{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.30042194092827,
  "eval_steps": 500,
  "global_step": 267,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.33328112959861755,
      "learning_rate": 2e-05,
      "loss": 0.9029,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.341234415769577,
      "learning_rate": 4e-05,
      "loss": 0.9276,
      "step": 2
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.3182106614112854,
      "learning_rate": 6e-05,
      "loss": 0.9148,
      "step": 3
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.22865141928195953,
      "learning_rate": 8e-05,
      "loss": 0.8421,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.29670122265815735,
      "learning_rate": 0.0001,
      "loss": 0.7984,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.28762516379356384,
      "learning_rate": 0.00012,
      "loss": 0.7625,
      "step": 6
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.23907965421676636,
      "learning_rate": 0.00014,
      "loss": 0.7226,
      "step": 7
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.19532263278961182,
      "learning_rate": 0.00016,
      "loss": 0.7043,
      "step": 8
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.1425202488899231,
      "learning_rate": 0.00018,
      "loss": 0.6784,
      "step": 9
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.10882167518138885,
      "learning_rate": 0.0002,
      "loss": 0.6579,
      "step": 10
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.11275648325681686,
      "learning_rate": 0.00019999935985220405,
      "loss": 0.6592,
      "step": 11
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.10155748575925827,
      "learning_rate": 0.00019999743941701188,
      "loss": 0.6554,
      "step": 12
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.0845816433429718,
      "learning_rate": 0.0001999942387190108,
      "loss": 0.6513,
      "step": 13
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.09046202898025513,
      "learning_rate": 0.0001999897577991792,
      "loss": 0.6267,
      "step": 14
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.08296829462051392,
      "learning_rate": 0.00019998399671488612,
      "loss": 0.6434,
      "step": 15
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.07594181597232819,
      "learning_rate": 0.00019997695553989042,
      "loss": 0.6096,
      "step": 16
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.0683172270655632,
      "learning_rate": 0.00019996863436433997,
      "loss": 0.6143,
      "step": 17
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.05627186596393585,
      "learning_rate": 0.0001999590332947704,
      "loss": 0.6024,
      "step": 18
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.05644279345870018,
      "learning_rate": 0.00019994815245410384,
      "loss": 0.595,
      "step": 19
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.05661479011178017,
      "learning_rate": 0.00019993599198164715,
      "loss": 0.5759,
      "step": 20
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.04077177122235298,
      "learning_rate": 0.00019992255203309033,
      "loss": 0.582,
      "step": 21
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.04510512948036194,
      "learning_rate": 0.00019990783278050448,
      "loss": 0.5751,
      "step": 22
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.0470162108540535,
      "learning_rate": 0.00019989183441233952,
      "loss": 0.5716,
      "step": 23
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.04402562975883484,
      "learning_rate": 0.00019987455713342187,
      "loss": 0.564,
      "step": 24
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.045594893395900726,
      "learning_rate": 0.00019985600116495173,
      "loss": 0.5657,
      "step": 25
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.037670280784368515,
      "learning_rate": 0.0001998361667445004,
      "loss": 0.5619,
      "step": 26
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.034366946667432785,
      "learning_rate": 0.00019981505412600706,
      "loss": 0.554,
      "step": 27
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.044084370136260986,
      "learning_rate": 0.00019979266357977564,
      "loss": 0.5527,
      "step": 28
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.04839107394218445,
      "learning_rate": 0.0001997689953924713,
      "loss": 0.5534,
      "step": 29
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.04943666234612465,
      "learning_rate": 0.0001997440498671168,
      "loss": 0.5357,
      "step": 30
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.05644814297556877,
      "learning_rate": 0.00019971782732308867,
      "loss": 0.5388,
      "step": 31
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.05796538665890694,
      "learning_rate": 0.00019969032809611287,
      "loss": 0.5327,
      "step": 32
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.05399211496114731,
      "learning_rate": 0.0001996615525382609,
      "loss": 0.5447,
      "step": 33
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.03574652597308159,
      "learning_rate": 0.0001996315010179449,
      "loss": 0.5213,
      "step": 34
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.04394914582371712,
