149722736,
      "grad_norm": 0.8505294322967529,
      "learning_rate": 0.001,
      "loss": 0.6223,
      "step": 219
    },
    {
      "epoch": 0.4066543438077634,
      "grad_norm": 0.6489795446395874,
      "learning_rate": 0.001,
      "loss": 0.6429,
      "step": 220
    },
    {
      "epoch": 0.40850277264325324,
      "grad_norm": 0.8948644399642944,
      "learning_rate": 0.001,
      "loss": 1.4723,
      "step": 221
    },
    {
      "epoch": 0.41035120147874304,
      "grad_norm": 210.18814086914062,
      "learning_rate": 0.001,
      "loss": 1.6274,
      "step": 222
    },
    {
      "epoch": 0.4121996303142329,
      "grad_norm": 23.37410545349121,
      "learning_rate": 0.001,
      "loss": 0.6821,
      "step": 223
    },
    {
      "epoch": 0.41404805914972276,
      "grad_norm": 25.335840225219727,
      "learning_rate": 0.001,
      "loss": 1.5518,
      "step": 224
    },
    {
      "epoch": 0.41589648798521256,
      "grad_norm": 1.2805469036102295,
      "learning_rate": 0.001,
      "loss": 0.755,
      "step": 225
    },
    {
      "epoch": 0.4177449168207024,
      "grad_norm": 3.5078518390655518,
      "learning_rate": 0.001,
      "loss": 0.765,
      "step": 226
    },
    {
      "epoch": 0.4195933456561922,
      "grad_norm": 2.665682315826416,
      "learning_rate": 0.001,
      "loss": 1.0047,
      "step": 227
    },
    {
      "epoch": 0.4214417744916821,
      "grad_norm": 0.8399984240531921,
      "learning_rate": 0.001,
      "loss": 0.6717,
      "step": 228
    },
    {
      "epoch": 0.4232902033271719,
      "grad_norm": 0.5785517692565918,
      "learning_rate": 0.001,
      "loss": 0.6277,
      "step": 229
    },
    {
      "epoch": 0.42513863216266173,
      "grad_norm": 0.7574679851531982,
      "learning_rate": 0.001,
      "loss": 0.6001,
      "step": 230
    },
    {
      "epoch": 0.4269870609981516,
      "grad_norm": 1.1060686111450195,
      "learning_rate": 0.001,
      "loss": 0.4657,
      "step": 231
    },
    {
      "epoch": 0.4288354898336414,
      "grad_norm": 0.8456437587738037,
      "learning_rate": 0.001,
      "loss": 0.6504,
      "step": 232
    },
    {
      "epoch": 0.43068391866913125,
      "grad_norm": 1.1631237268447876,
      "learning_rate": 0.001,
      "loss": 0.6474,
      "step": 233
    },
    {
      "epoch": 0.43253234750462105,
      "grad_norm": 0.8575699925422668,
      "learning_rate": 0.001,
      "loss": 0.8597,
      "step": 234
    },
    {
      "epoch": 0.4343807763401109,
      "grad_norm": 1.1094099283218384,
      "learning_rate": 0.001,
      "loss": 0.6128,
      "step": 235
    },
    {
      "epoch": 0.43622920517560076,
      "grad_norm": 0.765487015247345,
      "learning_rate": 0.001,
      "loss": 0.685,
      "step": 236
    },
    {
      "epoch": 0.43807763401109057,
      "grad_norm": 0.713035523891449,
      "learning_rate": 0.001,
      "loss": 0.6375,
      "step": 237
    },
    {
      "epoch": 0.4399260628465804,
      "grad_norm": 1.1346995830535889,
      "learning_rate": 0.001,
      "loss": 0.8121,
      "step": 238
    },
    {
      "epoch": 0.4417744916820702,
      "grad_norm": 10.435094833374023,
      "learning_rate": 0.001,
      "loss": 0.7499,
      "step": 239
    },
    {
      "epoch": 0.4436229205175601,
      "grad_norm": 1.442493200302124,
      "learning_rate": 0.001,
      "loss": 0.6899,
      "step": 240
    },
    {
      "epoch": 0.4454713493530499,
      "grad_norm": 1.5144755840301514,
      "learning_rate": 0.001,
      "loss": 0.566,
      "step": 241
    },
    {
      "epoch": 0.44731977818853974,
      "grad_norm": 1.2616835832595825,
      "learning_rate": 0.001,
      "loss": 0.6848,
      "step": 242
    },
    {
      "epoch": 0.4491682070240296,
      "grad_norm": 1.6803869009017944,
      "learning_rate": 0.001,
      "loss": 1.9734,
      "step": 243
    },
    {
      "epoch": 0.4510166358595194,
      "grad_norm": 1.6784708499908447,
      "learning_rate": 0.001,
      "loss": 0.8113,
      "step": 244
    },
    {
      "epoch": 0.45286506469500926,
      "grad_norm": 0.6301059126853943,
      "learning_rate": 0.001,
      "loss": 0.5922,
      "step": 245
    },
    {
      "epoch": 0.45471349353049906,
      "grad_norm": 2.435321807861328,
      "learning_rate": 0.001,
      "loss": 0.7648,
      "step": 246
    },
    {
      "epoch": 0.4565619223659889,
      "grad_norm": 0.9158065915107727,
      "learning_rate": 0.001,
      "loss": 0.6473,
      "step": 247
    },
    {
      "epoch": 0.4584103512014787,
      "grad_norm": 1.1794534921646118,
      "learning_rate": 0.001,
      "loss": 0.6715,
      "step": 248
    },
    {
      "epoch": 0.4602587800369686,
      "grad_norm": 5.524970054626465,
      "learning_rate": 0.001,
      "loss": 0.7828,
      "step": 249
    },
    {
      "epoch": 0.46210720887245843,
      "grad_norm": 1.7100472450256348,
      "learning_rate": 0.001,
      "loss": 0.8253,
      "step": 250
    },
    {
      "epoch": 0.46395563770794823,
      "grad_norm": 43.962615966796875,
      "learning_rate": 0.001,
      "loss": 7.6281,
      "step": 251
    },
    {
      "epoch": 0.4658040665434381,
      "grad_norm": 8.905851364135742,
      "learning_rate": 0.001,
      "loss": 1.2425,
      "step": 252
    },
    {
      "epoch": 0.4676524953789279,
      "grad_norm": 1.4537878036499023,
      "learning_rate": 0.001,
      "loss": 0.6607,
      "step": 253
    },
    {
      "epoch": 0.46950092421441775,
      "grad_norm": 1.0906081199645996,
      "learning_rate": 0.001,
      "loss": 0.7711,
      "step": 254
    },
    {
      "epoch": 0.4713493530499076,
      "grad_norm": 4.024237155914307,
      "learning_rate": 0.001,
      "loss": 0.8851,
      "step": 255
    },
    {
      "epoch": 0.4731977818853974,
      "grad_norm": 0.7822116017341614,
      "learning_rate": 0.001,
      "loss": 0.5662,
      "step": 256
    },
    {
      "epoch": 0.47504621072088726,
      "grad_norm": 1.1747384071350098,
      "learning_rate": 0.001,
      "loss": 0.6728,
      "step": 257
    },
    {
      "epoch": 0.47689463955637706,
      "grad_norm": 1.1935127973556519,
      "learning_rate": 0.001,
      "loss": 0.5782,
      "step": 258
    },
    {
      "epoch": 0.4787430683918669,
      "grad_norm": 0.5861594080924988,
      "learning_rate": 0.001,
      "loss": 0.6337,
      "step": 259
    },
    {
      "epoch": 0.4805914972273567,
      "grad_norm": 1.6729638576507568,
