{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 510,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00392156862745098,
      "grad_norm": 16.544786089270207,
      "learning_rate": 3.921568627450981e-07,
      "loss": 1.6547,
      "step": 1
    },
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 14.762176989308287,
      "learning_rate": 1.96078431372549e-06,
      "loss": 1.617,
      "step": 5
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 5.1165863939415654,
      "learning_rate": 3.92156862745098e-06,
      "loss": 1.4078,
      "step": 10
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 2.2787880179843194,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.2895,
      "step": 15
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 1.832234050305862,
      "learning_rate": 7.84313725490196e-06,
      "loss": 1.2313,
      "step": 20
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 1.2251164606770868,
      "learning_rate": 9.803921568627451e-06,
      "loss": 1.1832,
      "step": 25
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.51446787757622,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.1558,
      "step": 30
    },
    {
      "epoch": 0.13725490196078433,
      "grad_norm": 1.1054530221391963,
      "learning_rate": 1.3725490196078432e-05,
      "loss": 1.1678,
      "step": 35
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 1.1955722975383631,
      "learning_rate": 1.568627450980392e-05,
      "loss": 1.162,
      "step": 40
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 1.1601166405223855,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 1.1303,
      "step": 45
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 1.2824519717268024,
      "learning_rate": 1.9607843137254903e-05,
      "loss": 1.1272,
      "step": 50
    },
    {
      "epoch": 0.21568627450980393,
      "grad_norm": 1.1682993723393238,
      "learning_rate": 1.999625253802851e-05,
      "loss": 1.1209,
      "step": 55
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.302075491367261,
      "learning_rate": 1.9981033287370443e-05,
      "loss": 1.0887,
      "step": 60
    },
    {
      "epoch": 0.2549019607843137,
      "grad_norm": 1.4556930650649318,
      "learning_rate": 1.9954125840299165e-05,
      "loss": 1.1226,
      "step": 65
    },
    {
      "epoch": 0.27450980392156865,
      "grad_norm": 1.289748942480489,
      "learning_rate": 1.9915561706530882e-05,
      "loss": 1.1327,
      "step": 70
    },
    {
      "epoch": 0.29411764705882354,
      "grad_norm": 1.1271075422611054,
      "learning_rate": 1.9865386046236597e-05,
      "loss": 1.1238,
      "step": 75
    },
    {
      "epoch": 0.3137254901960784,
      "grad_norm": 1.2436214858595933,
      "learning_rate": 1.9803657617157693e-05,
      "loss": 1.08,
      "step": 80
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.1690258085683884,
      "learning_rate": 1.973044870579824e-05,
      "loss": 1.111,
      "step": 85
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 1.0669536039386904,
      "learning_rate": 1.9645845042774555e-05,
      "loss": 1.1074,
      "step": 90
    },
    {
      "epoch": 0.37254901960784315,
      "grad_norm": 1.2617056965745426,
      "learning_rate": 1.9549945702421144e-05,
      "loss": 1.1073,
      "step": 95
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 1.0667234116768218,
      "learning_rate": 1.9442862986770645e-05,
      "loss": 1.1018,
      "step": 100
    },
    {
      "epoch": 0.4117647058823529,
      "grad_norm": 1.1310556155759037,
      "learning_rate": 1.932472229404356e-05,
      "loss": 1.1108,
      "step": 105
    },
    {
      "epoch": 0.43137254901960786,
      "grad_norm": 1.0707842591727832,
      "learning_rate": 1.9195661971801825e-05,
      "loss": 1.0978,
      "step": 110
    },
    {
      "epoch": 0.45098039215686275,
      "grad_norm": 1.1964147323589545,
      "learning_rate": 1.9055833154938208e-05,
      "loss": 1.0952,
      "step": 115
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.0532587111658636,
      "learning_rate": 1.8905399588691165e-05,
      "loss": 1.0901,
      "step": 120
    },
    {
      "epoch": 0.49019607843137253,
      "grad_norm": 1.0534305550044942,
      "learning_rate": 1.8744537436892517e-05,
      "loss": 1.0739,
      "step": 125
    },
    {
      "epoch": 0.5098039215686274,
      "grad_norm": 1.032737951798708,
      "learning_rate": 1.8573435075672422e-05,
      "loss": 1.0871,
      "step": 130
    },
