{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.997496871088861,
  "eval_steps": 500,
  "global_step": 1197,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025031289111389236,
      "grad_norm": 2.131367059642943,
      "learning_rate": 5e-06,
      "loss": 1.0783,
      "step": 10
    },
    {
      "epoch": 0.05006257822277847,
      "grad_norm": 5.240110415023845,
      "learning_rate": 5e-06,
      "loss": 0.9676,
      "step": 20
    },
    {
      "epoch": 0.07509386733416772,
      "grad_norm": 3.8068595828161884,
      "learning_rate": 5e-06,
      "loss": 0.9339,
      "step": 30
    },
    {
      "epoch": 0.10012515644555695,
      "grad_norm": 1.6005118869442196,
      "learning_rate": 5e-06,
      "loss": 0.9069,
      "step": 40
    },
    {
      "epoch": 0.1251564455569462,
      "grad_norm": 1.144980360790589,
      "learning_rate": 5e-06,
      "loss": 0.8873,
      "step": 50
    },
    {
      "epoch": 0.15018773466833543,
      "grad_norm": 0.9988315731444815,
      "learning_rate": 5e-06,
      "loss": 0.8743,
      "step": 60
    },
    {
      "epoch": 0.17521902377972465,
      "grad_norm": 1.1160785754418054,
      "learning_rate": 5e-06,
      "loss": 0.8694,
      "step": 70
    },
    {
      "epoch": 0.2002503128911139,
      "grad_norm": 0.6502972385224608,
      "learning_rate": 5e-06,
      "loss": 0.8554,
      "step": 80
    },
    {
      "epoch": 0.22528160200250313,
      "grad_norm": 1.1342296445805713,
      "learning_rate": 5e-06,
      "loss": 0.8509,
      "step": 90
    },
    {
      "epoch": 0.2503128911138924,
      "grad_norm": 1.7350477074788984,
      "learning_rate": 5e-06,
      "loss": 0.8447,
      "step": 100
    },
    {
      "epoch": 0.2753441802252816,
      "grad_norm": 1.4021943431412354,
      "learning_rate": 5e-06,
      "loss": 0.8397,
      "step": 110
    },
    {
      "epoch": 0.30037546933667086,
      "grad_norm": 0.7783764690541898,
      "learning_rate": 5e-06,
      "loss": 0.8363,
      "step": 120
    },
    {
      "epoch": 0.32540675844806005,
      "grad_norm": 1.054120463662093,
      "learning_rate": 5e-06,
      "loss": 0.8331,
      "step": 130
    },
    {
      "epoch": 0.3504380475594493,
      "grad_norm": 0.7025904608947156,
      "learning_rate": 5e-06,
      "loss": 0.8319,
      "step": 140
    },
    {
      "epoch": 0.37546933667083854,
      "grad_norm": 0.625073338332613,
      "learning_rate": 5e-06,
      "loss": 0.8228,
      "step": 150
    },
    {
      "epoch": 0.4005006257822278,
      "grad_norm": 0.68586294875638,
      "learning_rate": 5e-06,
      "loss": 0.8273,
      "step": 160
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 0.7166203381918367,
      "learning_rate": 5e-06,
      "loss": 0.8271,
      "step": 170
    },
    {
      "epoch": 0.45056320400500627,
      "grad_norm": 0.7727657584916029,
      "learning_rate": 5e-06,
      "loss": 0.8201,
      "step": 180
    },
    {
      "epoch": 0.4755944931163955,
      "grad_norm": 0.6165452607139709,
      "learning_rate": 5e-06,
      "loss": 0.8165,
      "step": 190
    },
    {
      "epoch": 0.5006257822277848,
      "grad_norm": 0.5941915725497845,
      "learning_rate": 5e-06,
      "loss": 0.8165,
      "step": 200
    },
    {
      "epoch": 0.5256570713391739,
      "grad_norm": 0.9044617312024994,
      "learning_rate": 5e-06,
      "loss": 0.814,
      "step": 210
    },
    {
      "epoch": 0.5506883604505632,
      "grad_norm": 0.9023052529604444,
      "learning_rate": 5e-06,
      "loss": 0.8158,
      "step": 220
    },
    {
      "epoch": 0.5757196495619524,
      "grad_norm": 0.8778852029110713,
      "learning_rate": 5e-06,
      "loss": 0.8126,
      "step": 230
    },
    {
      "epoch": 0.6007509386733417,
      "grad_norm": 0.7745768192218916,
