{
  "best_metric": 1.8705838918685913,
  "best_model_checkpoint": "outputs/checkpoint-200",
  "epoch": 0.2983404810740257,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014917024053701287,
      "grad_norm": 2.6047203540802,
      "learning_rate": 4e-05,
      "loss": 1.9885,
      "step": 1
    },
    {
      "epoch": 0.0029834048107402573,
      "grad_norm": 3.559100389480591,
      "learning_rate": 8e-05,
      "loss": 2.01,
      "step": 2
    },
    {
      "epoch": 0.004475107216110386,
      "grad_norm": 2.0908730030059814,
      "learning_rate": 0.00012,
      "loss": 1.9122,
      "step": 3
    },
    {
      "epoch": 0.005966809621480515,
      "grad_norm": 2.6787052154541016,
      "learning_rate": 0.00016,
      "loss": 1.8426,
      "step": 4
    },
    {
      "epoch": 0.007458512026850644,
      "grad_norm": 1.9292813539505005,
      "learning_rate": 0.0002,
      "loss": 1.767,
      "step": 5
    },
    {
      "epoch": 0.008950214432220773,
      "grad_norm": 1.3694391250610352,
      "learning_rate": 0.0001996638655462185,
      "loss": 1.9173,
      "step": 6
    },
    {
      "epoch": 0.0104419168375909,
      "grad_norm": 1.817445993423462,
      "learning_rate": 0.00019932773109243698,
      "loss": 1.8486,
      "step": 7
    },
    {
      "epoch": 0.01193361924296103,
      "grad_norm": 1.4658751487731934,
      "learning_rate": 0.00019899159663865548,
      "loss": 1.9785,
      "step": 8
    },
    {
      "epoch": 0.013425321648331158,
      "grad_norm": 1.6042131185531616,
      "learning_rate": 0.00019865546218487395,
      "loss": 1.9975,
      "step": 9
    },
    {
      "epoch": 0.014917024053701287,
      "grad_norm": 1.5578440427780151,
      "learning_rate": 0.00019831932773109245,
      "loss": 1.8709,
      "step": 10
    },
    {
      "epoch": 0.016408726459071415,
      "grad_norm": 1.6463985443115234,
      "learning_rate": 0.00019798319327731095,
      "loss": 1.838,
      "step": 11
    },
    {
      "epoch": 0.017900428864441546,
      "grad_norm": 1.4298287630081177,
      "learning_rate": 0.00019764705882352942,
      "loss": 1.9203,
      "step": 12
    },
    {
      "epoch": 0.019392131269811673,
      "grad_norm": 1.7401193380355835,
      "learning_rate": 0.00019731092436974792,
      "loss": 1.7784,
      "step": 13
    },
    {
      "epoch": 0.0208838336751818,
      "grad_norm": 2.249098062515259,
      "learning_rate": 0.00019697478991596642,
      "loss": 1.7385,
      "step": 14
    },
    {
      "epoch": 0.02237553608055193,
      "grad_norm": 1.2887922525405884,
      "learning_rate": 0.00019663865546218486,
      "loss": 1.8462,
      "step": 15
    },
    {
      "epoch": 0.02386723848592206,
      "grad_norm": 1.374350905418396,
      "learning_rate": 0.00019630252100840336,
      "loss": 1.8092,
      "step": 16
    },
    {
      "epoch": 0.025358940891292186,
      "grad_norm": 1.2544641494750977,
      "learning_rate": 0.00019596638655462186,
      "loss": 1.8555,
      "step": 17
    },
    {
      "epoch": 0.026850643296662317,
      "grad_norm": 1.4571586847305298,
      "learning_rate": 0.00019563025210084033,
      "loss": 1.8792,
      "step": 18
    },
    {
      "epoch": 0.028342345702032444,
      "grad_norm": 1.2989751100540161,
      "learning_rate": 0.00019529411764705883,
      "loss": 1.9073,
      "step": 19
    },
    {
      "epoch": 0.029834048107402575,
      "grad_norm": 1.1583518981933594,
      "learning_rate": 0.0001949579831932773,
      "loss": 1.9557,
      "step": 20
    },
    {
      "epoch": 0.0313257505127727,
      "grad_norm": 1.2384063005447388,
      "learning_rate": 0.0001946218487394958,
      "loss": 1.8436,
      "step": 21
    },
    {
      "epoch": 0.03281745291814283,
      "grad_norm": 1.4381242990493774,
      "learning_rate": 0.0001942857142857143,
      "loss": 1.7804,
      "step": 22
    },
    {
      "epoch": 0.03430915532351296,
      "grad_norm": 1.160043716430664,
      "learning_rate": 0.00019394957983193278,
      "loss": 1.8407,
      "step": 23
    },
    {
      "epoch": 0.03580085772888309,
      "grad_norm": 1.4776676893234253,
      "learning_rate": 0.00019361344537815127,
      "loss": 1.9378,
      "step": 24
    },
    {
      "epoch": 0.037292560134253215,
      "grad_norm": 1.365653157234192,
      "learning_rate": 0.00019327731092436975,
      "loss": 1.789,
      "step": 25
    },
    {
      "epoch": 0.037292560134253215,
      "eval_loss": 1.8776626586914062,
      "eval_runtime": 12.8602,
      "eval_samples_per_second": 4.977,