      "learning_rate": 0.00019960017391991314,
      "loss": 0.5247,
      "step": 35
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.05197073519229889,
      "learning_rate": 0.00019956757164524516,
      "loss": 0.5253,
      "step": 36
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.05605654790997505,
      "learning_rate": 0.00019953369461134634,
      "loss": 0.5289,
      "step": 37
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.05167644843459129,
      "learning_rate": 0.00019949854325194294,
      "loss": 0.5223,
      "step": 38
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.04118728265166283,
      "learning_rate": 0.0001994621180170762,
      "loss": 0.52,
      "step": 39
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0373263917863369,
      "learning_rate": 0.00019942441937309684,
      "loss": 0.5076,
      "step": 40
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.04870600998401642,
      "learning_rate": 0.0001993854478026589,
      "loss": 0.5287,
      "step": 41
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.05014103651046753,
      "learning_rate": 0.00019934520380471372,
      "loss": 0.5048,
      "step": 42
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.04807833209633827,
      "learning_rate": 0.0001993036878945034,
      "loss": 0.5075,
      "step": 43
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.040045421570539474,
      "learning_rate": 0.0001992609006035543,
      "loss": 0.4954,
      "step": 44
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.04202349856495857,
      "learning_rate": 0.00019921684247967028,
      "loss": 0.4953,
      "step": 45
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.041629109531641006,
      "learning_rate": 0.0001991715140869255,
      "loss": 0.501,
      "step": 46
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.04767894372344017,
      "learning_rate": 0.0001991249160056574,
      "loss": 0.4878,
      "step": 47
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.05395263060927391,
      "learning_rate": 0.00019907704883245916,
      "loss": 0.5014,
      "step": 48
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.06040235981345177,
      "learning_rate": 0.00019902791318017205,
      "loss": 0.5043,
      "step": 49
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.06749273091554642,
      "learning_rate": 0.0001989775096778777,
      "loss": 0.4931,
      "step": 50
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.06482889503240585,
      "learning_rate": 0.00019892583897088994,
      "loss": 0.4869,
      "step": 51
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.045358914881944656,
      "learning_rate": 0.0001988729017207465,
      "loss": 0.479,
      "step": 52
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.043360061943531036,
      "learning_rate": 0.00019881869860520073,
      "loss": 0.4953,
      "step": 53
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.060205183923244476,
      "learning_rate": 0.00019876323031821266,
      "loss": 0.4705,
      "step": 54
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.05729120969772339,
      "learning_rate": 0.00019870649756994037,
      "loss": 0.4887,
      "step": 55
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.03843148052692413,
      "learning_rate": 0.00019864850108673073,
      "loss": 0.4737,
      "step": 56
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.053673889487981796,
      "learning_rate": 0.00019858924161111015,
      "loss": 0.4817,
      "step": 57
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.05148368701338768,
      "learning_rate": 0.00019852871990177503,
      "loss": 0.4763,
      "step": 58
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.05371672287583351,
      "learning_rate": 0.00019846693673358226,
      "loss": 0.4751,
      "step": 59
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.05490916967391968,
      "learning_rate": 0.00019840389289753896,
      "loss": 0.457,
      "step": 60
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.04629400372505188,
      "learning_rate": 0.00019833958920079255,
      "loss": 0.4692,
      "step": 61
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.051137253642082214,
      "learning_rate": 0.00019827402646662047,
      "loss": 0.4614,
      "step": 62
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.051790811121463776,
      "learning_rate": 0.0001982072055344195,
      "loss": 0.4594,
      "step": 63
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0445956289768219,
      "learning_rate": 0.00019813912725969509,
      "loss": 0.4601,
      "step": 64
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.04766576737165451,
      "learning_rate": 0.0001980697925140504,
      "loss": 0.4631,
      "step": 65
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.04839074984192848,
      "learning_rate": 0.0001979992021851751,
      "loss": 0.4605,
      "step": 66
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.04736727103590965,
      "learning_rate": 0.0001979273571768341,
      "loss": 0.4617,
      "step": 67
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.057293377816677094,
      "learning_rate": 0.0001978542584088558,
      "loss": 0.4621,