      "learning_rate": 0.001,
      "loss": 0.7732,
      "step": 260
    },
    {
      "epoch": 0.4824399260628466,
      "grad_norm": 6.095468044281006,
      "learning_rate": 0.001,
      "loss": 0.8832,
      "step": 261
    },
    {
      "epoch": 0.48428835489833644,
      "grad_norm": 366.1634521484375,
      "learning_rate": 0.001,
      "loss": 1.8354,
      "step": 262
    },
    {
      "epoch": 0.48613678373382624,
      "grad_norm": 119.24848175048828,
      "learning_rate": 0.001,
      "loss": 2.4536,
      "step": 263
    },
    {
      "epoch": 0.4879852125693161,
      "grad_norm": 1.6337554454803467,
      "learning_rate": 0.001,
      "loss": 0.7948,
      "step": 264
    },
    {
      "epoch": 0.4898336414048059,
      "grad_norm": 0.7200238704681396,
      "learning_rate": 0.001,
      "loss": 0.5746,
      "step": 265
    },
    {
      "epoch": 0.49168207024029575,
      "grad_norm": 0.9898024201393127,
      "learning_rate": 0.001,
      "loss": 0.9548,
      "step": 266
    },
    {
      "epoch": 0.49353049907578556,
      "grad_norm": 48.905426025390625,
      "learning_rate": 0.001,
      "loss": 2.7047,
      "step": 267
    },
    {
      "epoch": 0.4953789279112754,
      "grad_norm": 2.0077579021453857,
      "learning_rate": 0.001,
      "loss": 0.9014,
      "step": 268
    },
    {
      "epoch": 0.49722735674676527,
      "grad_norm": 0.7598840594291687,
      "learning_rate": 0.001,
      "loss": 0.6205,
      "step": 269
    },
    {
      "epoch": 0.49907578558225507,
      "grad_norm": 0.6317667365074158,
      "learning_rate": 0.001,
      "loss": 0.6323,
      "step": 270
    },
    {
      "epoch": 0.5009242144177449,
      "grad_norm": 1.1243677139282227,
      "learning_rate": 0.001,
      "loss": 0.699,
      "step": 271
    },
    {
      "epoch": 0.5027726432532348,
      "grad_norm": 0.7714710235595703,
      "learning_rate": 0.001,
      "loss": 0.6488,
      "step": 272
    },
    {
      "epoch": 0.5027726432532348,
      "eval_loss": 2.399911403656006,
      "eval_runtime": 36.8979,
      "eval_samples_per_second": 1.491,
      "eval_steps_per_second": 0.19,
      "step": 272
    },
    {
      "epoch": 0.5046210720887245,
      "grad_norm": 5.736697196960449,
      "learning_rate": 0.001,
      "loss": 0.7481,
      "step": 273
    },
    {
      "epoch": 0.5064695009242144,
      "grad_norm": 0.6620627641677856,
      "learning_rate": 0.001,
      "loss": 0.6781,
      "step": 274
    },
    {
      "epoch": 0.5083179297597042,
      "grad_norm": 1.1013222932815552,
      "learning_rate": 0.001,
      "loss": 0.8447,
      "step": 275
    },
    {
      "epoch": 0.5101663585951941,
      "grad_norm": 0.6351478099822998,
      "learning_rate": 0.001,
      "loss": 0.486,
      "step": 276
    },
    {
      "epoch": 0.512014787430684,
      "grad_norm": 0.7216677069664001,
      "learning_rate": 0.001,
      "loss": 0.6427,
      "step": 277
    },
    {
      "epoch": 0.5138632162661737,
      "grad_norm": 0.9114554524421692,
      "learning_rate": 0.001,
      "loss": 2.2048,
      "step": 278
    },
    {
      "epoch": 0.5157116451016636,
      "grad_norm": 0.9319707155227661,
      "learning_rate": 0.001,
      "loss": 0.6169,
      "step": 279
    },
    {
      "epoch": 0.5175600739371534,
      "grad_norm": 1.0675102472305298,
      "learning_rate": 0.001,
      "loss": 0.8317,
      "step": 280
    },
    {
      "epoch": 0.5194085027726433,
      "grad_norm": 1.91627037525177,
      "learning_rate": 0.001,
      "loss": 0.7027,
      "step": 281
    },
    {
      "epoch": 0.5212569316081331,
      "grad_norm": 1.4550344944000244,
      "learning_rate": 0.001,
      "loss": 0.7876,
      "step": 282
    },
    {
      "epoch": 0.5231053604436229,
      "grad_norm": 1.139053463935852,
      "learning_rate": 0.001,
      "loss": 2.3306,
      "step": 283
    },
    {
      "epoch": 0.5249537892791127,
      "grad_norm": 1.3426302671432495,
      "learning_rate": 0.001,
      "loss": 0.4473,
      "step": 284
    },
    {
      "epoch": 0.5268022181146026,
      "grad_norm": 1.4722453355789185,
      "learning_rate": 0.001,
      "loss": 0.7528,
      "step": 285
    },
    {
      "epoch": 0.5286506469500925,
      "grad_norm": 0.6636189222335815,
      "learning_rate": 0.001,
      "loss": 0.7003,
      "step": 286
    },
    {
      "epoch": 0.5304990757855823,
      "grad_norm": 0.6289682388305664,
      "learning_rate": 0.001,
      "loss": 0.6891,
      "step": 287
    },
    {
      "epoch": 0.532347504621072,
      "grad_norm": 0.518354058265686,
      "learning_rate": 0.001,
      "loss": 0.6492,
      "step": 288
    },
    {
      "epoch": 0.5341959334565619,
      "grad_norm": 0.6105506420135498,
      "learning_rate": 0.001,
      "loss": 0.642,
      "step": 289
    },
    {
      "epoch": 0.5360443622920518,
      "grad_norm": 0.663215160369873,
      "learning_rate": 0.001,
      "loss": 0.7104,
      "step": 290
    },
    {
      "epoch": 0.5378927911275416,
      "grad_norm": 0.6891048550605774,
      "learning_rate": 0.001,
      "loss": 0.7431,
      "step": 291
    },
    {
      "epoch": 0.5397412199630314,
      "grad_norm": 1.533583641052246,
      "learning_rate": 0.001,
      "loss": 1.886,
      "step": 292
    },
    {
      "epoch": 0.5415896487985212,
      "grad_norm": 0.933929979801178,
      "learning_rate": 0.001,
      "loss": 0.6183,
      "step": 293
    },
    {
      "epoch": 0.5434380776340111,
      "grad_norm": 0.7768216729164124,
      "learning_rate": 0.001,
      "loss": 0.7606,
      "step": 294
    },
    {
      "epoch": 0.5452865064695009,
      "grad_norm": 2.2823166847229004,
      "learning_rate": 0.001,
      "loss": 0.7254,
      "step": 295
    },
    {
      "epoch": 0.5471349353049908,
      "grad_norm": 0.7304850816726685,
      "learning_rate": 0.001,
      "loss": 0.7621,
      "step": 296
    },
    {
      "epoch": 0.5489833641404805,
      "grad_norm": 0.593639075756073,
      "learning_rate": 0.001,
      "loss": 0.6813,
      "step": 297
    },
    {
      "epoch": 0.5508317929759704,
      "grad_norm": 2.0610456466674805,
      "learning_rate": 0.001,
      "loss": 1.0654,
      "step": 298
    },
    {
      "epoch": 0.5526802218114603,
      "grad_norm": 1.1367557048797607,
      "learning_rate": 0.001,
      "loss": 0.6536,
      "step": 299
    },
    {
      "epoch": 0.5545286506469501,
      "grad_norm": 5.493245601654053,
