{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9725490196078432,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023529411764705882,
      "grad_norm": 6.901826858520508,
      "learning_rate": 7.692307692307694e-07,
      "loss": 1.1119,
      "step": 1
    },
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 7.422886371612549,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 1.1537,
      "step": 2
    },
    {
      "epoch": 0.07058823529411765,
      "grad_norm": 6.920129299163818,
      "learning_rate": 2.307692307692308e-06,
      "loss": 1.1205,
      "step": 3
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 6.285982608795166,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 1.0476,
      "step": 4
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 5.431225299835205,
      "learning_rate": 3.846153846153847e-06,
      "loss": 1.0753,
      "step": 5
    },
    {
      "epoch": 0.1411764705882353,
      "grad_norm": 3.6898839473724365,
      "learning_rate": 4.615384615384616e-06,
      "loss": 0.9761,
      "step": 6
    },
    {
      "epoch": 0.16470588235294117,
      "grad_norm": 2.8562192916870117,
      "learning_rate": 5.384615384615385e-06,
      "loss": 0.9581,
      "step": 7
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 4.019009590148926,
      "learning_rate": 6.153846153846155e-06,
      "loss": 1.0193,
      "step": 8
    },
    {
      "epoch": 0.21176470588235294,
      "grad_norm": 4.8232526779174805,
      "learning_rate": 6.923076923076923e-06,
      "loss": 0.951,
      "step": 9
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 4.59989595413208,
      "learning_rate": 7.692307692307694e-06,
      "loss": 1.0139,
      "step": 10
    },
    {
      "epoch": 0.25882352941176473,
      "grad_norm": 3.852893829345703,
      "learning_rate": 8.461538461538462e-06,
      "loss": 0.9087,
      "step": 11
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 3.7579197883605957,
      "learning_rate": 9.230769230769232e-06,
      "loss": 1.0375,
      "step": 12
    },
    {
      "epoch": 0.3058823529411765,
      "grad_norm": 2.5401360988616943,
      "learning_rate": 1e-05,
      "loss": 0.9651,
      "step": 13
    },
    {
      "epoch": 0.32941176470588235,
      "grad_norm": 2.095151424407959,
      "learning_rate": 9.998067787472772e-06,
      "loss": 0.9098,
      "step": 14
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 2.1526248455047607,
      "learning_rate": 9.992272643269181e-06,
      "loss": 0.8308,
      "step": 15
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 1.9617197513580322,
      "learning_rate": 9.982619046369321e-06,
      "loss": 0.9148,
      "step": 16
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.5976275205612183,
      "learning_rate": 9.96911445789354e-06,
      "loss": 0.8948,
      "step": 17
    },
    {
      "epoch": 0.4235294117647059,
      "grad_norm": 1.484428882598877,
      "learning_rate": 9.951769315335843e-06,
      "loss": 0.8592,
      "step": 18
    },
    {
      "epoch": 0.4470588235294118,
      "grad_norm": 1.4591351747512817,
      "learning_rate": 9.930597024496933e-06,
      "loss": 0.8315,
      "step": 19
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.1599817276000977,
      "learning_rate": 9.905613949123036e-06,
      "loss": 0.808,
      "step": 20
    },
    {
      "epoch": 0.49411764705882355,
      "grad_norm": 1.2381192445755005,
      "learning_rate": 9.87683939825864e-06,
      "loss": 0.8833,
      "step": 21
    },
    {
      "epoch": 0.5176470588235295,
      "grad_norm": 1.25748872756958,