    {
      "epoch": 0.5294117647058824,
      "grad_norm": 1.0758071447152808,
      "learning_rate": 1.839229287286327e-05,
      "loss": 1.0945,
      "step": 135
    },
    {
      "epoch": 0.5490196078431373,
      "grad_norm": 1.109162566034754,
      "learning_rate": 1.8201322953360758e-05,
      "loss": 1.0708,
      "step": 140
    },
    {
      "epoch": 0.5686274509803921,
      "grad_norm": 1.317192816494283,
      "learning_rate": 1.800074895071704e-05,
      "loss": 1.0764,
      "step": 145
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.0795334451744183,
      "learning_rate": 1.7790805745256703e-05,
      "loss": 1.0791,
      "step": 150
    },
    {
      "epoch": 0.6078431372549019,
      "grad_norm": 1.0411588891000574,
      "learning_rate": 1.7571739189022365e-05,
      "loss": 1.091,
      "step": 155
    },
    {
      "epoch": 0.6274509803921569,
      "grad_norm": 1.0108445010492009,
      "learning_rate": 1.7343805817871885e-05,
      "loss": 1.0809,
      "step": 160
    },
    {
      "epoch": 0.6470588235294118,
      "grad_norm": 1.0901231094990715,
      "learning_rate": 1.710727255106447e-05,
      "loss": 1.0602,
      "step": 165
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.0945695101274928,
      "learning_rate": 1.686241637868734e-05,
      "loss": 1.0777,
      "step": 170
    },
    {
      "epoch": 0.6862745098039216,
      "grad_norm": 1.193395829329031,
      "learning_rate": 1.660952403728902e-05,
      "loss": 1.0444,
      "step": 175
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.1047822048211582,
      "learning_rate": 1.634889167409923e-05,
      "loss": 1.0534,
      "step": 180
    },
    {
      "epoch": 0.7254901960784313,
      "grad_norm": 1.114058959698183,
      "learning_rate": 1.6080824500228367e-05,
      "loss": 1.0529,
      "step": 185
    },
    {
      "epoch": 0.7450980392156863,
      "grad_norm": 0.9904799394022883,
      "learning_rate": 1.5805636433252892e-05,
      "loss": 1.0793,
      "step": 190
    },
    {
      "epoch": 0.7647058823529411,
      "grad_norm": 1.2525818789945302,
      "learning_rate": 1.552364972960506e-05,
      "loss": 1.0708,
      "step": 195
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 1.1154866308925613,
      "learning_rate": 1.5235194607197508e-05,
      "loss": 1.0241,
      "step": 200
    },
    {
      "epoch": 0.803921568627451,
      "grad_norm": 1.0785210608261893,
      "learning_rate": 1.494060885872464e-05,
      "loss": 1.0733,
      "step": 205
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 1.1856668561642758,
      "learning_rate": 1.4640237456093636e-05,
      "loss": 1.0704,
      "step": 210
    },
    {
      "epoch": 0.8431372549019608,
      "grad_norm": 1.1422476630742018,
      "learning_rate": 1.4334432146448272e-05,
      "loss": 1.0655,
      "step": 215
    },
    {
      "epoch": 0.8627450980392157,
      "grad_norm": 0.9839617489985488,
      "learning_rate": 1.4023551040258726e-05,
      "loss": 1.0551,
      "step": 220
    },
    {
      "epoch": 0.8823529411764706,
      "grad_norm": 1.0486919008457822,
      "learning_rate": 1.3707958191959609e-05,
      "loss": 1.0479,
      "step": 225
    },
    {
      "epoch": 0.9019607843137255,
      "grad_norm": 1.0279452846404875,
      "learning_rate": 1.3388023173627413e-05,
      "loss": 1.0466,
      "step": 230
    },
    {
      "epoch": 0.9215686274509803,
      "grad_norm": 1.0670615822796066,
      "learning_rate": 1.3064120642196549e-05,
      "loss": 1.0554,
      "step": 235
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.0549543392774092,
      "learning_rate": 1.2736629900720832e-05,
      "loss": 1.0648,
      "step": 240
    },
    {
      "epoch": 0.9607843137254902,
      "grad_norm": 0.9674738336064063,
      "learning_rate": 1.2405934454194146e-05,
      "loss": 1.0197,
      "step": 245
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 0.9981821541554068,
      "learning_rate": 1.2072421560450497e-05,
      "loss": 1.0355,
      "step": 250
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9908436174645702,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 1.0409,
      "step": 255
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0343828201293945,
      "eval_runtime": 4.2299,
      "eval_samples_per_second": 37.826,
      "eval_steps_per_second": 0.709,
      "step": 255
    },
    {
      "epoch": 1.0196078431372548,
      "grad_norm": 2.78732105665186,
      "learning_rate": 1.1398508502017047e-05,