      "learning_rate": 0.001,
      "loss": 0.6969,
      "step": 300
    },
    {
      "epoch": 0.55637707948244,
      "grad_norm": 0.56303471326828,
      "learning_rate": 0.001,
      "loss": 0.7435,
      "step": 301
    },
    {
      "epoch": 0.5582255083179297,
      "grad_norm": 0.5343788266181946,
      "learning_rate": 0.001,
      "loss": 0.6129,
      "step": 302
    },
    {
      "epoch": 0.5600739371534196,
      "grad_norm": 0.6194228529930115,
      "learning_rate": 0.001,
      "loss": 0.6848,
      "step": 303
    },
    {
      "epoch": 0.5619223659889094,
      "grad_norm": 0.7855530977249146,
      "learning_rate": 0.001,
      "loss": 0.8936,
      "step": 304
    },
    {
      "epoch": 0.5637707948243993,
      "grad_norm": 0.5858953595161438,
      "learning_rate": 0.001,
      "loss": 0.7653,
      "step": 305
    },
    {
      "epoch": 0.5656192236598891,
      "grad_norm": 48.524574279785156,
      "learning_rate": 0.001,
      "loss": 9.1166,
      "step": 306
    },
    {
      "epoch": 0.5674676524953789,
      "grad_norm": 0.6151651740074158,
      "learning_rate": 0.001,
      "loss": 0.7313,
      "step": 307
    },
    {
      "epoch": 0.5693160813308688,
      "grad_norm": 0.9248428344726562,
      "learning_rate": 0.001,
      "loss": 0.5781,
      "step": 308
    },
    {
      "epoch": 0.5711645101663586,
      "grad_norm": 0.49555471539497375,
      "learning_rate": 0.001,
      "loss": 0.5315,
      "step": 309
    },
    {
      "epoch": 0.5730129390018485,
      "grad_norm": 0.5464370250701904,
      "learning_rate": 0.001,
      "loss": 0.6076,
      "step": 310
    },
    {
      "epoch": 0.5748613678373382,
      "grad_norm": 0.6241145730018616,
      "learning_rate": 0.001,
      "loss": 0.3794,
      "step": 311
    },
    {
      "epoch": 0.5767097966728281,
      "grad_norm": 0.6810182929039001,
      "learning_rate": 0.001,
      "loss": 0.8058,
      "step": 312
    },
    {
      "epoch": 0.5785582255083179,
      "grad_norm": 0.6118370890617371,
      "learning_rate": 0.001,
      "loss": 0.6892,
      "step": 313
    },
    {
      "epoch": 0.5804066543438078,
      "grad_norm": 0.8108903169631958,
      "learning_rate": 0.001,
      "loss": 0.7409,
      "step": 314
    },
    {
      "epoch": 0.5822550831792976,
      "grad_norm": 0.6275304555892944,
      "learning_rate": 0.001,
      "loss": 0.5313,
      "step": 315
    },
    {
      "epoch": 0.5841035120147874,
      "grad_norm": 0.8600186705589294,
      "learning_rate": 0.001,
      "loss": 0.7863,
      "step": 316
    },
    {
      "epoch": 0.5859519408502772,
      "grad_norm": 1.5396201610565186,
      "learning_rate": 0.001,
      "loss": 0.8304,
      "step": 317
    },
    {
      "epoch": 0.5878003696857671,
      "grad_norm": 0.6472541689872742,
      "learning_rate": 0.001,
      "loss": 0.5984,
      "step": 318
    },
    {
      "epoch": 0.589648798521257,
      "grad_norm": 1.398506760597229,
      "learning_rate": 0.001,
      "loss": 0.9278,
      "step": 319
    },
    {
      "epoch": 0.5914972273567468,
      "grad_norm": 0.8885821104049683,
      "learning_rate": 0.001,
      "loss": 0.7355,
      "step": 320
    },
    {
      "epoch": 0.5933456561922366,
      "grad_norm": 0.6919491291046143,
      "learning_rate": 0.001,
      "loss": 0.7955,
      "step": 321
    },
    {
      "epoch": 0.5951940850277264,
      "grad_norm": 0.5543484687805176,
      "learning_rate": 0.001,
      "loss": 0.5661,
      "step": 322
    },
    {
      "epoch": 0.5970425138632163,
      "grad_norm": 0.9218202829360962,
      "learning_rate": 0.001,
      "loss": 0.6754,
      "step": 323
    },
    {
      "epoch": 0.5988909426987061,
      "grad_norm": 0.7282502055168152,
      "learning_rate": 0.001,
      "loss": 0.7551,
      "step": 324
    },
    {
      "epoch": 0.600739371534196,
      "grad_norm": 0.8452831506729126,
      "learning_rate": 0.001,
      "loss": 0.7975,
      "step": 325
    },
    {
      "epoch": 0.6025878003696857,
      "grad_norm": 0.6374185085296631,
      "learning_rate": 0.001,
      "loss": 0.6155,
      "step": 326
    },
    {
      "epoch": 0.6044362292051756,
      "grad_norm": 0.8224793076515198,
      "learning_rate": 0.001,
      "loss": 0.8842,
      "step": 327
    },
    {
      "epoch": 0.6062846580406654,
      "grad_norm": 0.8151664137840271,
      "learning_rate": 0.001,
      "loss": 0.6684,
      "step": 328
    },
    {
      "epoch": 0.6081330868761553,
      "grad_norm": 0.8286120295524597,
      "learning_rate": 0.001,
      "loss": 0.6752,
      "step": 329
    },
    {
      "epoch": 0.609981515711645,
      "grad_norm": 0.6680192351341248,
      "learning_rate": 0.001,
      "loss": 0.5938,
      "step": 330
    },
    {
      "epoch": 0.6118299445471349,
      "grad_norm": 0.6495516896247864,
      "learning_rate": 0.001,
      "loss": 0.6121,
      "step": 331
    },
    {
      "epoch": 0.6136783733826248,
      "grad_norm": 0.484153151512146,
      "learning_rate": 0.001,
      "loss": 0.5139,
      "step": 332
    },
    {
      "epoch": 0.6155268022181146,
      "grad_norm": 0.7952211499214172,
      "learning_rate": 0.001,
      "loss": 1.9693,
      "step": 333
    },
    {
      "epoch": 0.6173752310536045,
      "grad_norm": 0.6049392819404602,
      "learning_rate": 0.001,
      "loss": 0.6355,
      "step": 334
    },
    {
      "epoch": 0.6192236598890942,
      "grad_norm": 0.5543565154075623,
      "learning_rate": 0.001,
      "loss": 0.5789,
      "step": 335
    },
    {
      "epoch": 0.6210720887245841,
      "grad_norm": 0.6608275771141052,
      "learning_rate": 0.001,
      "loss": 0.7809,
      "step": 336
    },
    {
      "epoch": 0.6229205175600739,
      "grad_norm": 0.7678483724594116,
      "learning_rate": 0.001,
      "loss": 0.901,
      "step": 337
    },
    {
      "epoch": 0.6247689463955638,
      "grad_norm": 0.7045119404792786,
      "learning_rate": 0.001,
      "loss": 0.6893,
      "step": 338
    },
    {
      "epoch": 0.6266173752310537,
      "grad_norm": 0.6836982369422913,
      "learning_rate": 0.001,
      "loss": 0.6864,
      "step": 339
    },
    {
      "epoch": 0.6284658040665434,
      "grad_norm": 0.5288094878196716,
      "learning_rate": 0.001,
      "loss": 0.5089,
      "step": 340
    },
    {
      "epoch": 0.6303142329020333,
      "grad_norm": 0.6091610193252563,
      "learning_rate": 0.001,
      "loss": 0.8265,
