{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.968,
  "eval_steps": 500,
  "global_step": 123,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024,
      "grad_norm": 0.13470892473582247,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.9002,
      "step": 1
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.12684151805493843,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.8697,
      "step": 2
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.13524138740416147,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.8839,
      "step": 3
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.12441922660662,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.8799,
      "step": 4
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.116855421032801,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.8607,
      "step": 5
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.1081278232525602,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.8649,
      "step": 6
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.09391740911956674,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.85,
      "step": 7
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.093768679228211,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.8373,
      "step": 8
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.11850273448846249,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.8126,
      "step": 9
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.12308088090050255,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.803,
      "step": 10
    },
    {
      "epoch": 0.264,
      "grad_norm": 0.1012384950170664,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.7831,
      "step": 11
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.08935456718448598,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.7575,
      "step": 12
    },
    {
      "epoch": 0.312,
      "grad_norm": 0.08348093118245446,
      "learning_rate": 0.0001,
      "loss": 0.7635,
      "step": 13
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.10237088717244265,
      "learning_rate": 9.997960964140947e-05,
      "loss": 0.7505,
      "step": 14
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.09971346745654726,
      "learning_rate": 9.991845519630678e-05,
      "loss": 0.7268,
      "step": 15
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.0956041349604367,
      "learning_rate": 9.981658654313457e-05,
      "loss": 0.7075,
      "step": 16
    },
    {
      "epoch": 0.408,
      "grad_norm": 0.08930264667905229,
      "learning_rate": 9.967408676742751e-05,
      "loss": 0.7075,
      "step": 17
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.0805715992727793,
      "learning_rate": 9.949107209404665e-05,
      "loss": 0.7005,
      "step": 18
    },
    {
      "epoch": 0.456,
      "grad_norm": 0.0791880846722688,
      "learning_rate": 9.926769179238466e-05,
      "loss": 0.6842,
      "step": 19
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.08089271988918346,
      "learning_rate": 9.900412805461967e-05,
      "loss": 0.6791,
      "step": 20
    },
    {
      "epoch": 0.504,
      "grad_norm": 0.07928793051029351,
      "learning_rate": 9.870059584711668e-05,
      "loss": 0.6839,
      "step": 21
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.06499639850161912,
      "learning_rate": 9.835734273509786e-05,
      "loss": 0.6636,
      "step": 22
    },
    {
      "epoch": 0.552,
      "grad_norm": 0.05954930255476567,
      "learning_rate": 9.797464868072488e-05,
      "loss": 0.666,
      "step": 23
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.06162765168782512,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6578,
      "step": 24
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.06248610871137899,
      "learning_rate": 9.709221818197624e-05,
      "loss": 0.6549,
      "step": 25
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.0506950458274749,
      "learning_rate": 9.659320146057262e-05,
      "loss": 0.6304,
      "step": 26
    },
    {
      "epoch": 0.648,
      "grad_norm": 0.05374640897395996,
      "learning_rate": 9.60561826557425e-05,
      "loss": 0.6416,
      "step": 27
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.05706061454780688,
      "learning_rate": 9.548159976772592e-05,
      "loss": 0.6439,
      "step": 28
    },
    {
      "epoch": 0.696,
      "grad_norm": 0.0557974734976607,
      "learning_rate": 9.486992143456792e-05,
      "loss": 0.6339,
      "step": 29
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.049431517782371044,
      "learning_rate": 9.422164654989072e-05,
      "loss": 0.636,
      "step": 30
    },
    {
      "epoch": 0.744,
      "grad_norm": 0.04943967511643338,
      "learning_rate": 9.353730385598887e-05,
      "loss": 0.623,
      "step": 31
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.057481818878385216,