      "loss": 0.7588,
      "step": 260
    },
    {
      "epoch": 1.0392156862745099,
      "grad_norm": 1.5405892203726659,
      "learning_rate": 1.1058897516960817e-05,
      "loss": 0.7294,
      "step": 265
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 1.1503472595942978,
      "learning_rate": 1.0718046519793276e-05,
      "loss": 0.7224,
      "step": 270
    },
    {
      "epoch": 1.0784313725490196,
      "grad_norm": 1.1159446663960584,
      "learning_rate": 1.0376354660911772e-05,
      "loss": 0.7354,
      "step": 275
    },
    {
      "epoch": 1.0980392156862746,
      "grad_norm": 1.0502332790639606,
      "learning_rate": 1.0034222075396954e-05,
      "loss": 0.7255,
      "step": 280
    },
    {
      "epoch": 1.1176470588235294,
      "grad_norm": 0.9509421475398706,
      "learning_rate": 9.692049414438298e-06,
      "loss": 0.7154,
      "step": 285
    },
    {
      "epoch": 1.1372549019607843,
      "grad_norm": 0.988479903928271,
      "learning_rate": 9.350237376155269e-06,
      "loss": 0.7218,
      "step": 290
    },
    {
      "epoch": 1.156862745098039,
      "grad_norm": 1.0085376248525226,
      "learning_rate": 9.00918623636349e-06,
      "loss": 0.7366,
      "step": 295
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.9961601641040383,
      "learning_rate": 8.669295379835467e-06,
      "loss": 0.7184,
      "step": 300
    },
    {
      "epoch": 1.196078431372549,
      "grad_norm": 0.9921390197234601,
      "learning_rate": 8.330962832604747e-06,
      "loss": 0.7313,
      "step": 305
    },
    {
      "epoch": 1.215686274509804,
      "grad_norm": 1.0706453846667212,
      "learning_rate": 7.994584795861248e-06,
      "loss": 0.7257,
      "step": 310
    },
    {
      "epoch": 1.2352941176470589,
      "grad_norm": 1.0297863168482826,
      "learning_rate": 7.660555181983517e-06,
      "loss": 0.7468,
      "step": 315
    },
    {
      "epoch": 1.2549019607843137,
      "grad_norm": 0.9995332244709463,
      "learning_rate": 7.329265153251285e-06,
      "loss": 0.7439,
      "step": 320
    },
    {
      "epoch": 1.2745098039215685,
      "grad_norm": 1.0186580227806559,
      "learning_rate": 7.001102663778533e-06,
      "loss": 0.7172,
      "step": 325
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 1.014034224454933,
      "learning_rate": 6.6764520052034054e-06,
      "loss": 0.7309,
      "step": 330
    },
    {
      "epoch": 1.3137254901960784,
      "grad_norm": 1.0151160383199134,
      "learning_rate": 6.3556933566670656e-06,
      "loss": 0.719,
      "step": 335
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.9563996745028378,
      "learning_rate": 6.039202339608432e-06,
      "loss": 0.7448,
      "step": 340
    },
    {
      "epoch": 1.3529411764705883,
      "grad_norm": 0.9430025085055084,
      "learning_rate": 5.727349577896194e-06,
      "loss": 0.715,
      "step": 345
    },
    {
      "epoch": 1.3725490196078431,
      "grad_norm": 0.9520104411677209,
      "learning_rate": 5.420500263813141e-06,
      "loss": 0.7423,
      "step": 350
    },
    {
      "epoch": 1.392156862745098,
      "grad_norm": 0.9533462340832225,
      "learning_rate": 5.119013730401152e-06,
      "loss": 0.7206,
      "step": 355
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.944013138090968,
      "learning_rate": 4.823243030667576e-06,
      "loss": 0.7112,
      "step": 360
    },
    {
      "epoch": 1.4313725490196079,
      "grad_norm": 0.9654739136152124,
      "learning_rate": 4.533534524145756e-06,
      "loss": 0.7092,
      "step": 365
    },
    {
      "epoch": 1.4509803921568627,
      "grad_norm": 1.0325541079170395,
      "learning_rate": 4.2502274712939355e-06,
      "loss": 0.7218,
      "step": 370
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.945807759954701,
      "learning_rate": 3.973653636207437e-06,
      "loss": 0.7304,
      "step": 375
    },
    {
      "epoch": 1.4901960784313726,
      "grad_norm": 0.9339565355678595,
      "learning_rate": 3.704136898109403e-06,
      "loss": 0.723,
      "step": 380
    },
    {
      "epoch": 1.5098039215686274,
      "grad_norm": 0.9680921345423967,
      "learning_rate": 3.4419928720750274e-06,
      "loss": 0.7382,
      "step": 385
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.9738097860413395,
      "learning_rate": 3.1875285394334575e-06,
      "loss": 0.7129,
      "step": 390
    },
    {
      "epoch": 1.5490196078431373,
      "grad_norm": 0.9541739057939187,