      "step": 341
    },
    {
      "epoch": 0.6321626617375231,
      "grad_norm": 0.7190775871276855,
      "learning_rate": 0.001,
      "loss": 0.5927,
      "step": 342
    },
    {
      "epoch": 0.634011090573013,
      "grad_norm": 16.79271697998047,
      "learning_rate": 0.001,
      "loss": 2.4376,
      "step": 343
    },
    {
      "epoch": 0.6358595194085028,
      "grad_norm": 0.6407002806663513,
      "learning_rate": 0.001,
      "loss": 0.6132,
      "step": 344
    },
    {
      "epoch": 0.6377079482439926,
      "grad_norm": 0.8412754535675049,
      "learning_rate": 0.001,
      "loss": 0.6561,
      "step": 345
    },
    {
      "epoch": 0.6395563770794824,
      "grad_norm": 0.6675889492034912,
      "learning_rate": 0.001,
      "loss": 0.5961,
      "step": 346
    },
    {
      "epoch": 0.6414048059149723,
      "grad_norm": 0.6772903203964233,
      "learning_rate": 0.001,
      "loss": 0.7657,
      "step": 347
    },
    {
      "epoch": 0.6432532347504621,
      "grad_norm": 0.568170964717865,
      "learning_rate": 0.001,
      "loss": 0.5673,
      "step": 348
    },
    {
      "epoch": 0.6451016635859519,
      "grad_norm": 0.7691311240196228,
      "learning_rate": 0.001,
      "loss": 0.6749,
      "step": 349
    },
    {
      "epoch": 0.6469500924214417,
      "grad_norm": 1.38419771194458,
      "learning_rate": 0.001,
      "loss": 0.7093,
      "step": 350
    },
    {
      "epoch": 0.6487985212569316,
      "grad_norm": 17.263277053833008,
      "learning_rate": 0.001,
      "loss": 1.152,
      "step": 351
    },
    {
      "epoch": 0.6506469500924215,
      "grad_norm": 1.9294712543487549,
      "learning_rate": 0.001,
      "loss": 0.857,
      "step": 352
    },
    {
      "epoch": 0.6524953789279113,
      "grad_norm": 0.6687116026878357,
      "learning_rate": 0.001,
      "loss": 0.7798,
      "step": 353
    },
    {
      "epoch": 0.6543438077634011,
      "grad_norm": 0.600409984588623,
      "learning_rate": 0.001,
      "loss": 0.5035,
      "step": 354
    },
    {
      "epoch": 0.6561922365988909,
      "grad_norm": 0.7064170837402344,
      "learning_rate": 0.001,
      "loss": 0.8408,
      "step": 355
    },
    {
      "epoch": 0.6580406654343808,
      "grad_norm": 0.5997954607009888,
      "learning_rate": 0.001,
      "loss": 0.7668,
      "step": 356
    },
    {
      "epoch": 0.6598890942698706,
      "grad_norm": 0.8595522046089172,
      "learning_rate": 0.001,
      "loss": 0.6487,
      "step": 357
    },
    {
      "epoch": 0.6617375231053605,
      "grad_norm": 0.8264375329017639,
      "learning_rate": 0.001,
      "loss": 0.8053,
      "step": 358
    },
    {
      "epoch": 0.6635859519408502,
      "grad_norm": 0.45927339792251587,
      "learning_rate": 0.001,
      "loss": 0.6095,
      "step": 359
    },
    {
      "epoch": 0.6654343807763401,
      "grad_norm": 0.734035849571228,
      "learning_rate": 0.001,
      "loss": 0.6616,
      "step": 360
    },
    {
      "epoch": 0.66728280961183,
      "grad_norm": 0.639272928237915,
      "learning_rate": 0.001,
      "loss": 0.7055,
      "step": 361
    },
    {
      "epoch": 0.6691312384473198,
      "grad_norm": 0.5212395787239075,
      "learning_rate": 0.001,
      "loss": 0.6112,
      "step": 362
    },
    {
      "epoch": 0.6709796672828097,
      "grad_norm": 0.5960317850112915,
      "learning_rate": 0.001,
      "loss": 0.6009,
      "step": 363
    },
    {
      "epoch": 0.6728280961182994,
      "grad_norm": 0.7983746528625488,
      "learning_rate": 0.001,
      "loss": 0.8488,
      "step": 364
    },
    {
      "epoch": 0.6746765249537893,
      "grad_norm": 0.5350251793861389,
      "learning_rate": 0.001,
      "loss": 0.6422,
      "step": 365
    },
    {
      "epoch": 0.6765249537892791,
      "grad_norm": 34.95353698730469,
      "learning_rate": 0.001,
      "loss": 2.1827,
      "step": 366
    },
    {
      "epoch": 0.678373382624769,
      "grad_norm": 0.6277118921279907,
      "learning_rate": 0.001,
      "loss": 0.636,
      "step": 367
    },
    {
      "epoch": 0.6802218114602587,
      "grad_norm": 0.5147830843925476,
      "learning_rate": 0.001,
      "loss": 0.6665,
      "step": 368
    },
    {
      "epoch": 0.6820702402957486,
      "grad_norm": 0.9916329979896545,
      "learning_rate": 0.001,
      "loss": 0.8003,
      "step": 369
    },
    {
      "epoch": 0.6839186691312384,
      "grad_norm": 0.49549809098243713,
      "learning_rate": 0.001,
      "loss": 0.7006,
      "step": 370
    },
    {
      "epoch": 0.6857670979667283,
      "grad_norm": 0.6405476331710815,
      "learning_rate": 0.001,
      "loss": 0.6889,
      "step": 371
    },
    {
      "epoch": 0.6876155268022182,
      "grad_norm": 17.999553680419922,
      "learning_rate": 0.001,
      "loss": 1.08,
      "step": 372
    },
    {
      "epoch": 0.6894639556377079,
      "grad_norm": 0.6254942417144775,
      "learning_rate": 0.001,
      "loss": 0.7336,
      "step": 373
    },
    {
      "epoch": 0.6913123844731978,
      "grad_norm": 0.7496931552886963,
      "learning_rate": 0.001,
      "loss": 0.7513,
      "step": 374
    },
    {
      "epoch": 0.6931608133086876,
      "grad_norm": 0.7643265128135681,
      "learning_rate": 0.001,
      "loss": 0.6091,
      "step": 375
    },
    {
      "epoch": 0.6950092421441775,
      "grad_norm": 0.6992492079734802,
      "learning_rate": 0.001,
      "loss": 0.6633,
      "step": 376
    },
    {
      "epoch": 0.6968576709796673,
      "grad_norm": 1.2083274126052856,
      "learning_rate": 0.001,
      "loss": 0.9582,
      "step": 377
    },
    {
      "epoch": 0.6987060998151571,
      "grad_norm": 1.052863359451294,
      "learning_rate": 0.001,
      "loss": 0.7435,
      "step": 378
    },
    {
      "epoch": 0.7005545286506469,
      "grad_norm": 5.199072360992432,
      "learning_rate": 0.001,
      "loss": 1.9021,
      "step": 379
    },
    {
      "epoch": 0.7024029574861368,
      "grad_norm": 0.6658142805099487,
      "learning_rate": 0.001,
      "loss": 0.578,
      "step": 380
    },
    {
      "epoch": 0.7042513863216266,
      "grad_norm": 0.9965769052505493,
      "learning_rate": 0.001,
      "loss": 0.6766,
      "step": 381
    },
    {
      "epoch": 0.7060998151571165,
      "grad_norm": 1.3572355508804321,
      "learning_rate": 0.001,
      "loss": 0.925,
      "step": 382
    },
    {
      "epoch": 0.7079482439926063,