      "step": 68
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.05025665834546089,
      "learning_rate": 0.0001977799068171206,
      "loss": 0.4671,
      "step": 69
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.057366687804460526,
      "learning_rate": 0.0001977043033535486,
      "loss": 0.4521,
      "step": 70
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07595837116241455,
      "learning_rate": 0.00019762744898608762,
      "loss": 0.4671,
      "step": 71
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07574213296175003,
      "learning_rate": 0.0001975493446987007,
      "loss": 0.4664,
      "step": 72
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.06472938507795334,
      "learning_rate": 0.00019746999149135362,
      "loss": 0.456,
      "step": 73
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.05983012542128563,
      "learning_rate": 0.00019738939038000205,
      "loss": 0.4459,
      "step": 74
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.05136057734489441,
      "learning_rate": 0.00019730754239657842,
      "loss": 0.4486,
      "step": 75
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.06191498041152954,
      "learning_rate": 0.00019722444858897878,
      "loss": 0.4424,
      "step": 76
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.06742191314697266,
      "learning_rate": 0.0001971401100210496,
      "loss": 0.458,
      "step": 77
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.06019548326730728,
      "learning_rate": 0.00019705452777257377,
      "loss": 0.4423,
      "step": 78
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.05012982338666916,
      "learning_rate": 0.0001969677029392571,
      "loss": 0.4466,
      "step": 79
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.0552060566842556,
      "learning_rate": 0.00019687963663271409,
      "loss": 0.4534,
      "step": 80
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.05883748456835747,
      "learning_rate": 0.00019679032998045376,
      "loss": 0.4409,
      "step": 81
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.07146705687046051,
      "learning_rate": 0.00019669978412586528,
      "loss": 0.4582,
      "step": 82
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.054095230996608734,
      "learning_rate": 0.00019660800022820317,
      "loss": 0.4487,
      "step": 83
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.04927053675055504,
      "learning_rate": 0.00019651497946257266,
      "loss": 0.4429,
      "step": 84
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.06037526577711105,
      "learning_rate": 0.00019642072301991455,
      "loss": 0.4456,
      "step": 85
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.05555957555770874,
      "learning_rate": 0.00019632523210698987,
      "loss": 0.4382,
      "step": 86
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.04606284573674202,
      "learning_rate": 0.00019622850794636455,
      "loss": 0.4411,
      "step": 87
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.04605920985341072,
      "learning_rate": 0.00019613055177639384,
      "loss": 0.4326,
      "step": 88
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.050325632095336914,
      "learning_rate": 0.0001960313648512062,
      "loss": 0.4338,
      "step": 89
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.04921424016356468,
      "learning_rate": 0.00019593094844068748,
      "loss": 0.4316,
      "step": 90
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.04333706200122833,
      "learning_rate": 0.00019582930383046457,
      "loss": 0.4441,
      "step": 91
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.048454612493515015,
      "learning_rate": 0.0001957264323218889,
      "loss": 0.4382,
      "step": 92
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0541059784591198,
      "learning_rate": 0.00019562233523201986,
      "loss": 0.4328,
      "step": 93
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.043696511536836624,
      "learning_rate": 0.00019551701389360795,
      "loss": 0.4335,
      "step": 94
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.04407835751771927,
      "learning_rate": 0.00019541046965507758,
      "loss": 0.4327,
      "step": 95
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.05477238819003105,
      "learning_rate": 0.00019530270388050998,
      "loss": 0.4294,
      "step": 96
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.05609311908483505,
      "learning_rate": 0.00019519371794962556,
      "loss": 0.4305,
      "step": 97
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.045145273208618164,
      "learning_rate": 0.00019508351325776642,
      "loss": 0.4395,
      "step": 98
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.04475285857915878,
      "learning_rate": 0.00019497209121587837,
      "loss": 0.4284,
      "step": 99
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.04405711591243744,
      "learning_rate": 0.00019485945325049288,
      "loss": 0.4214,
      "step": 100
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.04461454227566719,
      "learning_rate": 0.0001947456008037089,
      "loss": 0.4154,
      "step": 101
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.04791221395134926,