      "learning_rate": 2.9410418882801682e-06,
      "loss": 0.7392,
      "step": 395
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 0.9315613334411681,
      "learning_rate": 2.702821564520732e-06,
      "loss": 0.7323,
      "step": 400
    },
    {
      "epoch": 1.5882352941176472,
      "grad_norm": 0.9959745037027158,
      "learning_rate": 2.4731465338547556e-06,
      "loss": 0.7501,
      "step": 405
    },
    {
      "epoch": 1.607843137254902,
      "grad_norm": 0.9359344044277552,
      "learning_rate": 2.252285755095652e-06,
      "loss": 0.733,
      "step": 410
    },
    {
      "epoch": 1.6274509803921569,
      "grad_norm": 0.9222172843750491,
      "learning_rate": 2.0404978652089325e-06,
      "loss": 0.6955,
      "step": 415
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.9295279337365954,
      "learning_rate": 1.8380308764377841e-06,
      "loss": 0.7209,
      "step": 420
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.9978286311378533,
      "learning_rate": 1.6451218858706374e-06,
      "loss": 0.7229,
      "step": 425
    },
    {
      "epoch": 1.6862745098039216,
      "grad_norm": 0.9673841209469143,
      "learning_rate": 1.4619967977908157e-06,
      "loss": 0.7197,
      "step": 430
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 0.9537359526264119,
      "learning_rate": 1.2888700591334225e-06,
      "loss": 0.7144,
      "step": 435
    },
    {
      "epoch": 1.7254901960784315,
      "grad_norm": 0.9009373079713732,
      "learning_rate": 1.1259444083592585e-06,
      "loss": 0.7078,
      "step": 440
    },
    {
      "epoch": 1.7450980392156863,
      "grad_norm": 0.9618775347330766,
      "learning_rate": 9.734106380398022e-07,
      "loss": 0.743,
      "step": 445
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.951269838967216,
      "learning_rate": 8.31447371431372e-07,
      "loss": 0.7278,
      "step": 450
    },
    {
      "epoch": 1.784313725490196,
      "grad_norm": 0.912258612261103,
      "learning_rate": 7.002208532999933e-07,
      "loss": 0.7241,
      "step": 455
    },
    {
      "epoch": 1.803921568627451,
      "grad_norm": 0.9276161963363886,
      "learning_rate": 5.798847552420184e-07,
      "loss": 0.7143,
      "step": 460
    },
    {
      "epoch": 1.8235294117647058,
      "grad_norm": 0.9666247110758565,
      "learning_rate": 4.7057999572843516e-07,
      "loss": 0.7165,
      "step": 465
    },
    {
      "epoch": 1.843137254901961,
      "grad_norm": 0.9040376476718873,
      "learning_rate": 3.7243457508358784e-07,
      "loss": 0.7192,
      "step": 470
    },
    {
      "epoch": 1.8627450980392157,
      "grad_norm": 0.9529298475220304,
      "learning_rate": 2.8556342559159513e-07,
      "loss": 0.7213,
      "step": 475
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.9373675816598103,
      "learning_rate": 2.1006827690595478e-07,
      "loss": 0.7247,
      "step": 480
    },
    {
      "epoch": 1.9019607843137254,
      "grad_norm": 0.9049110221925867,
      "learning_rate": 1.4603753691998735e-07,
      "loss": 0.7217,
      "step": 485
    },
    {
      "epoch": 1.9215686274509802,
      "grad_norm": 1.0200136766624364,
      "learning_rate": 9.354618823758654e-08,
      "loss": 0.712,
      "step": 490
    },
    {
      "epoch": 1.9411764705882353,
      "grad_norm": 1.0048113834797883,
      "learning_rate": 5.265570036553813e-08,
      "loss": 0.7337,
      "step": 495
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": 0.9199685223066211,
      "learning_rate": 2.3413957730226144e-08,
      "loss": 0.7121,
      "step": 500
    },
    {
      "epoch": 1.9803921568627452,
      "grad_norm": 0.8894954442490418,
      "learning_rate": 5.855203603017945e-09,
      "loss": 0.7124,
      "step": 505
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9330570772451235,
      "learning_rate": 0.0,
      "loss": 0.7276,
      "step": 510
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0487182140350342,
      "eval_runtime": 5.9345,
      "eval_samples_per_second": 26.961,
      "eval_steps_per_second": 0.506,
      "step": 510
    },
    {
      "epoch": 2.0,
      "step": 510,
      "total_flos": 106783624396800.0,
      "train_loss": 0.9181881465163886,
      "train_runtime": 3659.086,
      "train_samples_per_second": 8.919,
      "train_steps_per_second": 0.139
    }
  ],
  "logging_steps": 5,
  "max_steps": 510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 106783624396800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}