      "learning_rate": 5e-06,
      "loss": 0.8094,
      "step": 240
    },
    {
      "epoch": 0.6257822277847309,
      "grad_norm": 0.676919868236649,
      "learning_rate": 5e-06,
      "loss": 0.8081,
      "step": 250
    },
    {
      "epoch": 0.6508135168961201,
      "grad_norm": 0.6457111096534787,
      "learning_rate": 5e-06,
      "loss": 0.8063,
      "step": 260
    },
    {
      "epoch": 0.6758448060075094,
      "grad_norm": 0.6026716036669796,
      "learning_rate": 5e-06,
      "loss": 0.8086,
      "step": 270
    },
    {
      "epoch": 0.7008760951188986,
      "grad_norm": 0.6933525279767419,
      "learning_rate": 5e-06,
      "loss": 0.8006,
      "step": 280
    },
    {
      "epoch": 0.7259073842302879,
      "grad_norm": 0.9470644278270366,
      "learning_rate": 5e-06,
      "loss": 0.8006,
      "step": 290
    },
    {
      "epoch": 0.7509386733416771,
      "grad_norm": 0.9427280269205052,
      "learning_rate": 5e-06,
      "loss": 0.7961,
      "step": 300
    },
    {
      "epoch": 0.7759699624530664,
      "grad_norm": 0.7264873730589139,
      "learning_rate": 5e-06,
      "loss": 0.7989,
      "step": 310
    },
    {
      "epoch": 0.8010012515644556,
      "grad_norm": 0.6143483178764919,
      "learning_rate": 5e-06,
      "loss": 0.7958,
      "step": 320
    },
    {
      "epoch": 0.8260325406758448,
      "grad_norm": 0.8137195556401391,
      "learning_rate": 5e-06,
      "loss": 0.798,
      "step": 330
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.6352119054411591,
      "learning_rate": 5e-06,
      "loss": 0.7979,
      "step": 340
    },
    {
      "epoch": 0.8760951188986232,
      "grad_norm": 0.6463859124240815,
      "learning_rate": 5e-06,
      "loss": 0.796,
      "step": 350
    },
    {
      "epoch": 0.9011264080100125,
      "grad_norm": 0.60316586739445,
      "learning_rate": 5e-06,
      "loss": 0.7927,
      "step": 360
    },
    {
      "epoch": 0.9261576971214017,
      "grad_norm": 0.893894099723059,
      "learning_rate": 5e-06,
      "loss": 0.7954,
      "step": 370
    },
    {
      "epoch": 0.951188986232791,
      "grad_norm": 0.5680880106145626,
      "learning_rate": 5e-06,
      "loss": 0.7892,
      "step": 380
    },
    {
      "epoch": 0.9762202753441802,
      "grad_norm": 0.6238008753559559,
      "learning_rate": 5e-06,
      "loss": 0.7876,
      "step": 390
    },
    {
      "epoch": 0.9987484355444305,
      "eval_loss": 0.7894856929779053,
      "eval_runtime": 272.7742,
      "eval_samples_per_second": 39.461,
      "eval_steps_per_second": 0.62,
      "step": 399
    },
    {
      "epoch": 1.0018773466833542,
      "grad_norm": 1.4020823851876998,
      "learning_rate": 5e-06,
      "loss": 0.8446,
      "step": 400
    },
    {
      "epoch": 1.0269086357947435,
      "grad_norm": 0.9263533629153153,
      "learning_rate": 5e-06,
      "loss": 0.7458,
      "step": 410
    },
    {
      "epoch": 1.0519399249061328,
      "grad_norm": 0.7694418549908636,
      "learning_rate": 5e-06,
      "loss": 0.7468,
      "step": 420
    },
    {
      "epoch": 1.0769712140175218,
      "grad_norm": 0.6223863756395531,
      "learning_rate": 5e-06,
      "loss": 0.7482,
      "step": 430
    },
    {
      "epoch": 1.1020025031289111,
      "grad_norm": 0.6462188205588866,
      "learning_rate": 5e-06,
      "loss": 0.7462,
      "step": 440
    },
    {
      "epoch": 1.1270337922403004,
      "grad_norm": 0.8428401134288817,
      "learning_rate": 5e-06,
      "loss": 0.7451,
      "step": 450
    },
    {
      "epoch": 1.1520650813516897,
      "grad_norm": 0.6127601124586929,
      "learning_rate": 5e-06,
      "loss": 0.7455,
      "step": 460
    },
    {
      "epoch": 1.1770963704630788,
      "grad_norm": 0.6867077491456403,