      "eval_steps_per_second": 2.488,
      "step": 25
    },
    {
      "epoch": 0.038784262539623346,
      "grad_norm": 1.3155896663665771,
      "learning_rate": 0.00019294117647058825,
      "loss": 1.8049,
      "step": 26
    },
    {
      "epoch": 0.04027596494499348,
      "grad_norm": 1.5831129550933838,
      "learning_rate": 0.00019260504201680674,
      "loss": 1.8892,
      "step": 27
    },
    {
      "epoch": 0.0417676673503636,
      "grad_norm": 1.278041958808899,
      "learning_rate": 0.00019226890756302522,
      "loss": 1.8892,
      "step": 28
    },
    {
      "epoch": 0.04325936975573373,
      "grad_norm": 1.1963578462600708,
      "learning_rate": 0.00019193277310924372,
      "loss": 1.8318,
      "step": 29
    },
    {
      "epoch": 0.04475107216110386,
      "grad_norm": 0.9278161525726318,
      "learning_rate": 0.00019159663865546221,
      "loss": 1.9127,
      "step": 30
    },
    {
      "epoch": 0.046242774566473986,
      "grad_norm": 1.434067964553833,
      "learning_rate": 0.0001912605042016807,
      "loss": 1.8937,
      "step": 31
    },
    {
      "epoch": 0.04773447697184412,
      "grad_norm": 1.3193391561508179,
      "learning_rate": 0.00019092436974789919,
      "loss": 1.7366,
      "step": 32
    },
    {
      "epoch": 0.04922617937721425,
      "grad_norm": 1.2383922338485718,
      "learning_rate": 0.00019058823529411766,
      "loss": 1.8462,
      "step": 33
    },
    {
      "epoch": 0.05071788178258437,
      "grad_norm": 1.178370714187622,
      "learning_rate": 0.00019025210084033613,
      "loss": 1.887,
      "step": 34
    },
    {
      "epoch": 0.0522095841879545,
      "grad_norm": 1.534515142440796,
      "learning_rate": 0.00018991596638655463,
      "loss": 1.7176,
      "step": 35
    },
    {
      "epoch": 0.05370128659332463,
      "grad_norm": 1.201993703842163,
      "learning_rate": 0.0001895798319327731,
      "loss": 1.8099,
      "step": 36
    },
    {
      "epoch": 0.05519298899869476,
      "grad_norm": 1.2329827547073364,
      "learning_rate": 0.0001892436974789916,
      "loss": 1.8096,
      "step": 37
    },
    {
      "epoch": 0.05668469140406489,
      "grad_norm": 1.255269169807434,
      "learning_rate": 0.0001889075630252101,
      "loss": 1.821,
      "step": 38
    },
    {
      "epoch": 0.05817639380943502,
      "grad_norm": 1.233344554901123,
      "learning_rate": 0.00018857142857142857,
      "loss": 1.7468,
      "step": 39
    },
    {
      "epoch": 0.05966809621480515,
      "grad_norm": 1.4332133531570435,
      "learning_rate": 0.00018823529411764707,
      "loss": 1.7706,
      "step": 40
    },
    {
      "epoch": 0.061159798620175274,
      "grad_norm": 1.202459454536438,
      "learning_rate": 0.00018789915966386554,
      "loss": 1.8073,
      "step": 41
    },
    {
      "epoch": 0.0626515010255454,
      "grad_norm": 2.1169466972351074,
      "learning_rate": 0.00018756302521008404,
      "loss": 1.8198,
      "step": 42
    },
    {
      "epoch": 0.06414320343091554,
      "grad_norm": 1.4463489055633545,
      "learning_rate": 0.00018722689075630254,
      "loss": 1.9105,
      "step": 43
    },
    {
      "epoch": 0.06563490583628566,
      "grad_norm": 1.0720268487930298,
      "learning_rate": 0.000186890756302521,
      "loss": 1.7282,
      "step": 44
    },
    {
      "epoch": 0.06712660824165578,
      "grad_norm": 1.3291202783584595,
      "learning_rate": 0.0001865546218487395,
      "loss": 1.8572,
      "step": 45
    },
    {
      "epoch": 0.06861831064702592,
      "grad_norm": 1.4792389869689941,
      "learning_rate": 0.000186218487394958,
      "loss": 1.8633,
      "step": 46
    },
    {
      "epoch": 0.07011001305239604,
      "grad_norm": 1.1921184062957764,
      "learning_rate": 0.00018588235294117648,
      "loss": 1.8363,
      "step": 47
    },
    {
      "epoch": 0.07160171545776618,
      "grad_norm": 1.0988856554031372,
      "learning_rate": 0.00018554621848739498,
      "loss": 1.9583,
      "step": 48
    },
    {
      "epoch": 0.0730934178631363,
      "grad_norm": 1.3254163265228271,
      "learning_rate": 0.00018521008403361345,
      "loss": 1.902,
      "step": 49
    },
    {
      "epoch": 0.07458512026850643,
      "grad_norm": 1.0671206712722778,
      "learning_rate": 0.00018487394957983195,
      "loss": 1.8353,
      "step": 50
    },
    {
      "epoch": 0.07458512026850643,
      "eval_loss": 1.8837151527404785,
      "eval_runtime": 9.6048,
      "eval_samples_per_second": 6.663,
      "eval_steps_per_second": 3.332,
