{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9965635738831615,
  "eval_steps": 500,
  "global_step": 145,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 0.37809523940086365,
      "learning_rate": 2e-05,
      "loss": 1.7814,
      "step": 1
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.366623193025589,
      "learning_rate": 4e-05,
      "loss": 1.69,
      "step": 2
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.3546508848667145,
      "learning_rate": 6e-05,
      "loss": 1.7151,
      "step": 3
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.36381417512893677,
      "learning_rate": 8e-05,
      "loss": 1.6609,
      "step": 4
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.4049898684024811,
      "learning_rate": 0.0001,
      "loss": 1.752,
      "step": 5
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.4318874478340149,
      "learning_rate": 0.00012,
      "loss": 1.747,
      "step": 6
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.39768990874290466,
      "learning_rate": 0.00014,
      "loss": 1.4432,
      "step": 7
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.5056629180908203,
      "learning_rate": 0.00016,
      "loss": 1.7657,
      "step": 8
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.4276069104671478,
      "learning_rate": 0.00018,
      "loss": 1.4221,
      "step": 9
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.433552622795105,
      "learning_rate": 0.0002,
      "loss": 1.3117,
      "step": 10
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.42256900668144226,
      "learning_rate": 0.0001999972679420179,
      "loss": 1.2687,
      "step": 11
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3066452145576477,
      "learning_rate": 0.00019998907191735434,
      "loss": 1.0398,
      "step": 12
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.3393724858760834,
      "learning_rate": 0.00019997541237384966,
      "loss": 1.0063,
      "step": 13
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.49836328625679016,
      "learning_rate": 0.00019995629005787713,
      "loss": 1.2251,
      "step": 14
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.3539387285709381,
      "learning_rate": 0.0001999317060143023,
      "loss": 0.9454,
      "step": 15
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.35584160685539246,
      "learning_rate": 0.0001999016615864258,
      "loss": 1.0105,
      "step": 16
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.33191052079200745,
      "learning_rate": 0.00019986615841591002,
      "loss": 1.1322,
      "step": 17
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.3499913513660431,
      "learning_rate": 0.00019982519844268933,
      "loss": 0.8495,
      "step": 18
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.2582085132598877,
      "learning_rate": 0.0001997787839048642,
      "loss": 0.9725,
      "step": 19
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.23511624336242676,
      "learning_rate": 0.00019972691733857883,
      "loss": 0.9233,
      "step": 20
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.273019939661026,
      "learning_rate": 0.00019966960157788248,
      "loss": 1.0366,
      "step": 21
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.283527135848999,
      "learning_rate": 0.0001996068397545748,
      "loss": 0.9944,
      "step": 22
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.24311360716819763,
      "learning_rate": 0.00019953863529803466,
      "loss": 1.0308,
      "step": 23
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.24368223547935486,
      "learning_rate": 0.00019946499193503262,
      "loss": 1.0051,
      "step": 24
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.2269805669784546,
      "learning_rate": 0.0001993859136895274,
      "loss": 0.835,
      "step": 25
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.21915565431118011,
      "learning_rate": 0.00019930140488244602,
      "loss": 0.9997,
      "step": 26
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.21885964274406433,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.0013,
      "step": 27
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.22426557540893555,
      "learning_rate": 0.00019911611435067172,
      "loss": 0.8633,
      "step": 28
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.21587449312210083,
      "learning_rate": 0.0001990153427504683,
      "loss": 0.8479,
      "step": 29
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.24985891580581665,
      "learning_rate": 0.0001989091608371146,
      "loss": 0.8936,
      "step": 30
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.19733141362667084,
      "learning_rate": 0.0001987975744125135,
      "loss": 0.7743,
      "step": 31
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.1997266411781311,
      "learning_rate": 0.00019868058957387663,
      "loss": 0.9078,
      "step": 32
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.24114945530891418,
      "learning_rate": 0.00019855821271339125,
      "loss": 1.0413,
      "step": 33
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.2427120953798294,
      "learning_rate": 0.00019843045051787096,
      "loss": 0.8308,
      "step": 34
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.1968858540058136,
      "learning_rate": 0.0001982973099683902,
      "loss": 0.818,
      "step": 35
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.2783421576023102,
      "learning_rate": 0.00019815879833990304,
      "loss": 0.8504,
      "step": 36
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.23332269489765167,
      "learning_rate": 0.00019801492320084546,
      "loss": 0.9826,
      "step": 37