      "learning_rate": 9.844295611322804e-06,
      "loss": 0.873,
      "step": 22
    },
    {
      "epoch": 0.5411764705882353,
      "grad_norm": 1.0262051820755005,
      "learning_rate": 9.808007740920647e-06,
      "loss": 0.7802,
      "step": 23
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.9352391362190247,
      "learning_rate": 9.768003833403278e-06,
      "loss": 0.8134,
      "step": 24
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.0994199514389038,
      "learning_rate": 9.724314807191197e-06,
      "loss": 0.8358,
      "step": 25
    },
    {
      "epoch": 0.611764705882353,
      "grad_norm": 0.9108858704566956,
      "learning_rate": 9.6769744288779e-06,
      "loss": 0.8229,
      "step": 26
    },
    {
      "epoch": 0.6352941176470588,
      "grad_norm": 0.7783969044685364,
      "learning_rate": 9.626019287132202e-06,
      "loss": 0.7928,
      "step": 27
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.8140386343002319,
      "learning_rate": 9.571488764419381e-06,
      "loss": 0.8129,
      "step": 28
    },
    {
      "epoch": 0.6823529411764706,
      "grad_norm": 0.7752570509910583,
      "learning_rate": 9.51342500656308e-06,
      "loss": 0.8572,
      "step": 29
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.678372323513031,
      "learning_rate": 9.451872890171419e-06,
      "loss": 0.8103,
      "step": 30
    },
    {
      "epoch": 0.7294117647058823,
      "grad_norm": 0.6800512075424194,
      "learning_rate": 9.386879987952549e-06,
      "loss": 0.897,
      "step": 31
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.6305904388427734,
      "learning_rate": 9.318496531946411e-06,
      "loss": 0.818,
      "step": 32
    },
    {
      "epoch": 0.7764705882352941,
      "grad_norm": 0.7293695211410522,
      "learning_rate": 9.246775374701139e-06,
      "loss": 0.8332,
      "step": 33
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7706238031387329,
      "learning_rate": 9.171771948424138e-06,
      "loss": 0.8584,
      "step": 34
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.6435885429382324,
      "learning_rate": 9.093544222139338e-06,
      "loss": 0.8726,
      "step": 35
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.7461095452308655,
      "learning_rate": 9.012152656883824e-06,
      "loss": 0.7851,
      "step": 36
    },
    {
      "epoch": 0.8705882352941177,
      "grad_norm": 0.8690148591995239,
      "learning_rate": 8.927660158978392e-06,
      "loss": 0.8347,
      "step": 37
    },
    {
      "epoch": 0.8941176470588236,
      "grad_norm": 0.6226567625999451,
      "learning_rate": 8.84013203140821e-06,
      "loss": 0.8419,
      "step": 38
    },
    {
      "epoch": 0.9176470588235294,
      "grad_norm": 0.603524923324585,
      "learning_rate": 8.749635923351108e-06,
      "loss": 0.776,
      "step": 39
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.6303524374961853,
      "learning_rate": 8.656241777892544e-06,
      "loss": 0.7207,
      "step": 40
    },
    {
      "epoch": 0.9647058823529412,
      "grad_norm": 0.5369915962219238,
      "learning_rate": 8.56002177796765e-06,
      "loss": 0.7694,
      "step": 41
    },
    {
      "epoch": 0.9882352941176471,
      "grad_norm": 0.5721177458763123,
      "learning_rate": 8.461050290572114e-06,
      "loss": 0.7732,
      "step": 42
    },
    {
      "epoch": 1.0156862745098039,
      "grad_norm": 1.0953840017318726,
      "learning_rate": 8.359403809285054e-06,
      "loss": 1.3119,
      "step": 43
    },
    {
      "epoch": 1.0392156862745099,
      "grad_norm": 0.5467516183853149,