      "learning_rate": 0.00019463053533317425,
      "loss": 0.4248,
      "step": 102
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.05543987452983856,
      "learning_rate": 0.00019451425831206706,
      "loss": 0.4303,
      "step": 103
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.06330578774213791,
      "learning_rate": 0.00019439677122907697,
      "loss": 0.4274,
      "step": 104
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.05569112300872803,
      "learning_rate": 0.00019427807558838588,
      "loss": 0.4234,
      "step": 105
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.047680530697107315,
      "learning_rate": 0.00019415817290964883,
      "loss": 0.4155,
      "step": 106
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.05214262008666992,
      "learning_rate": 0.0001940370647279746,
      "loss": 0.4224,
      "step": 107
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.06332990527153015,
      "learning_rate": 0.00019391475259390584,
      "loss": 0.4233,
      "step": 108
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.05726313218474388,
      "learning_rate": 0.00019379123807339942,
      "loss": 0.4118,
      "step": 109
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.044936031103134155,
      "learning_rate": 0.00019366652274780628,
      "loss": 0.4296,
      "step": 110
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.05117325484752655,
      "learning_rate": 0.0001935406082138513,
      "loss": 0.4287,
      "step": 111
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.058542776852846146,
      "learning_rate": 0.00019341349608361267,
      "loss": 0.4213,
      "step": 112
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.056066304445266724,
      "learning_rate": 0.00019328518798450138,
      "loss": 0.4174,
      "step": 113
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.049762677401304245,
      "learning_rate": 0.00019315568555924035,
      "loss": 0.418,
      "step": 114
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.043821126222610474,
      "learning_rate": 0.00019302499046584348,
      "loss": 0.4012,
      "step": 115
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.05036221817135811,
      "learning_rate": 0.00019289310437759427,
      "loss": 0.4237,
      "step": 116
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.050889529287815094,
      "learning_rate": 0.00019276002898302447,
      "loss": 0.4144,
      "step": 117
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.04269757494330406,
      "learning_rate": 0.0001926257659858925,
      "loss": 0.4078,
      "step": 118
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.04927165433764458,
      "learning_rate": 0.00019249031710516162,
      "loss": 0.4155,
      "step": 119
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.05124311521649361,
      "learning_rate": 0.00019235368407497788,
      "loss": 0.3966,
      "step": 120
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.04073040187358856,
      "learning_rate": 0.00019221586864464786,
      "loss": 0.4064,
      "step": 121
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.04988453537225723,
      "learning_rate": 0.00019207687257861655,
      "loss": 0.4197,
      "step": 122
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.05227258801460266,
      "learning_rate": 0.0001919366976564444,
      "loss": 0.414,
      "step": 123
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.0466819666326046,
      "learning_rate": 0.00019179534567278475,
      "loss": 0.4173,
      "step": 124
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.047633491456508636,
      "learning_rate": 0.00019165281843736085,
      "loss": 0.4085,
      "step": 125
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.05280464142560959,
      "learning_rate": 0.00019150911777494258,
      "loss": 0.4051,
      "step": 126
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.052302148193120956,
      "learning_rate": 0.00019136424552532318,
      "loss": 0.42,
      "step": 127
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.04875241965055466,
      "learning_rate": 0.00019121820354329577,
      "loss": 0.4258,
      "step": 128
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.04654408246278763,
      "learning_rate": 0.0001910709936986293,
      "loss": 0.409,
      "step": 129
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.05745020881295204,
      "learning_rate": 0.00019092261787604492,
      "loss": 0.4059,
      "step": 130
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.06945241987705231,
      "learning_rate": 0.00019077307797519183,
      "loss": 0.4038,
      "step": 131
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.06346461176872253,
      "learning_rate": 0.00019062237591062272,
      "loss": 0.4031,
      "step": 132
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.058026187121868134,
      "learning_rate": 0.00019047051361176953,
      "loss": 0.4126,
      "step": 133
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.04755179584026337,
      "learning_rate": 0.0001903174930229185,
      "loss": 0.4209,
      "step": 134
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.05765068158507347,
      "learning_rate": 0.0001901633161031856,
      "loss": 0.4067,