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.22864645719528198,
      "learning_rate": 0.00019786569241272197,
      "loss": 0.8705,
      "step": 38
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.20620585978031158,
      "learning_rate": 0.00019771111412967583,
      "loss": 0.8264,
      "step": 39
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.20590244233608246,
      "learning_rate": 0.00019755119679804367,
      "loss": 0.8455,
      "step": 40
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.20340456068515778,
      "learning_rate": 0.00019738594915589397,
      "loss": 0.871,
      "step": 41
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.2383277714252472,
      "learning_rate": 0.0001972153802325495,
      "loss": 0.6833,
      "step": 42
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.21479888260364532,
      "learning_rate": 0.00019703949934809408,
      "loss": 0.8355,
      "step": 43
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.23538872599601746,
      "learning_rate": 0.0001968583161128631,
      "loss": 0.8479,
      "step": 44
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.2260449230670929,
      "learning_rate": 0.00019667184042691875,
      "loss": 0.779,
      "step": 45
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.20232993364334106,
      "learning_rate": 0.0001964800824795087,
      "loss": 0.7293,
      "step": 46
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.19780154526233673,
      "learning_rate": 0.00019628305274850956,
      "loss": 0.7709,
      "step": 47
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.24822202324867249,
      "learning_rate": 0.00019608076199985433,
      "loss": 0.8885,
      "step": 48
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.20940056443214417,
      "learning_rate": 0.0001958732212869441,
      "loss": 0.6916,
      "step": 49
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.18944858014583588,
      "learning_rate": 0.0001956604419500441,
      "loss": 0.7326,
      "step": 50
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.201398104429245,
      "learning_rate": 0.00019544243561566403,
      "loss": 0.6542,
      "step": 51
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.22385160624980927,
      "learning_rate": 0.00019521921419592283,
      "loss": 0.8036,
      "step": 52
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.19502398371696472,
      "learning_rate": 0.0001949907898878977,
      "loss": 0.7579,
      "step": 53
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.21633867919445038,
      "learning_rate": 0.00019475717517295778,
      "loss": 0.7803,
      "step": 54
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.24109330773353577,
      "learning_rate": 0.00019451838281608197,
      "loss": 0.7745,
      "step": 55
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.20285621285438538,
      "learning_rate": 0.00019427442586516155,
      "loss": 0.7306,
      "step": 56
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.23838144540786743,
      "learning_rate": 0.00019402531765028722,
      "loss": 0.7606,
      "step": 57
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.25280559062957764,
      "learning_rate": 0.00019377107178302074,
      "loss": 0.7928,
      "step": 58
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.24614648520946503,
      "learning_rate": 0.00019351170215565114,
      "loss": 0.739,
      "step": 59
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.20391589403152466,
      "learning_rate": 0.00019324722294043558,
      "loss": 0.7636,
      "step": 60
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.23704086244106293,
      "learning_rate": 0.00019297764858882514,
      "loss": 0.6919,
      "step": 61
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.22057901322841644,
      "learning_rate": 0.00019270299383067498,
      "loss": 0.6035,
      "step": 62
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.22797846794128418,
      "learning_rate": 0.0001924232736734396,
      "loss": 0.7087,
      "step": 63
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.22181542217731476,
      "learning_rate": 0.00019213850340135276,
      "loss": 0.8088,
      "step": 64
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.2096872180700302,
      "learning_rate": 0.00019184869857459232,
      "loss": 0.7073,
      "step": 65
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.192199245095253,
      "learning_rate": 0.00019155387502843013,
      "loss": 0.6605,
      "step": 66
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.2242266982793808,
      "learning_rate": 0.00019125404887236663,
      "loss": 0.7287,
      "step": 67
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.24139907956123352,
      "learning_rate": 0.00019094923648925067,
      "loss": 0.6611,
      "step": 68
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.22859904170036316,
      "learning_rate": 0.00019063945453438432,
      "loss": 0.6189,
      "step": 69
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.27671098709106445,
      "learning_rate": 0.0001903247199346129,
      "loss": 0.8595,
      "step": 70
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.23342834413051605,
      "learning_rate": 0.00019000504988739986,
      "loss": 0.6718,
      "step": 71
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.2517896890640259,
      "learning_rate": 0.00018968046185988732,
      "loss": 0.722,
      "step": 72
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.25217679142951965,
      "learning_rate": 0.00018935097358794144,
      "loss": 0.824,
      "step": 73
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.2682301998138428,