      "grad_norm": 0.796585202217102,
      "learning_rate": 0.001,
      "loss": 0.8363,
      "step": 383
    },
    {
      "epoch": 0.7097966728280961,
      "grad_norm": 1.294584035873413,
      "learning_rate": 0.001,
      "loss": 0.6018,
      "step": 384
    },
    {
      "epoch": 0.711645101663586,
      "grad_norm": 0.5120808482170105,
      "learning_rate": 0.001,
      "loss": 0.6919,
      "step": 385
    },
    {
      "epoch": 0.7134935304990758,
      "grad_norm": 0.6790513396263123,
      "learning_rate": 0.001,
      "loss": 0.7894,
      "step": 386
    },
    {
      "epoch": 0.7153419593345656,
      "grad_norm": 0.796168863773346,
      "learning_rate": 0.001,
      "loss": 0.7301,
      "step": 387
    },
    {
      "epoch": 0.7171903881700554,
      "grad_norm": 0.7078443169593811,
      "learning_rate": 0.001,
      "loss": 0.614,
      "step": 388
    },
    {
      "epoch": 0.7190388170055453,
      "grad_norm": 0.656707227230072,
      "learning_rate": 0.001,
      "loss": 0.7422,
      "step": 389
    },
    {
      "epoch": 0.7208872458410351,
      "grad_norm": 1.1826304197311401,
      "learning_rate": 0.001,
      "loss": 0.9052,
      "step": 390
    },
    {
      "epoch": 0.722735674676525,
      "grad_norm": 1.317765474319458,
      "learning_rate": 0.001,
      "loss": 0.7672,
      "step": 391
    },
    {
      "epoch": 0.7245841035120147,
      "grad_norm": 0.6513253450393677,
      "learning_rate": 0.001,
      "loss": 0.6832,
      "step": 392
    },
    {
      "epoch": 0.7264325323475046,
      "grad_norm": 0.6068792939186096,
      "learning_rate": 0.001,
      "loss": 0.6591,
      "step": 393
    },
    {
      "epoch": 0.7282809611829945,
      "grad_norm": 0.7942211031913757,
      "learning_rate": 0.001,
      "loss": 2.1942,
      "step": 394
    },
    {
      "epoch": 0.7301293900184843,
      "grad_norm": 0.7121322751045227,
      "learning_rate": 0.001,
      "loss": 0.7641,
      "step": 395
    },
    {
      "epoch": 0.7319778188539742,
      "grad_norm": 0.5792383551597595,
      "learning_rate": 0.001,
      "loss": 0.6137,
      "step": 396
    },
    {
      "epoch": 0.7338262476894639,
      "grad_norm": 0.40939533710479736,
      "learning_rate": 0.001,
      "loss": 0.4706,
      "step": 397
    },
    {
      "epoch": 0.7356746765249538,
      "grad_norm": 0.8896576762199402,
      "learning_rate": 0.001,
      "loss": 0.7001,
      "step": 398
    },
    {
      "epoch": 0.7375231053604436,
      "grad_norm": 0.5687329173088074,
      "learning_rate": 0.001,
      "loss": 0.6926,
      "step": 399
    },
    {
      "epoch": 0.7393715341959335,
      "grad_norm": 0.7827416658401489,
      "learning_rate": 0.001,
      "loss": 0.8797,
      "step": 400
    },
    {
      "epoch": 0.7412199630314233,
      "grad_norm": 0.6891829371452332,
      "learning_rate": 0.001,
      "loss": 0.6442,
      "step": 401
    },
    {
      "epoch": 0.7430683918669131,
      "grad_norm": 0.9651913046836853,
      "learning_rate": 0.001,
      "loss": 0.7578,
      "step": 402
    },
    {
      "epoch": 0.744916820702403,
      "grad_norm": 1.134435772895813,
      "learning_rate": 0.001,
      "loss": 0.7586,
      "step": 403
    },
    {
      "epoch": 0.7467652495378928,
      "grad_norm": 0.7820314764976501,
      "learning_rate": 0.001,
      "loss": 0.7503,
      "step": 404
    },
    {
      "epoch": 0.7486136783733827,
      "grad_norm": 1.1618527173995972,
      "learning_rate": 0.001,
      "loss": 0.7242,
      "step": 405
    },
    {
      "epoch": 0.7504621072088724,
      "grad_norm": 0.8468978404998779,
      "learning_rate": 0.001,
      "loss": 0.804,
      "step": 406
    },
    {
      "epoch": 0.7523105360443623,
      "grad_norm": 0.6495232582092285,
      "learning_rate": 0.001,
      "loss": 0.4844,
      "step": 407
    },
    {
      "epoch": 0.7541589648798521,
      "grad_norm": 62.157989501953125,
      "learning_rate": 0.001,
      "loss": 2.3715,
      "step": 408
    },
    {
      "epoch": 0.7541589648798521,
      "eval_loss": 0.6921550631523132,
      "eval_runtime": 36.9225,
      "eval_samples_per_second": 1.49,
      "eval_steps_per_second": 0.19,
      "step": 408
    },
    {
      "epoch": 0.756007393715342,
      "grad_norm": 0.9253891110420227,
      "learning_rate": 0.001,
      "loss": 1.0238,
      "step": 409
    },
    {
      "epoch": 0.7578558225508318,
      "grad_norm": 1.3141051530838013,
      "learning_rate": 0.001,
      "loss": 1.2068,
      "step": 410
    },
    {
      "epoch": 0.7597042513863216,
      "grad_norm": 0.5310596227645874,
      "learning_rate": 0.001,
      "loss": 0.5432,
      "step": 411
    },
    {
      "epoch": 0.7615526802218114,
      "grad_norm": 0.9271712899208069,
      "learning_rate": 0.001,
      "loss": 0.7643,
      "step": 412
    },
    {
      "epoch": 0.7634011090573013,
      "grad_norm": 0.9340744018554688,
      "learning_rate": 0.001,
      "loss": 0.8286,
      "step": 413
    },
    {
      "epoch": 0.7652495378927912,
      "grad_norm": 1.0287261009216309,
      "learning_rate": 0.001,
      "loss": 0.9113,
      "step": 414
    },
    {
      "epoch": 0.767097966728281,
      "grad_norm": 0.6159982085227966,
      "learning_rate": 0.001,
      "loss": 0.6518,
      "step": 415
    },
    {
      "epoch": 0.7689463955637708,
      "grad_norm": 0.6261630654335022,
      "learning_rate": 0.001,
      "loss": 0.8691,
      "step": 416
    },
    {
      "epoch": 0.7707948243992606,
      "grad_norm": 0.5993965268135071,
      "learning_rate": 0.001,
      "loss": 0.7519,
      "step": 417
    },
    {
      "epoch": 0.7726432532347505,
      "grad_norm": 0.738401472568512,
      "learning_rate": 0.001,
      "loss": 0.6912,
      "step": 418
    },
    {
      "epoch": 0.7744916820702403,
      "grad_norm": 0.7634181976318359,
      "learning_rate": 0.001,
      "loss": 0.5789,
      "step": 419
    },
    {
      "epoch": 0.7763401109057301,
      "grad_norm": 1.065432071685791,
      "learning_rate": 0.001,
      "loss": 0.7503,
      "step": 420
    },
    {
      "epoch": 0.7781885397412199,
      "grad_norm": 0.9008420705795288,
      "learning_rate": 0.001,
      "loss": 0.5917,
      "step": 421
    },
    {
      "epoch": 0.7800369685767098,
      "grad_norm": 0.6660546660423279,
      "learning_rate": 0.001,
      "loss": 0.685,
      "step": 422
    },
    {
      "epoch": 0.7818853974121996,