      "learning_rate": 8.255160895148263e-06,
      "loss": 0.7665,
      "step": 44
    },
    {
      "epoch": 1.0627450980392157,
      "grad_norm": 0.6043545007705688,
      "learning_rate": 8.14840211594757e-06,
      "loss": 0.7368,
      "step": 45
    },
    {
      "epoch": 1.0862745098039215,
      "grad_norm": 0.6263077259063721,
      "learning_rate": 8.039209983943201e-06,
      "loss": 0.7976,
      "step": 46
    },
    {
      "epoch": 1.1098039215686275,
      "grad_norm": 0.5699981451034546,
      "learning_rate": 7.927668892097288e-06,
      "loss": 0.7109,
      "step": 47
    },
    {
      "epoch": 1.1333333333333333,
      "grad_norm": 0.5554935336112976,
      "learning_rate": 7.81386504884782e-06,
      "loss": 0.738,
      "step": 48
    },
    {
      "epoch": 1.156862745098039,
      "grad_norm": 0.7168362736701965,
      "learning_rate": 7.697886411479422e-06,
      "loss": 0.8269,
      "step": 49
    },
    {
      "epoch": 1.1803921568627451,
      "grad_norm": 0.5106287002563477,
      "learning_rate": 7.579822618142505e-06,
      "loss": 0.7993,
      "step": 50
    },
    {
      "epoch": 1.203921568627451,
      "grad_norm": 0.7224318385124207,
      "learning_rate": 7.459764918573264e-06,
      "loss": 0.8325,
      "step": 51
    },
    {
      "epoch": 1.227450980392157,
      "grad_norm": 0.6035781502723694,
      "learning_rate": 7.3378061035681415e-06,
      "loss": 0.73,
      "step": 52
    },
    {
      "epoch": 1.2509803921568627,
      "grad_norm": 0.5344979166984558,
      "learning_rate": 7.2140404332671986e-06,
      "loss": 0.7398,
      "step": 53
    },
    {
      "epoch": 1.2745098039215685,
      "grad_norm": 0.6349881291389465,
      "learning_rate": 7.088563564301874e-06,
      "loss": 0.8289,
      "step": 54
    },
    {
      "epoch": 1.2980392156862746,
      "grad_norm": 0.5782693028450012,
      "learning_rate": 6.961472475863406e-06,
      "loss": 0.7454,
      "step": 55
    },
    {
      "epoch": 1.3215686274509804,
      "grad_norm": 0.4461568295955658,
      "learning_rate": 6.832865394749065e-06,
      "loss": 0.6694,
      "step": 56
    },
    {
      "epoch": 1.3450980392156864,
      "grad_norm": 0.5781851410865784,
      "learning_rate": 6.702841719444141e-06,
      "loss": 0.8093,
      "step": 57
    },
    {
      "epoch": 1.3686274509803922,
      "grad_norm": 0.48329582810401917,
      "learning_rate": 6.571501943298335e-06,
      "loss": 0.7096,
      "step": 58
    },
    {
      "epoch": 1.392156862745098,
      "grad_norm": 0.6234760284423828,
      "learning_rate": 6.4389475768559675e-06,
      "loss": 0.8138,
      "step": 59
    },
    {
      "epoch": 1.415686274509804,
      "grad_norm": 0.49070653319358826,
      "learning_rate": 6.305281069399989e-06,
      "loss": 0.6619,
      "step": 60
    },
    {
      "epoch": 1.4392156862745098,
      "grad_norm": 0.49748146533966064,
      "learning_rate": 6.17060572977047e-06,
      "loss": 0.693,
      "step": 61
    },
    {
      "epoch": 1.4627450980392158,
      "grad_norm": 0.5554483532905579,
      "learning_rate": 6.035025646518747e-06,
      "loss": 0.7561,
      "step": 62
    },
    {
      "epoch": 1.4862745098039216,
      "grad_norm": 0.6127786040306091,
      "learning_rate": 5.898645607458941e-06,
      "loss": 0.7799,
      "step": 63
    },
    {
      "epoch": 1.5098039215686274,
      "grad_norm": 0.5526847839355469,
      "learning_rate": 5.761571018679025e-06,
      "loss": 0.7374,
      "step": 64
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 0.5685780644416809,
      "learning_rate": 5.623907823074044e-06,