      "learning_rate": 0.00018901660307518354,
      "loss": 0.7837,
      "step": 74
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.28926676511764526,
      "learning_rate": 0.0001886773685920062,
      "loss": 0.7364,
      "step": 75
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.25249186158180237,
      "learning_rate": 0.00018833328867457497,
      "loss": 0.8566,
      "step": 76
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.21752771735191345,
      "learning_rate": 0.0001879843821238155,
      "loss": 0.7077,
      "step": 77
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.22346794605255127,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.6522,
      "step": 78
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.23172937333583832,
      "learning_rate": 0.00018727216564363723,
      "loss": 0.6099,
      "step": 79
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.20895916223526,
      "learning_rate": 0.00018690889463055283,
      "loss": 0.7242,
      "step": 80
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.26868510246276855,
      "learning_rate": 0.0001865408748146826,
      "loss": 0.705,
      "step": 81
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.243666410446167,
      "learning_rate": 0.00018616812630505597,
      "loss": 0.8512,
      "step": 82
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.21445880830287933,
      "learning_rate": 0.00018579066946908384,
      "loss": 0.7092,
      "step": 83
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.22805824875831604,
      "learning_rate": 0.00018540852493144545,
      "loss": 0.6757,
      "step": 84
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.25106164813041687,
      "learning_rate": 0.00018502171357296144,
      "loss": 0.7171,
      "step": 85
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.2290162742137909,
      "learning_rate": 0.000184630256529453,
      "loss": 0.7053,
      "step": 86
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.21118655800819397,
      "learning_rate": 0.00018423417519058694,
      "loss": 0.5827,
      "step": 87
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.23761862516403198,
      "learning_rate": 0.00018383349119870695,
      "loss": 0.5827,
      "step": 88
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.23689566552639008,
      "learning_rate": 0.00018342822644765104,
      "loss": 0.6401,
      "step": 89
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.26510947942733765,
      "learning_rate": 0.00018301840308155507,
      "loss": 0.5963,
      "step": 90
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.2142990678548813,
      "learning_rate": 0.0001826040434936431,
      "loss": 0.6258,
      "step": 91
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.20709159970283508,
      "learning_rate": 0.00018218517032500344,
      "loss": 0.5685,
      "step": 92
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.2485310137271881,
      "learning_rate": 0.0001817618064633518,
      "loss": 0.5901,
      "step": 93
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.2432468980550766,
      "learning_rate": 0.00018133397504178057,
      "loss": 0.6891,
      "step": 94
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.2318205088376999,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.7339,
      "step": 95
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.25346460938453674,
      "learning_rate": 0.00018046500327053463,
      "loss": 0.6606,
      "step": 96
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.29421111941337585,
      "learning_rate": 0.0001800239104024851,
      "loss": 0.6698,
      "step": 97
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.2356603443622589,
      "learning_rate": 0.00017957844493517213,
      "loss": 0.6225,
      "step": 98
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.2331649512052536,
      "learning_rate": 0.00017912863120934534,
      "loss": 0.6838,
      "step": 99
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.23008978366851807,
      "learning_rate": 0.00017867449380334834,
      "loss": 0.6303,
      "step": 100
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.21604081988334656,
      "learning_rate": 0.00017821605753177562,
      "loss": 0.4923,
      "step": 101
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.2283111810684204,
      "learning_rate": 0.00017775334744411678,
      "loss": 0.6344,
      "step": 102
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.2448730617761612,
      "learning_rate": 0.00017728638882338746,
      "loss": 0.6789,
      "step": 103
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.22479577362537384,
      "learning_rate": 0.00017681520718474823,
      "loss": 0.5841,
      "step": 104
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.21999216079711914,
      "learning_rate": 0.00017633982827411032,
      "loss": 0.6402,
      "step": 105
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.2296195775270462,
      "learning_rate": 0.00017586027806672857,
      "loss": 0.6148,
      "step": 106
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.22455835342407227,
      "learning_rate": 0.00017537658276578247,
      "loss": 0.6418,
      "step": 107
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.23929741978645325,
      "learning_rate": 0.00017488876880094413,
      "loss": 0.5459,
      "step": 108
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.229934424161911,
      "learning_rate": 0.00017439686282693436,
      "loss": 0.6049,
      "step": 109
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.24801373481750488,
      "learning_rate": 0.00017390089172206592,
      "loss": 0.7663,