      "grad_norm": 0.6387668251991272,
      "learning_rate": 0.001,
      "loss": 0.7161,
      "step": 423
    },
    {
      "epoch": 0.7837338262476895,
      "grad_norm": 1.0390757322311401,
      "learning_rate": 0.001,
      "loss": 0.8252,
      "step": 424
    },
    {
      "epoch": 0.7855822550831792,
      "grad_norm": 0.7057231664657593,
      "learning_rate": 0.001,
      "loss": 0.6607,
      "step": 425
    },
    {
      "epoch": 0.7874306839186691,
      "grad_norm": 1.4526139497756958,
      "learning_rate": 0.001,
      "loss": 0.7296,
      "step": 426
    },
    {
      "epoch": 0.789279112754159,
      "grad_norm": 0.6918472051620483,
      "learning_rate": 0.001,
      "loss": 0.6665,
      "step": 427
    },
    {
      "epoch": 0.7911275415896488,
      "grad_norm": 0.7483262419700623,
      "learning_rate": 0.001,
      "loss": 0.7229,
      "step": 428
    },
    {
      "epoch": 0.7929759704251387,
      "grad_norm": 0.5912255048751831,
      "learning_rate": 0.001,
      "loss": 0.765,
      "step": 429
    },
    {
      "epoch": 0.7948243992606284,
      "grad_norm": 0.8008376955986023,
      "learning_rate": 0.001,
      "loss": 0.7337,
      "step": 430
    },
    {
      "epoch": 0.7966728280961183,
      "grad_norm": 0.687903106212616,
      "learning_rate": 0.001,
      "loss": 0.7869,
      "step": 431
    },
    {
      "epoch": 0.7985212569316081,
      "grad_norm": 1.3599655628204346,
      "learning_rate": 0.001,
      "loss": 1.124,
      "step": 432
    },
    {
      "epoch": 0.800369685767098,
      "grad_norm": 0.8680609464645386,
      "learning_rate": 0.001,
      "loss": 0.7317,
      "step": 433
    },
    {
      "epoch": 0.8022181146025879,
      "grad_norm": 0.712820291519165,
      "learning_rate": 0.001,
      "loss": 0.6848,
      "step": 434
    },
    {
      "epoch": 0.8040665434380776,
      "grad_norm": 0.5497101545333862,
      "learning_rate": 0.001,
      "loss": 0.7699,
      "step": 435
    },
    {
      "epoch": 0.8059149722735675,
      "grad_norm": 0.657538115978241,
      "learning_rate": 0.001,
      "loss": 0.6637,
      "step": 436
    },
    {
      "epoch": 0.8077634011090573,
      "grad_norm": 0.5894818305969238,
      "learning_rate": 0.001,
      "loss": 0.7878,
      "step": 437
    },
    {
      "epoch": 0.8096118299445472,
      "grad_norm": 0.596224844455719,
      "learning_rate": 0.001,
      "loss": 0.7473,
      "step": 438
    },
    {
      "epoch": 0.8114602587800369,
      "grad_norm": 1.2735570669174194,
      "learning_rate": 0.001,
      "loss": 0.6826,
      "step": 439
    },
    {
      "epoch": 0.8133086876155268,
      "grad_norm": 0.9592067003250122,
      "learning_rate": 0.001,
      "loss": 0.9536,
      "step": 440
    },
    {
      "epoch": 0.8151571164510166,
      "grad_norm": 0.7559153437614441,
      "learning_rate": 0.001,
      "loss": 0.8591,
      "step": 441
    },
    {
      "epoch": 0.8170055452865065,
      "grad_norm": 0.49736127257347107,
      "learning_rate": 0.001,
      "loss": 0.6603,
      "step": 442
    },
    {
      "epoch": 0.8188539741219963,
      "grad_norm": 36.26533126831055,
      "learning_rate": 0.001,
      "loss": 2.834,
      "step": 443
    },
    {
      "epoch": 0.8207024029574861,
      "grad_norm": 0.7133930325508118,
      "learning_rate": 0.001,
      "loss": 0.6979,
      "step": 444
    },
    {
      "epoch": 0.822550831792976,
      "grad_norm": 0.5370646119117737,
      "learning_rate": 0.001,
      "loss": 0.549,
      "step": 445
    },
    {
      "epoch": 0.8243992606284658,
      "grad_norm": 0.4864414930343628,
      "learning_rate": 0.001,
      "loss": 0.516,
      "step": 446
    },
    {
      "epoch": 0.8262476894639557,
      "grad_norm": 1.0422941446304321,
      "learning_rate": 0.001,
      "loss": 0.7549,
      "step": 447
    },
    {
      "epoch": 0.8280961182994455,
      "grad_norm": 0.796935498714447,
      "learning_rate": 0.001,
      "loss": 1.1122,
      "step": 448
    },
    {
      "epoch": 0.8299445471349353,
      "grad_norm": 0.708077073097229,
      "learning_rate": 0.001,
      "loss": 0.5895,
      "step": 449
    },
    {
      "epoch": 0.8317929759704251,
      "grad_norm": 0.6083373427391052,
      "learning_rate": 0.001,
      "loss": 0.7167,
      "step": 450
    },
    {
      "epoch": 0.833641404805915,
      "grad_norm": 0.568143904209137,
      "learning_rate": 0.001,
      "loss": 0.5395,
      "step": 451
    },
    {
      "epoch": 0.8354898336414048,
      "grad_norm": 1.630936861038208,
      "learning_rate": 0.001,
      "loss": 0.9712,
      "step": 452
    },
    {
      "epoch": 0.8373382624768947,
      "grad_norm": 0.8898182511329651,
      "learning_rate": 0.001,
      "loss": 0.7966,
      "step": 453
    },
    {
      "epoch": 0.8391866913123844,
      "grad_norm": 0.6210492253303528,
      "learning_rate": 0.001,
      "loss": 0.7789,
      "step": 454
    },
    {
      "epoch": 0.8410351201478743,
      "grad_norm": 0.5374466180801392,
      "learning_rate": 0.001,
      "loss": 0.5124,
      "step": 455
    },
    {
      "epoch": 0.8428835489833642,
      "grad_norm": 0.731884241104126,
      "learning_rate": 0.001,
      "loss": 0.657,
      "step": 456
    },
    {
      "epoch": 0.844731977818854,
      "grad_norm": 0.6285644173622131,
      "learning_rate": 0.001,
      "loss": 0.878,
      "step": 457
    },
    {
      "epoch": 0.8465804066543438,
      "grad_norm": 0.6428564786911011,
      "learning_rate": 0.001,
      "loss": 0.6888,
      "step": 458
    },
    {
      "epoch": 0.8484288354898336,
      "grad_norm": 0.9038918614387512,
      "learning_rate": 0.001,
      "loss": 0.7343,
      "step": 459
    },
    {
      "epoch": 0.8502772643253235,
      "grad_norm": 0.6318102478981018,
      "learning_rate": 0.001,
      "loss": 0.803,
      "step": 460
    },
    {
      "epoch": 0.8521256931608133,
      "grad_norm": 0.7558817863464355,
      "learning_rate": 0.001,
      "loss": 0.847,
      "step": 461
    },
    {
      "epoch": 0.8539741219963032,
      "grad_norm": 0.6051446199417114,
      "learning_rate": 0.001,
      "loss": 0.7294,
      "step": 462
    },
    {
      "epoch": 0.8558225508317929,
      "grad_norm": 0.8236597776412964,
      "learning_rate": 0.001,
      "loss": 0.8389,
      "step": 463
    },
    {
      "epoch": 0.8576709796672828,
      "grad_norm": 0.5667428970336914,
      "learning_rate": 0.001,