      "learning_rate": 5e-06,
      "loss": 0.7464,
      "step": 470
    },
    {
      "epoch": 1.202127659574468,
      "grad_norm": 0.655478438583233,
      "learning_rate": 5e-06,
      "loss": 0.7467,
      "step": 480
    },
    {
      "epoch": 1.2271589486858574,
      "grad_norm": 0.6163393565591452,
      "learning_rate": 5e-06,
      "loss": 0.7466,
      "step": 490
    },
    {
      "epoch": 1.2521902377972465,
      "grad_norm": 0.593653632025471,
      "learning_rate": 5e-06,
      "loss": 0.7472,
      "step": 500
    },
    {
      "epoch": 1.2772215269086358,
      "grad_norm": 0.7027928119588218,
      "learning_rate": 5e-06,
      "loss": 0.7483,
      "step": 510
    },
    {
      "epoch": 1.302252816020025,
      "grad_norm": 0.6854728377454722,
      "learning_rate": 5e-06,
      "loss": 0.7435,
      "step": 520
    },
    {
      "epoch": 1.3272841051314144,
      "grad_norm": 1.0781928345187066,
      "learning_rate": 5e-06,
      "loss": 0.7466,
      "step": 530
    },
    {
      "epoch": 1.3523153942428034,
      "grad_norm": 0.6327512087924364,
      "learning_rate": 5e-06,
      "loss": 0.7448,
      "step": 540
    },
    {
      "epoch": 1.3773466833541927,
      "grad_norm": 0.6100108550845114,
      "learning_rate": 5e-06,
      "loss": 0.744,
      "step": 550
    },
    {
      "epoch": 1.402377972465582,
      "grad_norm": 0.7365288494797091,
      "learning_rate": 5e-06,
      "loss": 0.7478,
      "step": 560
    },
    {
      "epoch": 1.4274092615769711,
      "grad_norm": 0.5377128504214334,
      "learning_rate": 5e-06,
      "loss": 0.7439,
      "step": 570
    },
    {
      "epoch": 1.4524405506883604,
      "grad_norm": 0.6741574190963199,
      "learning_rate": 5e-06,
      "loss": 0.7409,
      "step": 580
    },
    {
      "epoch": 1.4774718397997497,
      "grad_norm": 0.6592122959853899,
      "learning_rate": 5e-06,
      "loss": 0.7426,
      "step": 590
    },
    {
      "epoch": 1.502503128911139,
      "grad_norm": 0.8235710348347305,
      "learning_rate": 5e-06,
      "loss": 0.7411,
      "step": 600
    },
    {
      "epoch": 1.5275344180225283,
      "grad_norm": 0.7239324585893679,
      "learning_rate": 5e-06,
      "loss": 0.7443,
      "step": 610
    },
    {
      "epoch": 1.5525657071339174,
      "grad_norm": 0.6151649317588374,
      "learning_rate": 5e-06,
      "loss": 0.745,
      "step": 620
    },
    {
      "epoch": 1.5775969962453065,
      "grad_norm": 0.750130072011022,
      "learning_rate": 5e-06,
      "loss": 0.7431,
      "step": 630
    },
    {
      "epoch": 1.6026282853566958,
      "grad_norm": 0.6703845951317265,
      "learning_rate": 5e-06,
      "loss": 0.745,
      "step": 640
    },
    {
      "epoch": 1.627659574468085,
      "grad_norm": 0.5817463764362418,
      "learning_rate": 5e-06,
      "loss": 0.745,
      "step": 650
    },
    {
      "epoch": 1.6526908635794744,
      "grad_norm": 0.6421167763606337,
      "learning_rate": 5e-06,
      "loss": 0.7413,
      "step": 660
    },
    {
      "epoch": 1.6777221526908637,
      "grad_norm": 0.60677554331151,
      "learning_rate": 5e-06,
      "loss": 0.746,
      "step": 670
    },
    {
      "epoch": 1.702753441802253,
      "grad_norm": 0.6934469874354038,
      "learning_rate": 5e-06,
      "loss": 0.7434,
      "step": 680
    },
    {
      "epoch": 1.727784730913642,
      "grad_norm": 0.6181233971516625,
      "learning_rate": 5e-06,
      "loss": 0.7426,
      "step": 690
    },
    {
      "epoch": 1.7528160200250313,
      "grad_norm": 1.2959559737613207,
      "learning_rate": 5e-06,
      "loss": 0.7397,
      "step": 700
    },
    {
      "epoch": 1.7778473091364204,
      "grad_norm": 0.5691879884263149,
      "learning_rate": 5e-06,