      "step": 110
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.2523267865180969,
      "learning_rate": 0.00017340088258677522,
      "loss": 0.6642,
      "step": 111
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.22252008318901062,
      "learning_rate": 0.00017289686274214118,
      "loss": 0.6325,
      "step": 112
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.27619731426239014,
      "learning_rate": 0.0001723888597283926,
      "loss": 0.655,
      "step": 113
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.25090277194976807,
      "learning_rate": 0.00017187690130340328,
      "loss": 0.6251,
      "step": 114
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.2236175239086151,
      "learning_rate": 0.00017136101544117525,
      "loss": 0.5959,
      "step": 115
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.21940240263938904,
      "learning_rate": 0.00017084123033031024,
      "loss": 0.6028,
      "step": 116
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.2741597294807434,
      "learning_rate": 0.00017031757437246947,
      "loss": 0.4947,
      "step": 117
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.23343035578727722,
      "learning_rate": 0.00016979007618082175,
      "loss": 0.4415,
      "step": 118
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.2116251140832901,
      "learning_rate": 0.00016925876457848,
      "loss": 0.5283,
      "step": 119
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.25621068477630615,
      "learning_rate": 0.00016872366859692627,
      "loss": 0.7334,
      "step": 120
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.22588759660720825,
      "learning_rate": 0.00016818481747442554,
      "loss": 0.6514,
      "step": 121
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.24995574355125427,
      "learning_rate": 0.00016764224065442796,
      "loss": 0.5632,
      "step": 122
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.2382134348154068,
      "learning_rate": 0.00016709596778396026,
      "loss": 0.5954,
      "step": 123
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.25166618824005127,
      "learning_rate": 0.00016654602871200546,
      "loss": 0.6092,
      "step": 124
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.23028074204921722,
      "learning_rate": 0.0001659924534878723,
      "loss": 0.576,
      "step": 125
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.2527604103088379,
      "learning_rate": 0.00016543527235955282,
      "loss": 0.5985,
      "step": 126
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.25870686769485474,
      "learning_rate": 0.00016487451577207018,
      "loss": 0.5767,
      "step": 127
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.24936434626579285,
      "learning_rate": 0.0001643102143658145,
      "loss": 0.7494,
      "step": 128
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.25158020853996277,
      "learning_rate": 0.000163742398974869,
      "loss": 0.578,
      "step": 129
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.22290346026420593,
      "learning_rate": 0.0001631711006253251,
      "loss": 0.6489,
      "step": 130
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.26421919465065,
      "learning_rate": 0.00016259635053358717,
      "loss": 0.5669,
      "step": 131
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.2573990225791931,
      "learning_rate": 0.0001620181801046667,
      "loss": 0.6405,
      "step": 132
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.19883453845977783,
      "learning_rate": 0.00016143662093046638,
      "loss": 0.4731,
      "step": 133
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.24181459844112396,
      "learning_rate": 0.00016085170478805395,
      "loss": 0.6819,
      "step": 134
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.2319963425397873,
      "learning_rate": 0.00016026346363792567,
      "loss": 0.6373,
      "step": 135
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.2552095055580139,
      "learning_rate": 0.0001596719296222601,
      "loss": 0.7151,
      "step": 136
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.27191445231437683,
      "learning_rate": 0.00015907713506316192,
      "loss": 0.611,
      "step": 137
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.26981061697006226,
      "learning_rate": 0.0001584791124608955,
      "loss": 0.5923,
      "step": 138
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.23907916247844696,
      "learning_rate": 0.00015787789449210938,
      "loss": 0.5655,
      "step": 139
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.23364509642124176,
      "learning_rate": 0.00015727351400805052,
      "loss": 0.6019,
      "step": 140
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.23096178472042084,
      "learning_rate": 0.0001566660040327695,
      "loss": 0.602,
      "step": 141
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.2656322717666626,
      "learning_rate": 0.0001560553977613158,
      "loss": 0.6195,
      "step": 142
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.23051652312278748,
      "learning_rate": 0.00015544172855792423,
      "loss": 0.6132,
      "step": 143
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.2443581074476242,
      "learning_rate": 0.00015482502995419167,
      "loss": 0.6144,
      "step": 144
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2075706273317337,
      "learning_rate": 0.00015420533564724495,
      "loss": 0.5556,
      "step": 145
    }
  ],
  "logging_steps": 1,
  "max_steps": 435,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 145,
  "total_flos": 9.76361694953472e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}