      "loss": 0.5978,
      "step": 464
    },
    {
      "epoch": 0.8595194085027726,
      "grad_norm": 0.6218537092208862,
      "learning_rate": 0.001,
      "loss": 0.6539,
      "step": 465
    },
    {
      "epoch": 0.8613678373382625,
      "grad_norm": 0.6580603718757629,
      "learning_rate": 0.001,
      "loss": 0.5846,
      "step": 466
    },
    {
      "epoch": 0.8632162661737524,
      "grad_norm": 0.8344849348068237,
      "learning_rate": 0.001,
      "loss": 0.819,
      "step": 467
    },
    {
      "epoch": 0.8650646950092421,
      "grad_norm": 0.6353901028633118,
      "learning_rate": 0.001,
      "loss": 0.6255,
      "step": 468
    },
    {
      "epoch": 0.866913123844732,
      "grad_norm": 0.5879977345466614,
      "learning_rate": 0.001,
      "loss": 0.8907,
      "step": 469
    },
    {
      "epoch": 0.8687615526802218,
      "grad_norm": 0.7070827484130859,
      "learning_rate": 0.001,
      "loss": 0.7093,
      "step": 470
    },
    {
      "epoch": 0.8706099815157117,
      "grad_norm": 0.6677271127700806,
      "learning_rate": 0.001,
      "loss": 0.6718,
      "step": 471
    },
    {
      "epoch": 0.8724584103512015,
      "grad_norm": 0.5725215673446655,
      "learning_rate": 0.001,
      "loss": 0.7003,
      "step": 472
    },
    {
      "epoch": 0.8743068391866913,
      "grad_norm": 0.6160258054733276,
      "learning_rate": 0.001,
      "loss": 0.6447,
      "step": 473
    },
    {
      "epoch": 0.8761552680221811,
      "grad_norm": 0.8822168111801147,
      "learning_rate": 0.001,
      "loss": 0.6368,
      "step": 474
    },
    {
      "epoch": 0.878003696857671,
      "grad_norm": 1.4470586776733398,
      "learning_rate": 0.001,
      "loss": 0.9277,
      "step": 475
    },
    {
      "epoch": 0.8798521256931608,
      "grad_norm": 0.6264105439186096,
      "learning_rate": 0.001,
      "loss": 0.6375,
      "step": 476
    },
    {
      "epoch": 0.8817005545286506,
      "grad_norm": 0.7535873651504517,
      "learning_rate": 0.001,
      "loss": 0.6433,
      "step": 477
    },
    {
      "epoch": 0.8835489833641405,
      "grad_norm": 0.6162166595458984,
      "learning_rate": 0.001,
      "loss": 0.6918,
      "step": 478
    },
    {
      "epoch": 0.8853974121996303,
      "grad_norm": 0.6916104555130005,
      "learning_rate": 0.001,
      "loss": 0.6636,
      "step": 479
    },
    {
      "epoch": 0.8872458410351202,
      "grad_norm": 0.7060137987136841,
      "learning_rate": 0.001,
      "loss": 0.4684,
      "step": 480
    },
    {
      "epoch": 0.88909426987061,
      "grad_norm": 0.6374285221099854,
      "learning_rate": 0.001,
      "loss": 0.9017,
      "step": 481
    },
    {
      "epoch": 0.8909426987060998,
      "grad_norm": 0.5305145382881165,
      "learning_rate": 0.001,
      "loss": 0.5699,
      "step": 482
    },
    {
      "epoch": 0.8927911275415896,
      "grad_norm": 0.6026877164840698,
      "learning_rate": 0.001,
      "loss": 0.9496,
      "step": 483
    },
    {
      "epoch": 0.8946395563770795,
      "grad_norm": 0.6786549091339111,
      "learning_rate": 0.001,
      "loss": 0.804,
      "step": 484
    },
    {
      "epoch": 0.8964879852125693,
      "grad_norm": 0.7018754482269287,
      "learning_rate": 0.001,
      "loss": 0.737,
      "step": 485
    },
    {
      "epoch": 0.8983364140480592,
      "grad_norm": 0.4089026153087616,
      "learning_rate": 0.001,
      "loss": 0.5953,
      "step": 486
    },
    {
      "epoch": 0.9001848428835489,
      "grad_norm": 0.48161014914512634,
      "learning_rate": 0.001,
      "loss": 0.5167,
      "step": 487
    },
    {
      "epoch": 0.9020332717190388,
      "grad_norm": 0.7609049677848816,
      "learning_rate": 0.001,
      "loss": 0.7631,
      "step": 488
    },
    {
      "epoch": 0.9038817005545287,
      "grad_norm": 0.8507420420646667,
      "learning_rate": 0.001,
      "loss": 0.8331,
      "step": 489
    },
    {
      "epoch": 0.9057301293900185,
      "grad_norm": 0.549686074256897,
      "learning_rate": 0.001,
      "loss": 0.5609,
      "step": 490
    },
    {
      "epoch": 0.9075785582255084,
      "grad_norm": 0.8549586534500122,
      "learning_rate": 0.001,
      "loss": 0.7975,
      "step": 491
    },
    {
      "epoch": 0.9094269870609981,
      "grad_norm": 0.5464617609977722,
      "learning_rate": 0.001,
      "loss": 0.7603,
      "step": 492
    },
    {
      "epoch": 0.911275415896488,
      "grad_norm": 0.8106308579444885,
      "learning_rate": 0.001,
      "loss": 0.5753,
      "step": 493
    },
    {
      "epoch": 0.9131238447319778,
      "grad_norm": 1.0989980697631836,
      "learning_rate": 0.001,
      "loss": 0.8119,
      "step": 494
    },
    {
      "epoch": 0.9149722735674677,
      "grad_norm": 53.603729248046875,
      "learning_rate": 0.001,
      "loss": 3.5664,
      "step": 495
    },
    {
      "epoch": 0.9168207024029574,
      "grad_norm": 0.6865960359573364,
      "learning_rate": 0.001,
      "loss": 0.6459,
      "step": 496
    },
    {
      "epoch": 0.9186691312384473,
      "grad_norm": 0.7828227877616882,
      "learning_rate": 0.001,
      "loss": 0.9751,
      "step": 497
    },
    {
      "epoch": 0.9205175600739371,
      "grad_norm": 0.8201976418495178,
      "learning_rate": 0.001,
      "loss": 0.9485,
      "step": 498
    },
    {
      "epoch": 0.922365988909427,
      "grad_norm": 0.7697083353996277,
      "learning_rate": 0.001,
      "loss": 0.8864,
      "step": 499
    },
    {
      "epoch": 0.9242144177449169,
      "grad_norm": 0.4081413447856903,
      "learning_rate": 0.001,
      "loss": 0.5863,
      "step": 500
    },
    {
      "epoch": 0.9260628465804066,
      "grad_norm": 0.592320442199707,
      "learning_rate": 0.001,
      "loss": 0.7524,
      "step": 501
    },
    {
      "epoch": 0.9279112754158965,
      "grad_norm": 0.4706171452999115,
      "learning_rate": 0.001,
      "loss": 0.5649,
      "step": 502
    },
    {
      "epoch": 0.9297597042513863,
      "grad_norm": 0.4379749000072479,
      "learning_rate": 0.001,
      "loss": 0.5178,
      "step": 503
    },
    {
      "epoch": 0.9316081330868762,
      "grad_norm": 0.6452725529670715,
      "learning_rate": 0.001,
      "loss": 0.6012,
      "step": 504
    },
    {
      "epoch": 0.933456561922366,
      "grad_norm": 0.7428618669509888,
      "learning_rate": 0.001,
      "loss": 0.6258,
      "step": 505
    },
    {