      "loss": 0.8134,
      "step": 65
    },
    {
      "epoch": 1.5568627450980392,
      "grad_norm": 0.4792926013469696,
      "learning_rate": 5.48576241846443e-06,
      "loss": 0.7933,
      "step": 66
    },
    {
      "epoch": 1.5803921568627453,
      "grad_norm": 0.4758462607860565,
      "learning_rate": 5.347241575362729e-06,
      "loss": 0.7209,
      "step": 67
    },
    {
      "epoch": 1.603921568627451,
      "grad_norm": 0.5107057690620422,
      "learning_rate": 5.208452354452275e-06,
      "loss": 0.7746,
      "step": 68
    },
    {
      "epoch": 1.6274509803921569,
      "grad_norm": 0.4799031913280487,
      "learning_rate": 5.069502023841576e-06,
      "loss": 0.7635,
      "step": 69
    },
    {
      "epoch": 1.6509803921568627,
      "grad_norm": 0.5203085541725159,
      "learning_rate": 4.9304979761584256e-06,
      "loss": 0.7708,
      "step": 70
    },
    {
      "epoch": 1.6745098039215687,
      "grad_norm": 0.44460946321487427,
      "learning_rate": 4.791547645547727e-06,
      "loss": 0.6827,
      "step": 71
    },
    {
      "epoch": 1.6980392156862745,
      "grad_norm": 0.5535275340080261,
      "learning_rate": 4.652758424637271e-06,
      "loss": 0.794,
      "step": 72
    },
    {
      "epoch": 1.7215686274509805,
      "grad_norm": 0.4878956377506256,
      "learning_rate": 4.514237581535571e-06,
      "loss": 0.7368,
      "step": 73
    },
    {
      "epoch": 1.7450980392156863,
      "grad_norm": 0.5016121864318848,
      "learning_rate": 4.3760921769259585e-06,
      "loss": 0.6936,
      "step": 74
    },
    {
      "epoch": 1.768627450980392,
      "grad_norm": 0.5011301040649414,
      "learning_rate": 4.2384289813209754e-06,
      "loss": 0.7475,
      "step": 75
    },
    {
      "epoch": 1.792156862745098,
      "grad_norm": 0.4553963243961334,
      "learning_rate": 4.101354392541061e-06,
      "loss": 0.7358,
      "step": 76
    },
    {
      "epoch": 1.815686274509804,
      "grad_norm": 0.4620165228843689,
      "learning_rate": 3.964974353481254e-06,
      "loss": 0.7331,
      "step": 77
    },
    {
      "epoch": 1.83921568627451,
      "grad_norm": 0.4453507363796234,
      "learning_rate": 3.829394270229531e-06,
      "loss": 0.7295,
      "step": 78
    },
    {
      "epoch": 1.8627450980392157,
      "grad_norm": 0.402537077665329,
      "learning_rate": 3.694718930600012e-06,
      "loss": 0.642,
      "step": 79
    },
    {
      "epoch": 1.8862745098039215,
      "grad_norm": 0.4362320601940155,
      "learning_rate": 3.5610524231440324e-06,
      "loss": 0.7889,
      "step": 80
    },
    {
      "epoch": 1.9098039215686273,
      "grad_norm": 0.43875452876091003,
      "learning_rate": 3.428498056701665e-06,
      "loss": 0.7499,
      "step": 81
    },
    {
      "epoch": 1.9333333333333333,
      "grad_norm": 0.43475160002708435,
      "learning_rate": 3.2971582805558622e-06,
      "loss": 0.7663,
      "step": 82
    },
    {
      "epoch": 1.9568627450980394,
      "grad_norm": 0.46115896105766296,
      "learning_rate": 3.167134605250938e-06,
      "loss": 0.7652,
      "step": 83
    },
    {
      "epoch": 1.9803921568627452,
      "grad_norm": 0.4670518934726715,
      "learning_rate": 3.0385275241365965e-06,
      "loss": 0.7709,
      "step": 84
    },
    {
      "epoch": 2.007843137254902,
      "grad_norm": 0.8610158562660217,
      "learning_rate": 2.9114364356981274e-06,
      "loss": 1.2373,
      "step": 85
    },
    {
      "epoch": 2.0313725490196077,
      "grad_norm": 0.3888493478298187,
      "learning_rate": 2.7859595667328027e-06,