      "step": 135
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.05687811225652695,
      "learning_rate": 0.000190007984826491,
      "loss": 0.3975,
      "step": 136
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.04930473491549492,
      "learning_rate": 0.0001898515011815343,
      "loss": 0.4146,
      "step": 137
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.05147051811218262,
      "learning_rate": 0.0001896938671717687,
      "loss": 0.4035,
      "step": 138
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.05680418014526367,
      "learning_rate": 0.0001895350848153754,
      "loss": 0.4049,
      "step": 139
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0444297268986702,
      "learning_rate": 0.00018937515614523797,
      "loss": 0.4085,
      "step": 140
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.05083802342414856,
      "learning_rate": 0.00018921408320891612,
      "loss": 0.4036,
      "step": 141
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.04978756606578827,
      "learning_rate": 0.00018905186806861957,
      "loss": 0.4058,
      "step": 142
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.04963681101799011,
      "learning_rate": 0.00018888851280118155,
      "loss": 0.3977,
      "step": 143
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0466095507144928,
      "learning_rate": 0.00018872401949803237,
      "loss": 0.3945,
      "step": 144
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.04972768574953079,
      "learning_rate": 0.00018855839026517257,
      "loss": 0.4151,
      "step": 145
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.054370637983083725,
      "learning_rate": 0.0001883916272231459,
      "loss": 0.3944,
      "step": 146
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.054699357599020004,
      "learning_rate": 0.00018822373250701224,
      "loss": 0.3989,
      "step": 147
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.054452769458293915,
      "learning_rate": 0.00018805470826632024,
      "loss": 0.3984,
      "step": 148
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.04596908017992973,
      "learning_rate": 0.00018788455666507981,
      "loss": 0.4018,
      "step": 149
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.054354868829250336,
      "learning_rate": 0.00018771327988173435,
      "loss": 0.3985,
      "step": 150
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.05570242181420326,
      "learning_rate": 0.00018754088010913304,
      "loss": 0.3818,
      "step": 151
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.054722048342227936,
      "learning_rate": 0.00018736735955450251,
      "loss": 0.4111,
      "step": 152
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.04620000347495079,
      "learning_rate": 0.00018719272043941882,
      "loss": 0.3949,
      "step": 153
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.048443205654621124,
      "learning_rate": 0.00018701696499977884,
      "loss": 0.3856,
      "step": 154
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.06628945469856262,
      "learning_rate": 0.00018684009548577168,
      "loss": 0.4048,
      "step": 155
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.05339967459440231,
      "learning_rate": 0.00018666211416184999,
      "loss": 0.3894,
      "step": 156
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.04650304839015007,
      "learning_rate": 0.00018648302330670082,
      "loss": 0.4004,
      "step": 157
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.05634591728448868,
      "learning_rate": 0.00018630282521321645,
      "loss": 0.4033,
      "step": 158
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.048666685819625854,
      "learning_rate": 0.00018612152218846513,
      "loss": 0.399,
      "step": 159
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.04597772657871246,
      "learning_rate": 0.0001859391165536615,
      "loss": 0.3931,
      "step": 160
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.0526028610765934,
      "learning_rate": 0.00018575561064413689,
      "loss": 0.3879,
      "step": 161
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.05867009237408638,
      "learning_rate": 0.00018557100680930937,
      "loss": 0.3905,
      "step": 162
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.05077454075217247,
      "learning_rate": 0.00018538530741265364,
      "loss": 0.395,
      "step": 163
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.0461389385163784,
      "learning_rate": 0.00018519851483167097,
      "loss": 0.4016,
      "step": 164
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.059010252356529236,
      "learning_rate": 0.00018501063145785846,
      "loss": 0.3823,
      "step": 165
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.06437338888645172,
      "learning_rate": 0.00018482165969667874,
      "loss": 0.3918,
      "step": 166
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.04585932940244675,
      "learning_rate": 0.00018463160196752887,
      "loss": 0.3808,
      "step": 167
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.05361521616578102,
      "learning_rate": 0.00018444046070370963,
      "loss": 0.3858,
      "step": 168
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.05653822794556618,