      "epoch": 0.9353049907578558,
      "grad_norm": 0.7185813188552856,
      "learning_rate": 0.001,
      "loss": 0.899,
      "step": 506
    },
    {
      "epoch": 0.9371534195933456,
      "grad_norm": 0.8039231896400452,
      "learning_rate": 0.001,
      "loss": 0.8567,
      "step": 507
    },
    {
      "epoch": 0.9390018484288355,
      "grad_norm": 0.6219761371612549,
      "learning_rate": 0.001,
      "loss": 0.6672,
      "step": 508
    },
    {
      "epoch": 0.9408502772643254,
      "grad_norm": 0.8613112568855286,
      "learning_rate": 0.001,
      "loss": 1.0144,
      "step": 509
    },
    {
      "epoch": 0.9426987060998152,
      "grad_norm": 0.6800719499588013,
      "learning_rate": 0.001,
      "loss": 0.6831,
      "step": 510
    },
    {
      "epoch": 0.944547134935305,
      "grad_norm": 0.8042735457420349,
      "learning_rate": 0.001,
      "loss": 0.8125,
      "step": 511
    },
    {
      "epoch": 0.9463955637707948,
      "grad_norm": 0.8199442625045776,
      "learning_rate": 0.001,
      "loss": 1.2534,
      "step": 512
    },
    {
      "epoch": 0.9482439926062847,
      "grad_norm": 6.547449111938477,
      "learning_rate": 0.001,
      "loss": 0.8561,
      "step": 513
    },
    {
      "epoch": 0.9500924214417745,
      "grad_norm": 1.0684571266174316,
      "learning_rate": 0.001,
      "loss": 0.7813,
      "step": 514
    },
    {
      "epoch": 0.9519408502772643,
      "grad_norm": 4.597997665405273,
      "learning_rate": 0.001,
      "loss": 0.9715,
      "step": 515
    },
    {
      "epoch": 0.9537892791127541,
      "grad_norm": 1.0539919137954712,
      "learning_rate": 0.001,
      "loss": 0.7927,
      "step": 516
    },
    {
      "epoch": 0.955637707948244,
      "grad_norm": 0.7296995520591736,
      "learning_rate": 0.001,
      "loss": 0.7152,
      "step": 517
    },
    {
      "epoch": 0.9574861367837338,
      "grad_norm": 0.6043654084205627,
      "learning_rate": 0.001,
      "loss": 0.6799,
      "step": 518
    },
    {
      "epoch": 0.9593345656192237,
      "grad_norm": 0.5910910964012146,
      "learning_rate": 0.001,
      "loss": 0.6224,
      "step": 519
    },
    {
      "epoch": 0.9611829944547134,
      "grad_norm": 2.4806816577911377,
      "learning_rate": 0.001,
      "loss": 0.4854,
      "step": 520
    },
    {
      "epoch": 0.9630314232902033,
      "grad_norm": 1.4178262948989868,
      "learning_rate": 0.001,
      "loss": 0.9269,
      "step": 521
    },
    {
      "epoch": 0.9648798521256932,
      "grad_norm": 0.5048137307167053,
      "learning_rate": 0.001,
      "loss": 0.5043,
      "step": 522
    },
    {
      "epoch": 0.966728280961183,
      "grad_norm": 1.0623221397399902,
      "learning_rate": 0.001,
      "loss": 1.0081,
      "step": 523
    },
    {
      "epoch": 0.9685767097966729,
      "grad_norm": 0.6304468512535095,
      "learning_rate": 0.001,
      "loss": 0.6194,
      "step": 524
    },
    {
      "epoch": 0.9704251386321626,
      "grad_norm": 0.5621396899223328,
      "learning_rate": 0.001,
      "loss": 0.4772,
      "step": 525
    },
    {
      "epoch": 0.9722735674676525,
      "grad_norm": 0.7014063000679016,
      "learning_rate": 0.001,
      "loss": 0.7481,
      "step": 526
    },
    {
      "epoch": 0.9741219963031423,
      "grad_norm": 0.7803249359130859,
      "learning_rate": 0.001,
      "loss": 0.6818,
      "step": 527
    },
    {
      "epoch": 0.9759704251386322,
      "grad_norm": 0.56339430809021,
      "learning_rate": 0.001,
      "loss": 0.529,
      "step": 528
    },
    {
      "epoch": 0.977818853974122,
      "grad_norm": 1.3150532245635986,
      "learning_rate": 0.001,
      "loss": 0.85,
      "step": 529
    },
    {
      "epoch": 0.9796672828096118,
      "grad_norm": 0.73233562707901,
      "learning_rate": 0.001,
      "loss": 0.6697,
      "step": 530
    },
    {
      "epoch": 0.9815157116451017,
      "grad_norm": 15.183834075927734,
      "learning_rate": 0.001,
      "loss": 0.6668,
      "step": 531
    },
    {
      "epoch": 0.9833641404805915,
      "grad_norm": 0.710564136505127,
      "learning_rate": 0.001,
      "loss": 0.5376,
      "step": 532
    },
    {
      "epoch": 0.9852125693160814,
      "grad_norm": 0.9392178654670715,
      "learning_rate": 0.001,
      "loss": 0.8452,
      "step": 533
    },
    {
      "epoch": 0.9870609981515711,
      "grad_norm": 0.6461498737335205,
      "learning_rate": 0.001,
      "loss": 0.7486,
      "step": 534
    },
    {
      "epoch": 0.988909426987061,
      "grad_norm": 0.8957709670066833,
      "learning_rate": 0.001,
      "loss": 0.6943,
      "step": 535
    },
    {
      "epoch": 0.9907578558225508,
      "grad_norm": 1.0718097686767578,
      "learning_rate": 0.001,
      "loss": 0.7135,
      "step": 536
    },
    {
      "epoch": 0.9926062846580407,
      "grad_norm": 0.8124735355377197,
      "learning_rate": 0.001,
      "loss": 0.9046,
      "step": 537
    },
    {
      "epoch": 0.9944547134935305,
      "grad_norm": 0.6564399600028992,
      "learning_rate": 0.001,
      "loss": 0.7277,
      "step": 538
    },
    {
      "epoch": 0.9963031423290203,
      "grad_norm": 4.252345085144043,
      "learning_rate": 0.001,
      "loss": 0.9342,
      "step": 539
    },
    {
      "epoch": 0.9981515711645101,
      "grad_norm": 0.8855632543563843,
      "learning_rate": 0.001,
      "loss": 0.7394,
      "step": 540
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.0222349166870117,
      "learning_rate": 0.001,
      "loss": 0.8512,
      "step": 541
    },
    {
      "epoch": 1.0018484288354899,
      "grad_norm": 0.7332062721252441,
      "learning_rate": 0.001,
      "loss": 0.7089,
      "step": 542
    },
    {
      "epoch": 1.0036968576709797,
      "grad_norm": 0.7275331020355225,
      "learning_rate": 0.001,
      "loss": 0.6,
      "step": 543
    },
    {
      "epoch": 1.0055452865064696,
      "grad_norm": 0.7912113070487976,
      "learning_rate": 0.001,
      "loss": 0.7719,
      "step": 544
    },
    {
      "epoch": 1.0055452865064696,
      "eval_loss": 0.6085956692695618,
      "eval_runtime": 36.9382,
      "eval_samples_per_second": 1.489,
      "eval_steps_per_second": 0.19,
      "step": 544
    }
  ],
  "logging_steps": 1,
  "max_steps": 1623,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 136,
  "total_flos": 7.871105024380109e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}