      "loss": 0.7425,
      "step": 710
    },
    {
      "epoch": 1.8028785982478097,
      "grad_norm": 0.6574433826038453,
      "learning_rate": 5e-06,
      "loss": 0.7415,
      "step": 720
    },
    {
      "epoch": 1.827909887359199,
      "grad_norm": 0.6537064387599367,
      "learning_rate": 5e-06,
      "loss": 0.7409,
      "step": 730
    },
    {
      "epoch": 1.8529411764705883,
      "grad_norm": 0.5954863570531691,
      "learning_rate": 5e-06,
      "loss": 0.741,
      "step": 740
    },
    {
      "epoch": 1.8779724655819776,
      "grad_norm": 0.6362794802654446,
      "learning_rate": 5e-06,
      "loss": 0.7398,
      "step": 750
    },
    {
      "epoch": 1.9030037546933667,
      "grad_norm": 0.5986786317956753,
      "learning_rate": 5e-06,
      "loss": 0.7375,
      "step": 760
    },
    {
      "epoch": 1.928035043804756,
      "grad_norm": 0.7083210186967874,
      "learning_rate": 5e-06,
      "loss": 0.7398,
      "step": 770
    },
    {
      "epoch": 1.953066332916145,
      "grad_norm": 0.5556104219419278,
      "learning_rate": 5e-06,
      "loss": 0.738,
      "step": 780
    },
    {
      "epoch": 1.9780976220275344,
      "grad_norm": 0.5820311052189984,
      "learning_rate": 5e-06,
      "loss": 0.7419,
      "step": 790
    },
    {
      "epoch": 1.9981226533166458,
      "eval_loss": 0.7726743817329407,
      "eval_runtime": 279.978,
      "eval_samples_per_second": 38.446,
      "eval_steps_per_second": 0.604,
      "step": 798
    },
    {
      "epoch": 2.0037546933667083,
      "grad_norm": 1.1635293256781625,
      "learning_rate": 5e-06,
      "loss": 0.7865,
      "step": 800
    },
    {
      "epoch": 2.0287859824780976,
      "grad_norm": 0.7276790303807796,
      "learning_rate": 5e-06,
      "loss": 0.699,
      "step": 810
    },
    {
      "epoch": 2.053817271589487,
      "grad_norm": 0.7288566025250091,
      "learning_rate": 5e-06,
      "loss": 0.6925,
      "step": 820
    },
    {
      "epoch": 2.078848560700876,
      "grad_norm": 0.7172705630929458,
      "learning_rate": 5e-06,
      "loss": 0.6919,
      "step": 830
    },
    {
      "epoch": 2.1038798498122655,
      "grad_norm": 0.6776212393282559,
      "learning_rate": 5e-06,
      "loss": 0.6934,
      "step": 840
    },
    {
      "epoch": 2.1289111389236544,
      "grad_norm": 0.6439197802971096,
      "learning_rate": 5e-06,
      "loss": 0.6927,
      "step": 850
    },
    {
      "epoch": 2.1539424280350437,
      "grad_norm": 0.6173323306558143,
      "learning_rate": 5e-06,
      "loss": 0.6937,
      "step": 860
    },
    {
      "epoch": 2.178973717146433,
      "grad_norm": 0.7564554823831022,
      "learning_rate": 5e-06,
      "loss": 0.6945,
      "step": 870
    },
    {
      "epoch": 2.2040050062578223,
      "grad_norm": 0.6620302857887288,
      "learning_rate": 5e-06,
      "loss": 0.6944,
      "step": 880
    },
    {
      "epoch": 2.2290362953692116,
      "grad_norm": 0.6377986146944816,
      "learning_rate": 5e-06,
      "loss": 0.6964,
      "step": 890
    },
    {
      "epoch": 2.254067584480601,
      "grad_norm": 0.5556020070065616,
      "learning_rate": 5e-06,
      "loss": 0.6935,
      "step": 900
    },
    {
      "epoch": 2.27909887359199,
      "grad_norm": 0.7076075517084951,
      "learning_rate": 5e-06,
      "loss": 0.6993,
      "step": 910
    },
    {
      "epoch": 2.3041301627033794,
      "grad_norm": 0.5973458431773908,
      "learning_rate": 5e-06,
      "loss": 0.6986,
      "step": 920
    },
    {
      "epoch": 2.3291614518147683,
      "grad_norm": 0.7640330738397633,
      "learning_rate": 5e-06,
      "loss": 0.6979,
      "step": 930
    },
    {
      "epoch": 2.3541927409261576,
      "grad_norm": 0.6544037662816962,
      "learning_rate": 5e-06,