      "step": 50
    },
    {
      "epoch": 0.07607682267387657,
      "grad_norm": 1.2634291648864746,
      "learning_rate": 0.00018453781512605045,
      "loss": 1.7784,
      "step": 51
    },
    {
      "epoch": 0.07756852507924669,
      "grad_norm": 1.1648616790771484,
      "learning_rate": 0.0001842016806722689,
      "loss": 1.6194,
      "step": 52
    },
    {
      "epoch": 0.07906022748461682,
      "grad_norm": 1.2529449462890625,
      "learning_rate": 0.0001838655462184874,
      "loss": 1.8644,
      "step": 53
    },
    {
      "epoch": 0.08055192988998695,
      "grad_norm": 1.230100393295288,
      "learning_rate": 0.0001835294117647059,
      "loss": 1.8477,
      "step": 54
    },
    {
      "epoch": 0.08204363229535708,
      "grad_norm": 1.111884593963623,
      "learning_rate": 0.00018319327731092437,
      "loss": 1.8443,
      "step": 55
    },
    {
      "epoch": 0.0835353347007272,
      "grad_norm": 1.145302176475525,
      "learning_rate": 0.00018285714285714286,
      "loss": 1.9136,
      "step": 56
    },
    {
      "epoch": 0.08502703710609734,
      "grad_norm": 1.1713634729385376,
      "learning_rate": 0.00018252100840336134,
      "loss": 1.8071,
      "step": 57
    },
    {
      "epoch": 0.08651873951146746,
      "grad_norm": 0.9681565761566162,
      "learning_rate": 0.00018218487394957984,
      "loss": 1.9432,
      "step": 58
    },
    {
      "epoch": 0.08801044191683759,
      "grad_norm": 1.2015904188156128,
      "learning_rate": 0.00018184873949579833,
      "loss": 1.774,
      "step": 59
    },
    {
      "epoch": 0.08950214432220772,
      "grad_norm": 1.0416995286941528,
      "learning_rate": 0.0001815126050420168,
      "loss": 1.8479,
      "step": 60
    },
    {
      "epoch": 0.09099384672757785,
      "grad_norm": 1.1236249208450317,
      "learning_rate": 0.0001811764705882353,
      "loss": 1.8281,
      "step": 61
    },
    {
      "epoch": 0.09248554913294797,
      "grad_norm": 1.6734750270843506,
      "learning_rate": 0.0001808403361344538,
      "loss": 1.7245,
      "step": 62
    },
    {
      "epoch": 0.09397725153831811,
      "grad_norm": 1.5988835096359253,
      "learning_rate": 0.00018050420168067228,
      "loss": 1.7511,
      "step": 63
    },
    {
      "epoch": 0.09546895394368823,
      "grad_norm": 1.3248356580734253,
      "learning_rate": 0.00018016806722689078,
      "loss": 1.8517,
      "step": 64
    },
    {
      "epoch": 0.09696065634905836,
      "grad_norm": 1.272733211517334,
      "learning_rate": 0.00017983193277310925,
      "loss": 1.8331,
      "step": 65
    },
    {
      "epoch": 0.0984523587544285,
      "grad_norm": 1.074728012084961,
      "learning_rate": 0.00017949579831932775,
      "loss": 1.903,
      "step": 66
    },
    {
      "epoch": 0.09994406115979862,
      "grad_norm": 0.9002382755279541,
      "learning_rate": 0.00017915966386554625,
      "loss": 1.6597,
      "step": 67
    },
    {
      "epoch": 0.10143576356516874,
      "grad_norm": 1.0076817274093628,
      "learning_rate": 0.00017882352941176472,
      "loss": 1.8571,
      "step": 68
    },
    {
      "epoch": 0.10292746597053888,
      "grad_norm": 1.0490552186965942,
      "learning_rate": 0.00017848739495798322,
      "loss": 1.9166,
      "step": 69
    },
    {
      "epoch": 0.104419168375909,
      "grad_norm": 1.1788151264190674,
      "learning_rate": 0.0001781512605042017,
      "loss": 1.8758,
      "step": 70
    },
    {
      "epoch": 0.10591087078127913,
      "grad_norm": 1.0090404748916626,
      "learning_rate": 0.00017781512605042016,
      "loss": 1.7205,
      "step": 71
    },
    {
      "epoch": 0.10740257318664927,
      "grad_norm": 1.176716685295105,
      "learning_rate": 0.00017747899159663866,
      "loss": 1.8767,
      "step": 72
    },
    {
      "epoch": 0.10889427559201939,
      "grad_norm": 1.2236241102218628,
      "learning_rate": 0.00017714285714285713,
      "loss": 1.8276,
      "step": 73
    },
    {
      "epoch": 0.11038597799738951,
      "grad_norm": 1.1437926292419434,
      "learning_rate": 0.00017680672268907563,
      "loss": 1.9052,
      "step": 74
    },
    {
      "epoch": 0.11187768040275965,
      "grad_norm": 1.3193964958190918,
      "learning_rate": 0.00017647058823529413,
      "loss": 1.8221,
      "step": 75
    },
    {
      "epoch": 0.11187768040275965,
      "eval_loss": 1.877716064453125,
      "eval_runtime": 9.6046,
      "eval_samples_per_second": 6.663,
      "eval_steps_per_second": 3.332,
      "step": 75