      "learning_rate": 9.281745151257946e-05,
      "loss": 0.6239,
      "step": 32
    },
    {
      "epoch": 0.792,
      "grad_norm": 0.04396292148227855,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.6148,
      "step": 33
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.050000504681156153,
      "learning_rate": 9.12735948481387e-05,
      "loss": 0.6222,
      "step": 34
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.04978849344079479,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6089,
      "step": 35
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.04110105308892455,
      "learning_rate": 8.959511229611376e-05,
      "loss": 0.6135,
      "step": 36
    },
    {
      "epoch": 0.888,
      "grad_norm": 0.04231119961691381,
      "learning_rate": 8.870708053195413e-05,
      "loss": 0.6062,
      "step": 37
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.04161289294733194,
      "learning_rate": 8.778747871771292e-05,
      "loss": 0.595,
      "step": 38
    },
    {
      "epoch": 0.936,
      "grad_norm": 0.040394425736741305,
      "learning_rate": 8.683705689382024e-05,
      "loss": 0.6189,
      "step": 39
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.039625585716789334,
      "learning_rate": 8.585659023794818e-05,
      "loss": 0.6125,
      "step": 40
    },
    {
      "epoch": 0.984,
      "grad_norm": 0.03942971331618393,
      "learning_rate": 8.484687843276469e-05,
      "loss": 0.5902,
      "step": 41
    },
    {
      "epoch": 1.016,
      "grad_norm": 0.06854283714031789,
      "learning_rate": 8.380874501370097e-05,
      "loss": 0.9837,
      "step": 42
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.044244844800252224,
      "learning_rate": 8.274303669726426e-05,
      "loss": 0.5954,
      "step": 43
    },
    {
      "epoch": 1.064,
      "grad_norm": 0.04315909037714035,
      "learning_rate": 8.165062269044353e-05,
      "loss": 0.5572,
      "step": 44
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.042343597409635,
      "learning_rate": 8.053239398177191e-05,
      "loss": 0.5947,
      "step": 45
    },
    {
      "epoch": 1.112,
      "grad_norm": 0.042609334474767446,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.598,
      "step": 46
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.042855620470266094,
      "learning_rate": 7.822216094333847e-05,
      "loss": 0.5948,
      "step": 47
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.038865911999576994,
      "learning_rate": 7.703204087277988e-05,
      "loss": 0.538,
      "step": 48
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.04351888230509946,
      "learning_rate": 7.58198730819481e-05,
      "loss": 0.6413,
      "step": 49
    },
    {
      "epoch": 1.208,
      "grad_norm": 0.038833703601196076,
      "learning_rate": 7.45866462322802e-05,
      "loss": 0.5664,
      "step": 50
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.042691953985913605,
      "learning_rate": 7.333336616128369e-05,
      "loss": 0.6138,
      "step": 51
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.03786316545193847,
      "learning_rate": 7.206105506216106e-05,
      "loss": 0.5708,
      "step": 52
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.03779522737510971,
      "learning_rate": 7.077075065009433e-05,
      "loss": 0.548,
      "step": 53
    },
    {
      "epoch": 1.304,
      "grad_norm": 0.03864001143875006,
      "learning_rate": 6.946350531586959e-05,
      "loss": 0.5777,
      "step": 54
    },
    {
      "epoch": 1.328,
      "grad_norm": 0.040817473223837275,
      "learning_rate": 6.814038526753205e-05,
      "loss": 0.6152,
      "step": 55
    },
    {
      "epoch": 1.3519999999999999,
      "grad_norm": 0.036713626306258296,
      "learning_rate": 6.680246966077151e-05,
      "loss": 0.5425,
      "step": 56
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.039957743150673776,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5807,
      "step": 57
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.03763361703526649,
      "learning_rate": 6.408662784207149e-05,
      "loss": 0.5524,
      "step": 58
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.03892474621010607,
      "learning_rate": 6.271091670967436e-05,
      "loss": 0.5842,
      "step": 59
    },
    {
      "epoch": 1.448,
      "grad_norm": 0.04548062476292172,
      "learning_rate": 6.132483837128823e-05,
      "loss": 0.5996,
      "step": 60
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.0384979096849966,
      "learning_rate": 5.992952333228728e-05,
      "loss": 0.5779,
      "step": 61
    },
    {
      "epoch": 1.496,
      "grad_norm": 0.04251581398744228,
      "learning_rate": 5.85261096316312e-05,
      "loss": 0.5614,
      "step": 62
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.041653573628985384,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 0.5793,
      "step": 63
    },
    {