      "learning_rate": 0.00018424823835239417,
      "loss": 0.3785,
      "step": 169
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.04439689964056015,
      "learning_rate": 0.0001840549373745968,
      "loss": 0.3894,
      "step": 170
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.05564529448747635,
      "learning_rate": 0.00018386056024514137,
      "loss": 0.3883,
      "step": 171
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.06035888195037842,
      "learning_rate": 0.00018366510945262972,
      "loss": 0.3855,
      "step": 172
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.044238511472940445,
      "learning_rate": 0.0001834685874994098,
      "loss": 0.3934,
      "step": 173
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.050235260277986526,
      "learning_rate": 0.00018327099690154344,
      "loss": 0.3819,
      "step": 174
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.051336683332920074,
      "learning_rate": 0.00018307234018877434,
      "loss": 0.3897,
      "step": 175
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.045052576810121536,
      "learning_rate": 0.0001828726199044957,
      "loss": 0.3822,
      "step": 176
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.05162283405661583,
      "learning_rate": 0.00018267183860571753,
      "loss": 0.4047,
      "step": 177
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0488157793879509,
      "learning_rate": 0.00018246999886303383,
      "loss": 0.3947,
      "step": 178
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.04454487934708595,
      "learning_rate": 0.00018226710326059006,
      "loss": 0.3942,
      "step": 179
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0500001423060894,
      "learning_rate": 0.0001820631543960496,
      "loss": 0.3826,
      "step": 180
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.04919865354895592,
      "learning_rate": 0.00018185815488056076,
      "loss": 0.3791,
      "step": 181
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.04547140747308731,
      "learning_rate": 0.00018165210733872336,
      "loss": 0.3879,
      "step": 182
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.044622063636779785,
      "learning_rate": 0.00018144501440855496,
      "loss": 0.3778,
      "step": 183
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.04467932507395744,
      "learning_rate": 0.00018123687874145721,
      "loss": 0.3994,
      "step": 184
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.04281982406973839,
      "learning_rate": 0.0001810277030021819,
      "loss": 0.3817,
      "step": 185
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.05303504317998886,
      "learning_rate": 0.00018081748986879679,
      "loss": 0.3749,
      "step": 186
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.046573616564273834,
      "learning_rate": 0.00018060624203265134,
      "loss": 0.3866,
      "step": 187
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.044320229440927505,
      "learning_rate": 0.00018039396219834237,
      "loss": 0.3732,
      "step": 188
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.05708359181880951,
      "learning_rate": 0.00018018065308367912,
      "loss": 0.3863,
      "step": 189
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.045029208064079285,
      "learning_rate": 0.00017996631741964888,
      "loss": 0.3862,
      "step": 190
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.055195923894643784,
      "learning_rate": 0.00017975095795038165,
      "loss": 0.3835,
      "step": 191
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.048293352127075195,
      "learning_rate": 0.00017953457743311523,
      "loss": 0.374,
      "step": 192
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.04677055403590202,
      "learning_rate": 0.00017931717863815987,
      "loss": 0.377,
      "step": 193
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.04955766722559929,
      "learning_rate": 0.00017909876434886273,
      "loss": 0.3808,
      "step": 194
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.04526973515748978,
      "learning_rate": 0.00017887933736157233,
      "loss": 0.3796,
      "step": 195
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.043622203171253204,
      "learning_rate": 0.00017865890048560277,
      "loss": 0.376,
      "step": 196
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.046581387519836426,
      "learning_rate": 0.0001784374565431976,
      "loss": 0.3716,
      "step": 197
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.04433497413992882,
      "learning_rate": 0.00017821500836949386,
      "loss": 0.3715,
      "step": 198
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.04146367311477661,
      "learning_rate": 0.00017799155881248572,
      "loss": 0.3809,
      "step": 199
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.045288585126399994,
      "learning_rate": 0.000177767110732988,
      "loss": 0.3885,
      "step": 200
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.04070120304822922,
      "learning_rate": 0.00017754166700459958,
      "loss": 0.3713,
      "step": 201
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.042820919305086136,