    },
    {
      "epoch": 0.11336938280812978,
      "grad_norm": 1.1918264627456665,
      "learning_rate": 0.0001761344537815126,
      "loss": 1.8814,
      "step": 76
    },
    {
      "epoch": 0.1148610852134999,
      "grad_norm": 1.232614517211914,
      "learning_rate": 0.0001757983193277311,
      "loss": 1.739,
      "step": 77
    },
    {
      "epoch": 0.11635278761887004,
      "grad_norm": 1.6352307796478271,
      "learning_rate": 0.0001754621848739496,
      "loss": 1.8363,
      "step": 78
    },
    {
      "epoch": 0.11784449002424016,
      "grad_norm": 1.2389256954193115,
      "learning_rate": 0.00017512605042016807,
      "loss": 1.8105,
      "step": 79
    },
    {
      "epoch": 0.1193361924296103,
      "grad_norm": 1.085701584815979,
      "learning_rate": 0.00017478991596638657,
      "loss": 1.8751,
      "step": 80
    },
    {
      "epoch": 0.12082789483498042,
      "grad_norm": 1.5276975631713867,
      "learning_rate": 0.00017445378151260504,
      "loss": 1.8892,
      "step": 81
    },
    {
      "epoch": 0.12231959724035055,
      "grad_norm": 1.2220733165740967,
      "learning_rate": 0.00017411764705882354,
      "loss": 1.7284,
      "step": 82
    },
    {
      "epoch": 0.12381129964572068,
      "grad_norm": 1.1983511447906494,
      "learning_rate": 0.00017378151260504204,
      "loss": 1.9117,
      "step": 83
    },
    {
      "epoch": 0.1253030020510908,
      "grad_norm": 1.185375690460205,
      "learning_rate": 0.0001734453781512605,
      "loss": 1.7894,
      "step": 84
    },
    {
      "epoch": 0.12679470445646093,
      "grad_norm": 1.1006300449371338,
      "learning_rate": 0.000173109243697479,
      "loss": 1.8714,
      "step": 85
    },
    {
      "epoch": 0.12828640686183107,
      "grad_norm": 1.0701563358306885,
      "learning_rate": 0.00017277310924369748,
      "loss": 1.9681,
      "step": 86
    },
    {
      "epoch": 0.12977810926720118,
      "grad_norm": 1.10486900806427,
      "learning_rate": 0.00017243697478991598,
      "loss": 1.8594,
      "step": 87
    },
    {
      "epoch": 0.13126981167257132,
      "grad_norm": 1.2423001527786255,
      "learning_rate": 0.00017210084033613448,
      "loss": 1.7603,
      "step": 88
    },
    {
      "epoch": 0.13276151407794146,
      "grad_norm": 1.2650513648986816,
      "learning_rate": 0.00017176470588235293,
      "loss": 1.8477,
      "step": 89
    },
    {
      "epoch": 0.13425321648331157,
      "grad_norm": 1.0919733047485352,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.9019,
      "step": 90
    },
    {
      "epoch": 0.1357449188886817,
      "grad_norm": 1.1384038925170898,
      "learning_rate": 0.00017109243697478992,
      "loss": 1.7632,
      "step": 91
    },
    {
      "epoch": 0.13723662129405184,
      "grad_norm": 1.2927051782608032,
      "learning_rate": 0.0001707563025210084,
      "loss": 1.8592,
      "step": 92
    },
    {
      "epoch": 0.13872832369942195,
      "grad_norm": 1.2602596282958984,
      "learning_rate": 0.0001704201680672269,
      "loss": 1.746,
      "step": 93
    },
    {
      "epoch": 0.1402200261047921,
      "grad_norm": 1.2915674448013306,
      "learning_rate": 0.0001700840336134454,
      "loss": 1.8301,
      "step": 94
    },
    {
      "epoch": 0.14171172851016223,
      "grad_norm": 1.1027021408081055,
      "learning_rate": 0.00016974789915966387,
      "loss": 1.8711,
      "step": 95
    },
    {
      "epoch": 0.14320343091553236,
      "grad_norm": 1.2534444332122803,
      "learning_rate": 0.00016941176470588237,
      "loss": 1.8429,
      "step": 96
    },
    {
      "epoch": 0.14469513332090247,
      "grad_norm": 1.1659573316574097,
      "learning_rate": 0.00016907563025210084,
      "loss": 1.9125,
      "step": 97
    },
    {
      "epoch": 0.1461868357262726,
      "grad_norm": 0.9224597215652466,
      "learning_rate": 0.00016873949579831934,
      "loss": 1.7884,
      "step": 98
    },
    {
      "epoch": 0.14767853813164275,
      "grad_norm": 1.5108716487884521,
      "learning_rate": 0.00016840336134453784,
      "loss": 1.756,
      "step": 99
    },
    {
      "epoch": 0.14917024053701286,
      "grad_norm": 1.0304495096206665,
      "learning_rate": 0.0001680672268907563,
      "loss": 1.8496,
      "step": 100
    },
    {
      "epoch": 0.14917024053701286,
      "eval_loss": 1.8782081604003906,
      "eval_runtime": 9.6109,
      "eval_samples_per_second": 6.659,
      "eval_steps_per_second": 3.33,
      "step": 100
    },
    {
      "epoch": 0.150661942942383,