      "epoch": 1.544,
      "grad_norm": 0.041382331057486954,
      "learning_rate": 5.569957049452703e-05,
      "loss": 0.5195,
      "step": 64
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.04890189320533228,
      "learning_rate": 5.427875042394199e-05,
      "loss": 0.576,
      "step": 65
    },
    {
      "epoch": 1.592,
      "grad_norm": 0.049055416858589336,
      "learning_rate": 5.2854440543138406e-05,
      "loss": 0.5864,
      "step": 66
    },
    {
      "epoch": 1.616,
      "grad_norm": 0.03746640997017083,
      "learning_rate": 5.142780253968481e-05,
      "loss": 0.5549,
      "step": 67
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.04719163575348306,
      "learning_rate": 5e-05,
      "loss": 0.582,
      "step": 68
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.04070903369553021,
      "learning_rate": 4.85721974603152e-05,
      "loss": 0.5794,
      "step": 69
    },
    {
      "epoch": 1.688,
      "grad_norm": 0.048706176585568355,
      "learning_rate": 4.71455594568616e-05,
      "loss": 0.554,
      "step": 70
    },
    {
      "epoch": 1.712,
      "grad_norm": 0.038856432195802794,
      "learning_rate": 4.5721249576058027e-05,
      "loss": 0.5623,
      "step": 71
    },
    {
      "epoch": 1.736,
      "grad_norm": 0.04528530194550223,
      "learning_rate": 4.4300429505472976e-05,
      "loss": 0.5894,
      "step": 72
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.03820539197407199,
      "learning_rate": 4.288425808633575e-05,
      "loss": 0.5439,
      "step": 73
    },
    {
      "epoch": 1.784,
      "grad_norm": 0.04187780982436848,
      "learning_rate": 4.147389036836881e-05,
      "loss": 0.5993,
      "step": 74
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.03642377304544682,
      "learning_rate": 4.007047666771274e-05,
      "loss": 0.5225,
      "step": 75
    },
    {
      "epoch": 1.8319999999999999,
      "grad_norm": 0.03958136941613791,
      "learning_rate": 3.8675161628711776e-05,
      "loss": 0.6058,
      "step": 76
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.03783379131667843,
      "learning_rate": 3.728908329032567e-05,
      "loss": 0.5823,
      "step": 77
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.04039103496258606,
      "learning_rate": 3.591337215792852e-05,
      "loss": 0.5546,
      "step": 78
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.03899593343895715,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5698,
      "step": 79
    },
    {
      "epoch": 1.928,
      "grad_norm": 0.038209698795034865,
      "learning_rate": 3.3197530339228487e-05,
      "loss": 0.5625,
      "step": 80
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.03810473583372995,
      "learning_rate": 3.1859614732467954e-05,
      "loss": 0.5662,
      "step": 81
    },
    {
      "epoch": 1.976,
      "grad_norm": 0.03782143044774664,
      "learning_rate": 3.053649468413043e-05,
      "loss": 0.5787,
      "step": 82
    },
    {
      "epoch": 2.008,
      "grad_norm": 0.07618753565677125,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 0.9057,
      "step": 83
    },
    {
      "epoch": 2.032,
      "grad_norm": 0.03999693328865991,
      "learning_rate": 2.7938944937838923e-05,
      "loss": 0.5789,
      "step": 84
    },
    {
      "epoch": 2.056,
      "grad_norm": 0.03791025644954389,
      "learning_rate": 2.6666633838716314e-05,
      "loss": 0.5505,
      "step": 85
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.039270508786545984,
      "learning_rate": 2.5413353767719805e-05,
      "loss": 0.5636,
      "step": 86
    },
    {
      "epoch": 2.104,
      "grad_norm": 0.03965008595990656,
      "learning_rate": 2.418012691805191e-05,
      "loss": 0.5364,
      "step": 87
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.038749970466848624,
      "learning_rate": 2.296795912722014e-05,
      "loss": 0.552,
      "step": 88
    },
    {
      "epoch": 2.152,
      "grad_norm": 0.040641039194667855,
      "learning_rate": 2.1777839056661554e-05,
      "loss": 0.5886,
      "step": 89
    },
    {
      "epoch": 2.176,
      "grad_norm": 0.036298755789872766,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5386,
      "step": 90
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.03698832601767516,
      "learning_rate": 1.946760601822809e-05,
      "loss": 0.563,
      "step": 91
    },
    {
      "epoch": 2.224,
      "grad_norm": 0.03999375914665445,
      "learning_rate": 1.8349377309556486e-05,
      "loss": 0.566,
      "step": 92
    },
    {
      "epoch": 2.248,
      "grad_norm": 0.04014616835285834,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.5373,
      "step": 93
    },
    {
      "epoch": 2.2720000000000002,
      "grad_norm": 0.038525153293531296,
      "learning_rate": 1.619125498629904e-05,
      "loss": 0.5337,
      "step": 94
    },
    {
      "epoch": 2.296,
      "grad_norm": 0.0385748600604672,