      "learning_rate": 0.00017731523051366658,
      "loss": 0.3839,
      "step": 202
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.04416365176439285,
      "learning_rate": 0.00017708780415924539,
      "loss": 0.3728,
      "step": 203
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.04461952671408653,
      "learning_rate": 0.00017685939085306562,
      "loss": 0.373,
      "step": 204
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.04675828292965889,
      "learning_rate": 0.00017662999351949278,
      "loss": 0.3711,
      "step": 205
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.04258272796869278,
      "learning_rate": 0.00017639961509549078,
      "loss": 0.3782,
      "step": 206
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.04638506844639778,
      "learning_rate": 0.00017616825853058443,
      "loss": 0.3592,
      "step": 207
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.04781416058540344,
      "learning_rate": 0.00017593592678682166,
      "loss": 0.383,
      "step": 208
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.04813629388809204,
      "learning_rate": 0.00017570262283873552,
      "loss": 0.3775,
      "step": 209
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.046996332705020905,
      "learning_rate": 0.00017546834967330617,
      "loss": 0.3815,
      "step": 210
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.04889595881104469,
      "learning_rate": 0.00017523311028992268,
      "loss": 0.3636,
      "step": 211
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.04298345744609833,
      "learning_rate": 0.00017499690770034443,
      "loss": 0.3672,
      "step": 212
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.04219110682606697,
      "learning_rate": 0.00017475974492866278,
      "loss": 0.3801,
      "step": 213
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.051573265343904495,
      "learning_rate": 0.00017452162501126227,
      "loss": 0.3778,
      "step": 214
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.048954349011182785,
      "learning_rate": 0.00017428255099678167,
      "loss": 0.3849,
      "step": 215
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.042610183358192444,
      "learning_rate": 0.0001740425259460751,
      "loss": 0.3682,
      "step": 216
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.04517417773604393,
      "learning_rate": 0.00017380155293217264,
      "loss": 0.3827,
      "step": 217
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.04968888312578201,
      "learning_rate": 0.00017355963504024123,
      "loss": 0.3821,
      "step": 218
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.051313381642103195,
      "learning_rate": 0.0001733167753675449,
      "loss": 0.381,
      "step": 219
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.044351302087306976,
      "learning_rate": 0.0001730729770234054,
      "loss": 0.381,
      "step": 220
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.03970547392964363,
      "learning_rate": 0.00017282824312916218,
      "loss": 0.3698,
      "step": 221
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.04822370782494545,
      "learning_rate": 0.00017258257681813244,
      "loss": 0.3838,
      "step": 222
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.045927174389362335,
      "learning_rate": 0.0001723359812355712,
      "loss": 0.3662,
      "step": 223
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.042983219027519226,
      "learning_rate": 0.00017208845953863076,
      "loss": 0.3574,
      "step": 224
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.0422198586165905,
      "learning_rate": 0.0001718400148963206,
      "loss": 0.3559,
      "step": 225
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.042307570576667786,
      "learning_rate": 0.00017159065048946644,
      "loss": 0.3834,
      "step": 226
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.04701109230518341,
      "learning_rate": 0.0001713403695106698,
      "loss": 0.3718,
      "step": 227
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.04007503017783165,
      "learning_rate": 0.00017108917516426704,
      "loss": 0.3785,
      "step": 228
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.04560061916708946,
      "learning_rate": 0.00017083707066628832,
      "loss": 0.3713,
      "step": 229
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.04315731301903725,
      "learning_rate": 0.00017058405924441636,
      "loss": 0.3702,
      "step": 230
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.040260497480630875,
      "learning_rate": 0.0001703301441379453,
      "loss": 0.367,
      "step": 231
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.04882992431521416,
      "learning_rate": 0.000170075328597739,
      "loss": 0.3737,
      "step": 232
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.04410382732748985,
      "learning_rate": 0.0001698196158861896,
      "loss": 0.3625,
      "step": 233
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.04889338091015816,
      "learning_rate": 0.00016956300927717575,
      "loss": 0.3697,
      "step": 234
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.044603537768125534,
      "learning_rate": 0.00016930551205602043,
      "loss": 0.3729,
      "step": 235