      "grad_norm": 1.3242460489273071,
      "learning_rate": 0.0001677310924369748,
      "loss": 1.829,
      "step": 101
    },
    {
      "epoch": 0.15215364534775314,
      "grad_norm": 1.3235081434249878,
      "learning_rate": 0.00016739495798319328,
      "loss": 1.8422,
      "step": 102
    },
    {
      "epoch": 0.15364534775312325,
      "grad_norm": 1.1545659303665161,
      "learning_rate": 0.00016705882352941178,
      "loss": 1.8066,
      "step": 103
    },
    {
      "epoch": 0.15513705015849338,
      "grad_norm": 1.0676213502883911,
      "learning_rate": 0.00016672268907563028,
      "loss": 1.8795,
      "step": 104
    },
    {
      "epoch": 0.15662875256386352,
      "grad_norm": 1.1830964088439941,
      "learning_rate": 0.00016638655462184875,
      "loss": 1.7718,
      "step": 105
    },
    {
      "epoch": 0.15812045496923363,
      "grad_norm": 0.8926868438720703,
      "learning_rate": 0.00016605042016806725,
      "loss": 2.0281,
      "step": 106
    },
    {
      "epoch": 0.15961215737460377,
      "grad_norm": 1.5321383476257324,
      "learning_rate": 0.00016571428571428575,
      "loss": 1.7645,
      "step": 107
    },
    {
      "epoch": 0.1611038597799739,
      "grad_norm": 1.2218270301818848,
      "learning_rate": 0.0001653781512605042,
      "loss": 1.8298,
      "step": 108
    },
    {
      "epoch": 0.16259556218534402,
      "grad_norm": 1.793670415878296,
      "learning_rate": 0.0001650420168067227,
      "loss": 1.9826,
      "step": 109
    },
    {
      "epoch": 0.16408726459071415,
      "grad_norm": 1.9927605390548706,
      "learning_rate": 0.0001647058823529412,
      "loss": 1.7738,
      "step": 110
    },
    {
      "epoch": 0.1655789669960843,
      "grad_norm": 1.101162075996399,
      "learning_rate": 0.00016436974789915966,
      "loss": 1.9763,
      "step": 111
    },
    {
      "epoch": 0.1670706694014544,
      "grad_norm": 1.1939274072647095,
      "learning_rate": 0.00016403361344537816,
      "loss": 1.8981,
      "step": 112
    },
    {
      "epoch": 0.16856237180682454,
      "grad_norm": 0.9935958981513977,
      "learning_rate": 0.00016369747899159663,
      "loss": 1.7811,
      "step": 113
    },
    {
      "epoch": 0.17005407421219468,
      "grad_norm": 1.1262861490249634,
      "learning_rate": 0.00016336134453781513,
      "loss": 1.7147,
      "step": 114
    },
    {
      "epoch": 0.1715457766175648,
      "grad_norm": 1.302400827407837,
      "learning_rate": 0.00016302521008403363,
      "loss": 1.7799,
      "step": 115
    },
    {
      "epoch": 0.17303747902293493,
      "grad_norm": 1.387164831161499,
      "learning_rate": 0.0001626890756302521,
      "loss": 1.7975,
      "step": 116
    },
    {
      "epoch": 0.17452918142830506,
      "grad_norm": 1.1098518371582031,
      "learning_rate": 0.0001623529411764706,
      "loss": 1.8904,
      "step": 117
    },
    {
      "epoch": 0.17602088383367517,
      "grad_norm": 1.1995928287506104,
      "learning_rate": 0.00016201680672268907,
      "loss": 1.9544,
      "step": 118
    },
    {
      "epoch": 0.1775125862390453,
      "grad_norm": 1.1032203435897827,
      "learning_rate": 0.00016168067226890757,
      "loss": 1.8541,
      "step": 119
    },
    {
      "epoch": 0.17900428864441545,
      "grad_norm": 1.1663708686828613,
      "learning_rate": 0.00016134453781512607,
      "loss": 1.8456,
      "step": 120
    },
    {
      "epoch": 0.18049599104978556,
      "grad_norm": 1.1270015239715576,
      "learning_rate": 0.00016100840336134454,
      "loss": 1.8631,
      "step": 121
    },
    {
      "epoch": 0.1819876934551557,
      "grad_norm": 1.103669285774231,
      "learning_rate": 0.00016067226890756304,
      "loss": 1.8903,
      "step": 122
    },
    {
      "epoch": 0.18347939586052583,
      "grad_norm": 1.108260154724121,
      "learning_rate": 0.00016033613445378154,
      "loss": 1.9331,
      "step": 123
    },
    {
      "epoch": 0.18497109826589594,
      "grad_norm": 1.1545782089233398,
      "learning_rate": 0.00016,
      "loss": 1.777,
      "step": 124
    },
    {
      "epoch": 0.18646280067126608,
      "grad_norm": 1.2768380641937256,
      "learning_rate": 0.0001596638655462185,
      "loss": 1.6511,
      "step": 125
    },
    {
      "epoch": 0.18646280067126608,
      "eval_loss": 1.874816656112671,
      "eval_runtime": 9.6122,
      "eval_samples_per_second": 6.658,
      "eval_steps_per_second": 3.329,
      "step": 125
    },
    {
      "epoch": 0.18795450307663622,