      "loss": 0.7255,
      "step": 86
    },
    {
      "epoch": 2.0549019607843135,
      "grad_norm": 0.42477184534072876,
      "learning_rate": 2.6621938964318593e-06,
      "loss": 0.6407,
      "step": 87
    },
    {
      "epoch": 2.0784313725490198,
      "grad_norm": 0.4506017863750458,
      "learning_rate": 2.5402350814267364e-06,
      "loss": 0.6873,
      "step": 88
    },
    {
      "epoch": 2.1019607843137256,
      "grad_norm": 0.48074784874916077,
      "learning_rate": 2.4201773818574956e-06,
      "loss": 0.6542,
      "step": 89
    },
    {
      "epoch": 2.1254901960784314,
      "grad_norm": 0.45760810375213623,
      "learning_rate": 2.302113588520578e-06,
      "loss": 0.6809,
      "step": 90
    },
    {
      "epoch": 2.149019607843137,
      "grad_norm": 0.3958469033241272,
      "learning_rate": 2.1861349511521817e-06,
      "loss": 0.6087,
      "step": 91
    },
    {
      "epoch": 2.172549019607843,
      "grad_norm": 0.479245662689209,
      "learning_rate": 2.072331107902713e-06,
      "loss": 0.9135,
      "step": 92
    },
    {
      "epoch": 2.196078431372549,
      "grad_norm": 0.4283719062805176,
      "learning_rate": 1.960790016056801e-06,
      "loss": 0.6736,
      "step": 93
    },
    {
      "epoch": 2.219607843137255,
      "grad_norm": 0.4299345314502716,
      "learning_rate": 1.8515978840524302e-06,
      "loss": 0.6972,
      "step": 94
    },
    {
      "epoch": 2.243137254901961,
      "grad_norm": 0.45547375082969666,
      "learning_rate": 1.7448391048517378e-06,
      "loss": 0.7224,
      "step": 95
    },
    {
      "epoch": 2.2666666666666666,
      "grad_norm": 0.40750595927238464,
      "learning_rate": 1.640596190714947e-06,
      "loss": 0.7225,
      "step": 96
    },
    {
      "epoch": 2.2901960784313724,
      "grad_norm": 0.43789613246917725,
      "learning_rate": 1.5389497094278861e-06,
      "loss": 0.7208,
      "step": 97
    },
    {
      "epoch": 2.313725490196078,
      "grad_norm": 0.4415332078933716,
      "learning_rate": 1.4399782220323515e-06,
      "loss": 0.6706,
      "step": 98
    },
    {
      "epoch": 2.3372549019607844,
      "grad_norm": 0.49981608986854553,
      "learning_rate": 1.3437582221074574e-06,
      "loss": 0.7925,
      "step": 99
    },
    {
      "epoch": 2.3607843137254902,
      "grad_norm": 0.48716047406196594,
      "learning_rate": 1.250364076648894e-06,
      "loss": 0.7385,
      "step": 100
    },
    {
      "epoch": 2.384313725490196,
      "grad_norm": 0.3869420886039734,
      "learning_rate": 1.1598679685917901e-06,
      "loss": 0.6665,
      "step": 101
    },
    {
      "epoch": 2.407843137254902,
      "grad_norm": 0.4081011116504669,
      "learning_rate": 1.0723398410216085e-06,
      "loss": 0.8291,
      "step": 102
    },
    {
      "epoch": 2.431372549019608,
      "grad_norm": 0.4056829512119293,
      "learning_rate": 9.878473431161767e-07,
      "loss": 0.6668,
      "step": 103
    },
    {
      "epoch": 2.454901960784314,
      "grad_norm": 0.36377865076065063,
      "learning_rate": 9.064557778606631e-07,
      "loss": 0.6017,
      "step": 104
    },
    {
      "epoch": 2.4784313725490197,
      "grad_norm": 0.43392133712768555,
      "learning_rate": 8.282280515758639e-07,
      "loss": 0.7824,
      "step": 105
    },
    {
      "epoch": 2.5019607843137255,
      "grad_norm": 0.47024935483932495,
      "learning_rate": 7.532246252988617e-07,
      "loss": 0.7446,
      "step": 106
    },
    {
      "epoch": 2.5254901960784313,
      "grad_norm": 0.425630658864975,
      "learning_rate": 6.815034680535915e-07,