      "learning_rate": 1.5153121567235335e-05,
      "loss": 0.5896,
      "step": 95
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.03679951278936808,
      "learning_rate": 1.414340976205183e-05,
      "loss": 0.5272,
      "step": 96
    },
    {
      "epoch": 2.344,
      "grad_norm": 0.03929593402454525,
      "learning_rate": 1.3162943106179749e-05,
      "loss": 0.5721,
      "step": 97
    },
    {
      "epoch": 2.368,
      "grad_norm": 0.0353829636923267,
      "learning_rate": 1.2212521282287092e-05,
      "loss": 0.5238,
      "step": 98
    },
    {
      "epoch": 2.392,
      "grad_norm": 0.039577733969761594,
      "learning_rate": 1.1292919468045877e-05,
      "loss": 0.6156,
      "step": 99
    },
    {
      "epoch": 2.416,
      "grad_norm": 0.03619160572847255,
      "learning_rate": 1.0404887703886251e-05,
      "loss": 0.5029,
      "step": 100
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.038621541462916534,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.575,
      "step": 101
    },
    {
      "epoch": 2.464,
      "grad_norm": 0.037325851942668076,
      "learning_rate": 8.7264051518613e-06,
      "loss": 0.5058,
      "step": 102
    },
    {
      "epoch": 2.488,
      "grad_norm": 0.04073574018349033,
      "learning_rate": 7.937323358440935e-06,
      "loss": 0.5521,
      "step": 103
    },
    {
      "epoch": 2.512,
      "grad_norm": 0.036589149211837486,
      "learning_rate": 7.182548487420554e-06,
      "loss": 0.5476,
      "step": 104
    },
    {
      "epoch": 2.536,
      "grad_norm": 0.041975055293630534,
      "learning_rate": 6.462696144011149e-06,
      "loss": 0.5711,
      "step": 105
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.037339999676971554,
      "learning_rate": 5.778353450109286e-06,
      "loss": 0.5671,
      "step": 106
    },
    {
      "epoch": 2.584,
      "grad_norm": 0.03722383390075537,
      "learning_rate": 5.13007856543209e-06,
      "loss": 0.5448,
      "step": 107
    },
    {
      "epoch": 2.608,
      "grad_norm": 0.03638299949371452,
      "learning_rate": 4.5184002322740785e-06,
      "loss": 0.57,
      "step": 108
    },
    {
      "epoch": 2.632,
      "grad_norm": 0.033646285554547885,
      "learning_rate": 3.9438173442575e-06,
      "loss": 0.5451,
      "step": 109
    },
    {
      "epoch": 2.656,
      "grad_norm": 0.03557917403444963,
      "learning_rate": 3.406798539427386e-06,
      "loss": 0.5671,
      "step": 110
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.03932882062272541,
      "learning_rate": 2.9077818180237693e-06,
      "loss": 0.5255,
      "step": 111
    },
    {
      "epoch": 2.7039999999999997,
      "grad_norm": 0.03928832403339685,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5619,
      "step": 112
    },
    {
      "epoch": 2.7279999999999998,
      "grad_norm": 0.03697704890616523,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 0.5236,
      "step": 113
    },
    {
      "epoch": 2.752,
      "grad_norm": 0.03535033007839283,
      "learning_rate": 1.6426572649021476e-06,
      "loss": 0.5765,
      "step": 114
    },
    {
      "epoch": 2.776,
      "grad_norm": 0.03390399749312069,
      "learning_rate": 1.2994041528833266e-06,
      "loss": 0.5428,
      "step": 115
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.03382823635726114,
      "learning_rate": 9.958719453803278e-07,
      "loss": 0.5384,
      "step": 116
    },
    {
      "epoch": 2.824,
      "grad_norm": 0.035688586966212944,
      "learning_rate": 7.323082076153509e-07,
      "loss": 0.5706,
      "step": 117
    },
    {
      "epoch": 2.848,
      "grad_norm": 0.035229142108639755,
      "learning_rate": 5.089279059533658e-07,
      "loss": 0.5766,
      "step": 118
    },
    {
      "epoch": 2.872,
      "grad_norm": 0.03239167426949711,
      "learning_rate": 3.2591323257248893e-07,
      "loss": 0.5172,
      "step": 119
    },
    {
      "epoch": 2.896,
      "grad_norm": 0.034544452731342226,
      "learning_rate": 1.8341345686543332e-07,
      "loss": 0.5491,
      "step": 120
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.034989830683371165,
      "learning_rate": 8.15448036932176e-08,
      "loss": 0.5576,
      "step": 121
    },
    {
      "epoch": 2.944,
      "grad_norm": 0.04321076770460129,
      "learning_rate": 2.0390358590538504e-08,
      "loss": 0.5803,
      "step": 122
    },
    {
      "epoch": 2.968,
      "grad_norm": 0.03411839473128948,
      "learning_rate": 0.0,
      "loss": 0.5549,
      "step": 123
    },
    {
      "epoch": 2.968,
      "step": 123,
      "total_flos": 684564746862592.0,
      "train_loss": 0.6186332760787592,
      "train_runtime": 23928.9155,
      "train_samples_per_second": 0.501,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 1,
  "max_steps": 123,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 684564746862592.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}