      "grad_norm": 1.2768590450286865,
      "learning_rate": 0.00015932773109243698,
      "loss": 1.8337,
      "step": 126
    },
    {
      "epoch": 0.18944620548200633,
      "grad_norm": 1.323432445526123,
      "learning_rate": 0.00015899159663865546,
      "loss": 1.747,
      "step": 127
    },
    {
      "epoch": 0.19093790788737647,
      "grad_norm": 1.2613009214401245,
      "learning_rate": 0.00015865546218487396,
      "loss": 1.9522,
      "step": 128
    },
    {
      "epoch": 0.1924296102927466,
      "grad_norm": 1.0958023071289062,
      "learning_rate": 0.00015831932773109243,
      "loss": 1.8094,
      "step": 129
    },
    {
      "epoch": 0.19392131269811672,
      "grad_norm": 1.1639002561569214,
      "learning_rate": 0.00015798319327731093,
      "loss": 1.812,
      "step": 130
    },
    {
      "epoch": 0.19541301510348685,
      "grad_norm": 1.2229630947113037,
      "learning_rate": 0.00015764705882352943,
      "loss": 1.8596,
      "step": 131
    },
    {
      "epoch": 0.196904717508857,
      "grad_norm": 1.122227430343628,
      "learning_rate": 0.0001573109243697479,
      "loss": 1.8077,
      "step": 132
    },
    {
      "epoch": 0.1983964199142271,
      "grad_norm": 1.3863284587860107,
      "learning_rate": 0.0001569747899159664,
      "loss": 1.8443,
      "step": 133
    },
    {
      "epoch": 0.19988812231959724,
      "grad_norm": 1.2235605716705322,
      "learning_rate": 0.00015663865546218487,
      "loss": 1.8502,
      "step": 134
    },
    {
      "epoch": 0.20137982472496738,
      "grad_norm": 1.147643804550171,
      "learning_rate": 0.00015630252100840337,
      "loss": 1.8126,
      "step": 135
    },
    {
      "epoch": 0.2028715271303375,
      "grad_norm": 1.0508145093917847,
      "learning_rate": 0.00015596638655462187,
      "loss": 1.7963,
      "step": 136
    },
    {
      "epoch": 0.20436322953570762,
      "grad_norm": 1.2935668230056763,
      "learning_rate": 0.00015563025210084034,
      "loss": 1.8309,
      "step": 137
    },
    {
      "epoch": 0.20585493194107776,
      "grad_norm": 1.3547037839889526,
      "learning_rate": 0.00015529411764705884,
      "loss": 1.9209,
      "step": 138
    },
    {
      "epoch": 0.20734663434644787,
      "grad_norm": 1.1742887496948242,
      "learning_rate": 0.00015495798319327734,
      "loss": 1.6319,
      "step": 139
    },
    {
      "epoch": 0.208838336751818,
      "grad_norm": 1.072054386138916,
      "learning_rate": 0.0001546218487394958,
      "loss": 1.9222,
      "step": 140
    },
    {
      "epoch": 0.21033003915718815,
      "grad_norm": 1.3844436407089233,
      "learning_rate": 0.0001542857142857143,
      "loss": 1.7804,
      "step": 141
    },
    {
      "epoch": 0.21182174156255826,
      "grad_norm": 1.2061916589736938,
      "learning_rate": 0.00015394957983193278,
      "loss": 1.923,
      "step": 142
    },
    {
      "epoch": 0.2133134439679284,
      "grad_norm": 1.239007592201233,
      "learning_rate": 0.00015361344537815128,
      "loss": 1.8048,
      "step": 143
    },
    {
      "epoch": 0.21480514637329853,
      "grad_norm": 1.2390162944793701,
      "learning_rate": 0.00015327731092436978,
      "loss": 1.8587,
      "step": 144
    },
    {
      "epoch": 0.21629684877866864,
      "grad_norm": 1.2212045192718506,
      "learning_rate": 0.00015294117647058822,
      "loss": 1.7354,
      "step": 145
    },
    {
      "epoch": 0.21778855118403878,
      "grad_norm": 1.0528079271316528,
      "learning_rate": 0.00015260504201680672,
      "loss": 1.7894,
      "step": 146
    },
    {
      "epoch": 0.21928025358940892,
      "grad_norm": 1.0495508909225464,
      "learning_rate": 0.00015226890756302522,
      "loss": 1.903,
      "step": 147
    },
    {
      "epoch": 0.22077195599477903,
      "grad_norm": 0.8550733327865601,
      "learning_rate": 0.0001519327731092437,
      "loss": 1.999,
      "step": 148
    },
    {
      "epoch": 0.22226365840014917,
      "grad_norm": 1.0874502658843994,
      "learning_rate": 0.0001515966386554622,
      "loss": 1.7004,
      "step": 149
    },
    {
      "epoch": 0.2237553608055193,
      "grad_norm": 0.9333251714706421,
      "learning_rate": 0.00015126050420168066,
      "loss": 1.734,
      "step": 150
    },
    {
      "epoch": 0.2237553608055193,
      "eval_loss": 1.8709282875061035,
      "eval_runtime": 9.6018,
      "eval_samples_per_second": 6.665,
      "eval_steps_per_second": 3.333,
      "step": 150
    },
    {
      "epoch": 0.22524706321088941,