      "loss": 0.713,
      "step": 107
    },
    {
      "epoch": 2.549019607843137,
      "grad_norm": 0.40889060497283936,
      "learning_rate": 6.131200120474512e-07,
      "loss": 0.7409,
      "step": 108
    },
    {
      "epoch": 2.572549019607843,
      "grad_norm": 0.40218353271484375,
      "learning_rate": 5.481271098285818e-07,
      "loss": 0.7501,
      "step": 109
    },
    {
      "epoch": 2.596078431372549,
      "grad_norm": 0.35820406675338745,
      "learning_rate": 4.865749934369224e-07,
      "loss": 0.6082,
      "step": 110
    },
    {
      "epoch": 2.619607843137255,
      "grad_norm": 0.42070600390434265,
      "learning_rate": 4.2851123558061927e-07,
      "loss": 0.7516,
      "step": 111
    },
    {
      "epoch": 2.6431372549019607,
      "grad_norm": 0.36287838220596313,
      "learning_rate": 3.739807128677986e-07,
      "loss": 0.6589,
      "step": 112
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.3751106560230255,
      "learning_rate": 3.230255711220992e-07,
      "loss": 0.7008,
      "step": 113
    },
    {
      "epoch": 2.6901960784313728,
      "grad_norm": 0.39373522996902466,
      "learning_rate": 2.756851928088056e-07,
      "loss": 0.7579,
      "step": 114
    },
    {
      "epoch": 2.7137254901960786,
      "grad_norm": 0.3703792989253998,
      "learning_rate": 2.3199616659672352e-07,
      "loss": 0.8005,
      "step": 115
    },
    {
      "epoch": 2.7372549019607844,
      "grad_norm": 0.3416251242160797,
      "learning_rate": 1.9199225907935492e-07,
      "loss": 0.6913,
      "step": 116
    },
    {
      "epoch": 2.76078431372549,
      "grad_norm": 0.3666976988315582,
      "learning_rate": 1.5570438867719695e-07,
      "loss": 0.6749,
      "step": 117
    },
    {
      "epoch": 2.784313725490196,
      "grad_norm": 0.41929343342781067,
      "learning_rate": 1.2316060174136e-07,
      "loss": 0.93,
      "step": 118
    },
    {
      "epoch": 2.8078431372549018,
      "grad_norm": 0.3298085033893585,
      "learning_rate": 9.43860508769645e-08,
      "loss": 0.5853,
      "step": 119
    },
    {
      "epoch": 2.831372549019608,
      "grad_norm": 0.4238205552101135,
      "learning_rate": 6.940297550306895e-08,
      "loss": 0.7548,
      "step": 120
    },
    {
      "epoch": 2.854901960784314,
      "grad_norm": 0.37445592880249023,
      "learning_rate": 4.823068466415615e-08,
      "loss": 0.7453,
      "step": 121
    },
    {
      "epoch": 2.8784313725490196,
      "grad_norm": 0.42801082134246826,
      "learning_rate": 3.088554210646133e-08,
      "loss": 0.8001,
      "step": 122
    },
    {
      "epoch": 2.9019607843137254,
      "grad_norm": 0.3497636616230011,
      "learning_rate": 1.7380953630678488e-08,
      "loss": 0.7289,
      "step": 123
    },
    {
      "epoch": 2.9254901960784316,
      "grad_norm": 0.4116727411746979,
      "learning_rate": 7.727356730820035e-09,
      "loss": 0.6974,
      "step": 124
    },
    {
      "epoch": 2.9490196078431374,
      "grad_norm": 0.3742615282535553,
      "learning_rate": 1.9322125272297488e-09,
      "loss": 0.765,
      "step": 125
    },
    {
      "epoch": 2.9725490196078432,
      "grad_norm": 0.36835694313049316,
      "learning_rate": 0.0,
      "loss": 0.6713,
      "step": 126
    },
    {
      "epoch": 2.9725490196078432,
      "step": 126,
      "total_flos": 121055548211200.0,
      "train_loss": 0.7961960165273576,
      "train_runtime": 4088.556,
      "train_samples_per_second": 2.986,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 121055548211200.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}