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0539550743997097,
      "learning_rate": 0.00016904712751944931,
      "loss": 0.3625,
      "step": 236
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.04753349721431732,
      "learning_rate": 0.00016878785897554818,
      "loss": 0.3662,
      "step": 237
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.04425463080406189,
      "learning_rate": 0.0001685277097437208,
      "loss": 0.3595,
      "step": 238
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.04160892590880394,
      "learning_rate": 0.0001682666831546463,
      "loss": 0.3679,
      "step": 239
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.04600003361701965,
      "learning_rate": 0.0001680047825502366,
      "loss": 0.3702,
      "step": 240
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.03887678310275078,
      "learning_rate": 0.00016774201128359357,
      "loss": 0.3633,
      "step": 241
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0477156862616539,
      "learning_rate": 0.00016747837271896622,
      "loss": 0.3702,
      "step": 242
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.04244072362780571,
      "learning_rate": 0.00016721387023170737,
      "loss": 0.3668,
      "step": 243
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.04049496725201607,
      "learning_rate": 0.0001669485072082308,
      "loss": 0.3785,
      "step": 244
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.04432998597621918,
      "learning_rate": 0.00016668228704596756,
      "loss": 0.3703,
      "step": 245
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.0432085320353508,
      "learning_rate": 0.00016641521315332265,
      "loss": 0.3615,
      "step": 246
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.03820549696683884,
      "learning_rate": 0.00016614728894963135,
      "loss": 0.3483,
      "step": 247
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.04436295107007027,
      "learning_rate": 0.00016587851786511543,
      "loss": 0.3661,
      "step": 248
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.04371733218431473,
      "learning_rate": 0.00016560890334083926,
      "loss": 0.3503,
      "step": 249
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.039205193519592285,
      "learning_rate": 0.00016533844882866568,
      "loss": 0.3482,
      "step": 250
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.04308384284377098,
      "learning_rate": 0.00016506715779121187,
      "loss": 0.373,
      "step": 251
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.040143441408872604,
      "learning_rate": 0.00016479503370180507,
      "loss": 0.3609,
      "step": 252
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.03845199570059776,
      "learning_rate": 0.000164522080044438,
      "loss": 0.3644,
      "step": 253
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.039730221033096313,
      "learning_rate": 0.00016424830031372425,
      "loss": 0.3514,
      "step": 254
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.04021477699279785,
      "learning_rate": 0.00016397369801485366,
      "loss": 0.3566,
      "step": 255
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.03929613530635834,
      "learning_rate": 0.00016369827666354745,
      "loss": 0.3649,
      "step": 256
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.040966227650642395,
      "learning_rate": 0.0001634220397860129,
      "loss": 0.3661,
      "step": 257
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.036787159740924835,
      "learning_rate": 0.0001631449909188987,
      "loss": 0.3572,
      "step": 258
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.039864350110292435,
      "learning_rate": 0.00016286713360924918,
      "loss": 0.3593,
      "step": 259
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.039622630923986435,
      "learning_rate": 0.00016258847141445928,
      "loss": 0.3711,
      "step": 260
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.03840857744216919,
      "learning_rate": 0.00016230900790222878,
      "loss": 0.3537,
      "step": 261
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.03800921142101288,
      "learning_rate": 0.00016202874665051674,
      "loss": 0.3662,
      "step": 262
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.03894530236721039,
      "learning_rate": 0.0001617476912474956,
      "loss": 0.3633,
      "step": 263
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.04486812278628349,
      "learning_rate": 0.00016146584529150526,
      "loss": 0.3594,
      "step": 264
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.0394977331161499,
      "learning_rate": 0.00016118321239100712,
      "loss": 0.3473,
      "step": 265
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.03960977867245674,
      "learning_rate": 0.0001608997961645377,
      "loss": 0.363,
      "step": 266
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.04547852650284767,
      "learning_rate": 0.00016061560024066248,
      "loss": 0.3698,
      "step": 267
    }
  ],
  "logging_steps": 1,
  "max_steps": 888,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 89,
  "total_flos": 5.32595180788777e+18,
  "train_batch_size": 14,
  "trial_name": null,
  "trial_params": null
}