      "grad_norm": 1.183721661567688,
      "learning_rate": 0.00015092436974789916,
      "loss": 1.8014,
      "step": 151
    },
    {
      "epoch": 0.22673876561625955,
      "grad_norm": 1.1360634565353394,
      "learning_rate": 0.00015058823529411766,
      "loss": 1.9695,
      "step": 152
    },
    {
      "epoch": 0.2282304680216297,
      "grad_norm": 1.233215093612671,
      "learning_rate": 0.00015025210084033613,
      "loss": 1.7755,
      "step": 153
    },
    {
      "epoch": 0.2297221704269998,
      "grad_norm": 1.2131235599517822,
      "learning_rate": 0.00014991596638655463,
      "loss": 1.8335,
      "step": 154
    },
    {
      "epoch": 0.23121387283236994,
      "grad_norm": 1.1295011043548584,
      "learning_rate": 0.00014957983193277313,
      "loss": 1.9578,
      "step": 155
    },
    {
      "epoch": 0.23270557523774008,
      "grad_norm": 0.9773207306861877,
      "learning_rate": 0.0001492436974789916,
      "loss": 1.787,
      "step": 156
    },
    {
      "epoch": 0.2341972776431102,
      "grad_norm": 1.0354061126708984,
      "learning_rate": 0.0001489075630252101,
      "loss": 1.7698,
      "step": 157
    },
    {
      "epoch": 0.23568898004848032,
      "grad_norm": 1.2250792980194092,
      "learning_rate": 0.00014857142857142857,
      "loss": 1.8126,
      "step": 158
    },
    {
      "epoch": 0.23718068245385046,
      "grad_norm": 1.046985387802124,
      "learning_rate": 0.00014823529411764707,
      "loss": 1.8212,
      "step": 159
    },
    {
      "epoch": 0.2386723848592206,
      "grad_norm": 1.2320305109024048,
      "learning_rate": 0.00014789915966386557,
      "loss": 1.8236,
      "step": 160
    },
    {
      "epoch": 0.2401640872645907,
      "grad_norm": 1.0551854372024536,
      "learning_rate": 0.00014756302521008404,
      "loss": 1.9667,
      "step": 161
    },
    {
      "epoch": 0.24165578966996085,
      "grad_norm": 1.2871147394180298,
      "learning_rate": 0.00014722689075630254,
      "loss": 1.601,
      "step": 162
    },
    {
      "epoch": 0.24314749207533098,
      "grad_norm": 1.041728138923645,
      "learning_rate": 0.00014689075630252101,
      "loss": 1.7647,
      "step": 163
    },
    {
      "epoch": 0.2446391944807011,
      "grad_norm": 1.0194857120513916,
      "learning_rate": 0.0001465546218487395,
      "loss": 1.8846,
      "step": 164
    },
    {
      "epoch": 0.24613089688607123,
      "grad_norm": 1.2751890420913696,
      "learning_rate": 0.00014621848739495799,
      "loss": 1.8289,
      "step": 165
    },
    {
      "epoch": 0.24762259929144137,
      "grad_norm": 1.199288010597229,
      "learning_rate": 0.00014588235294117646,
      "loss": 1.8981,
      "step": 166
    },
    {
      "epoch": 0.24911430169681148,
      "grad_norm": 1.0112318992614746,
      "learning_rate": 0.00014554621848739496,
      "loss": 1.7556,
      "step": 167
    },
    {
      "epoch": 0.2506060041021816,
      "grad_norm": 1.2500594854354858,
      "learning_rate": 0.00014521008403361346,
      "loss": 1.7519,
      "step": 168
    },
    {
      "epoch": 0.25209770650755176,
      "grad_norm": 1.0208771228790283,
      "learning_rate": 0.00014487394957983193,
      "loss": 1.877,
      "step": 169
    },
    {
      "epoch": 0.25358940891292187,
      "grad_norm": 0.9646258354187012,
      "learning_rate": 0.00014453781512605043,
      "loss": 1.7557,
      "step": 170
    },
    {
      "epoch": 0.255081111318292,
      "grad_norm": 1.0481817722320557,
      "learning_rate": 0.00014420168067226893,
      "loss": 1.7891,
      "step": 171
    },
    {
      "epoch": 0.25657281372366214,
      "grad_norm": 1.0916467905044556,
      "learning_rate": 0.0001438655462184874,
      "loss": 1.8675,
      "step": 172
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 1.1353753805160522,
      "learning_rate": 0.0001435294117647059,
      "loss": 1.7778,
      "step": 173
    },
    {
      "epoch": 0.25955621853440236,
      "grad_norm": 1.038346767425537,
      "learning_rate": 0.00014319327731092437,
      "loss": 1.8854,
      "step": 174
    },
    {
      "epoch": 0.2610479209397725,
      "grad_norm": 1.203598976135254,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.7975,
      "step": 175
    },
    {
      "epoch": 0.2610479209397725,
      "eval_loss": 1.86907160282135,
      "eval_runtime": 9.6023,
      "eval_samples_per_second": 6.665,
      "eval_steps_per_second": 3.333,
      "step": 175
    },
    {
      "epoch": 0.26253962334514264,
      "grad_norm": 1.0852186679840088,
      "learning_rate": 0.00014252100840336137,
      "loss": 1.6793,
      "step": 176
    },
    {
      "epoch": 0.26403132575051275,
      "grad_norm": 1.2202097177505493,
      "learning_rate": 0.00014218487394957984,
      "loss": 1.8407,
      "step": 177
    },
    {
      "epoch": 0.2655230281558829,
      "grad_norm": 1.1267554759979248,
      "learning_rate": 0.00014184873949579834,
      "loss": 1.9081,
      "step": 178
    },
    {
      "epoch": 0.267014730561253,
      "grad_norm": 1.2180603742599487,
      "learning_rate": 0.0001415126050420168,
      "loss": 1.7984,
      "step": 179
    },
    {
      "epoch": 0.26850643296662313,
      "grad_norm": 1.2492526769638062,
      "learning_rate": 0.0001411764705882353,
      "loss": 1.7882,
      "step": 180
    },
    {
      "epoch": 0.2699981353719933,
      "grad_norm": 1.2571358680725098,
      "learning_rate": 0.0001408403361344538,
      "loss": 1.8152,
      "step": 181
    },
    {
      "epoch": 0.2714898377773634,
      "grad_norm": 0.8651157021522522,
      "learning_rate": 0.00014050420168067225,
      "loss": 1.7297,
      "step": 182
    },
    {
      "epoch": 0.2729815401827335,
      "grad_norm": 1.1827569007873535,
      "learning_rate": 0.00014016806722689075,
      "loss": 1.7823,
      "step": 183
    },
    {
      "epoch": 0.2744732425881037,
      "grad_norm": 1.353014588356018,
      "learning_rate": 0.00013983193277310925,
      "loss": 1.8372,
      "step": 184
    },
    {
      "epoch": 0.2759649449934738,
      "grad_norm": 1.1514286994934082,
      "learning_rate": 0.00013949579831932772,
      "loss": 1.8761,
      "step": 185
    },
    {
      "epoch": 0.2774566473988439,
      "grad_norm": 1.187524437904358,
      "learning_rate": 0.00013915966386554622,
      "loss": 1.8541,
      "step": 186
    },
    {
      "epoch": 0.27894834980421407,
      "grad_norm": 1.2467368841171265,
      "learning_rate": 0.00013882352941176472,
      "loss": 1.7568,
      "step": 187
    },
    {
      "epoch": 0.2804400522095842,
      "grad_norm": 1.346911907196045,
      "learning_rate": 0.0001384873949579832,
      "loss": 1.8323,
      "step": 188
    },
    {
      "epoch": 0.28193175461495434,
      "grad_norm": 1.1479412317276,
      "learning_rate": 0.0001381512605042017,
      "loss": 1.807,
      "step": 189
    },
    {
      "epoch": 0.28342345702032445,
      "grad_norm": 1.1322258710861206,
      "learning_rate": 0.00013781512605042016,
      "loss": 1.8255,
      "step": 190
    },
    {
      "epoch": 0.28491515942569456,
      "grad_norm": 1.8296042680740356,
      "learning_rate": 0.00013747899159663866,
      "loss": 1.8455,
      "step": 191
    },
    {
      "epoch": 0.28640686183106473,
      "grad_norm": 0.9627158641815186,
      "learning_rate": 0.00013714285714285716,
      "loss": 1.9299,
      "step": 192
    },
    {
      "epoch": 0.28789856423643484,
      "grad_norm": 1.115510106086731,
      "learning_rate": 0.00013680672268907563,
      "loss": 1.9374,
      "step": 193
    },
    {
      "epoch": 0.28939026664180495,
      "grad_norm": 1.0655395984649658,
      "learning_rate": 0.00013647058823529413,
      "loss": 1.8119,
      "step": 194
    },
    {
      "epoch": 0.2908819690471751,
      "grad_norm": 1.1582270860671997,
      "learning_rate": 0.0001361344537815126,
      "loss": 1.6841,
      "step": 195
    },
    {
      "epoch": 0.2923736714525452,
      "grad_norm": 1.132757544517517,
      "learning_rate": 0.0001357983193277311,
      "loss": 1.7578,
      "step": 196
    },
    {
      "epoch": 0.29386537385791534,
      "grad_norm": 1.1855252981185913,
      "learning_rate": 0.0001354621848739496,
      "loss": 1.8448,
      "step": 197
    },
    {
      "epoch": 0.2953570762632855,
      "grad_norm": 1.0681709051132202,
      "learning_rate": 0.00013512605042016807,
      "loss": 1.9413,
      "step": 198
    },
    {
      "epoch": 0.2968487786686556,
      "grad_norm": 1.1889592409133911,
      "learning_rate": 0.00013478991596638657,
      "loss": 1.7304,
      "step": 199
    },
    {
      "epoch": 0.2983404810740257,
      "grad_norm": 0.9375355243682861,
      "learning_rate": 0.00013445378151260507,
      "loss": 1.8668,
      "step": 200
    },
    {
      "epoch": 0.2983404810740257,
      "eval_loss": 1.8705838918685913,
      "eval_runtime": 9.6071,
      "eval_samples_per_second": 6.662,
      "eval_steps_per_second": 3.331,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2708395899230618e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}