      "loss": 0.6985,
      "step": 940
    },
    {
      "epoch": 2.379224030037547,
      "grad_norm": 0.643258238595077,
      "learning_rate": 5e-06,
      "loss": 0.6994,
      "step": 950
    },
    {
      "epoch": 2.404255319148936,
      "grad_norm": 0.622397334096867,
      "learning_rate": 5e-06,
      "loss": 0.6953,
      "step": 960
    },
    {
      "epoch": 2.4292866082603255,
      "grad_norm": 0.7595102567708334,
      "learning_rate": 5e-06,
      "loss": 0.6977,
      "step": 970
    },
    {
      "epoch": 2.454317897371715,
      "grad_norm": 0.6430300856113221,
      "learning_rate": 5e-06,
      "loss": 0.6936,
      "step": 980
    },
    {
      "epoch": 2.4793491864831037,
      "grad_norm": 0.6649001597729085,
      "learning_rate": 5e-06,
      "loss": 0.6966,
      "step": 990
    },
    {
      "epoch": 2.504380475594493,
      "grad_norm": 0.7807773547782566,
      "learning_rate": 5e-06,
      "loss": 0.6977,
      "step": 1000
    },
    {
      "epoch": 2.5294117647058822,
      "grad_norm": 0.7685637796964472,
      "learning_rate": 5e-06,
      "loss": 0.7037,
      "step": 1010
    },
    {
      "epoch": 2.5544430538172715,
      "grad_norm": 0.6087836172391723,
      "learning_rate": 5e-06,
      "loss": 0.695,
      "step": 1020
    },
    {
      "epoch": 2.579474342928661,
      "grad_norm": 0.6126786752740975,
      "learning_rate": 5e-06,
      "loss": 0.702,
      "step": 1030
    },
    {
      "epoch": 2.60450563204005,
      "grad_norm": 0.5692342336245159,
      "learning_rate": 5e-06,
      "loss": 0.6965,
      "step": 1040
    },
    {
      "epoch": 2.6295369211514394,
      "grad_norm": 0.5461330132492804,
      "learning_rate": 5e-06,
      "loss": 0.6958,
      "step": 1050
    },
    {
      "epoch": 2.6545682102628287,
      "grad_norm": 0.5974455044275497,
      "learning_rate": 5e-06,
      "loss": 0.6977,
      "step": 1060
    },
    {
      "epoch": 2.679599499374218,
      "grad_norm": 0.6678395373217543,
      "learning_rate": 5e-06,
      "loss": 0.6992,
      "step": 1070
    },
    {
      "epoch": 2.704630788485607,
      "grad_norm": 0.6068475995182039,
      "learning_rate": 5e-06,
      "loss": 0.6977,
      "step": 1080
    },
    {
      "epoch": 2.729662077596996,
      "grad_norm": 0.6224775601315933,
      "learning_rate": 5e-06,
      "loss": 0.6994,
      "step": 1090
    },
    {
      "epoch": 2.7546933667083855,
      "grad_norm": 0.5607628869873644,
      "learning_rate": 5e-06,
      "loss": 0.698,
      "step": 1100
    },
    {
      "epoch": 2.779724655819775,
      "grad_norm": 1.0197508263783457,
      "learning_rate": 5e-06,
      "loss": 0.699,
      "step": 1110
    },
    {
      "epoch": 2.804755944931164,
      "grad_norm": 0.6699677843683128,
      "learning_rate": 5e-06,
      "loss": 0.6979,
      "step": 1120
    },
    {
      "epoch": 2.829787234042553,
      "grad_norm": 0.6628279862395011,
      "learning_rate": 5e-06,
      "loss": 0.7011,
      "step": 1130
    },
    {
      "epoch": 2.8548185231539422,
      "grad_norm": 0.5823164374883697,
      "learning_rate": 5e-06,
      "loss": 0.6988,
      "step": 1140
    },
    {
      "epoch": 2.8798498122653315,
      "grad_norm": 0.6607195364082912,
      "learning_rate": 5e-06,
      "loss": 0.6968,
      "step": 1150
    },
    {
      "epoch": 2.904881101376721,
      "grad_norm": 0.577549838302954,
      "learning_rate": 5e-06,
      "loss": 0.7005,
      "step": 1160
    },
    {
      "epoch": 2.92991239048811,
      "grad_norm": 0.6569021208672484,
      "learning_rate": 5e-06,
      "loss": 0.7034,
      "step": 1170
    },
    {
      "epoch": 2.9549436795994994,
      "grad_norm": 0.5809953224848247,
      "learning_rate": 5e-06,
      "loss": 0.6951,
      "step": 1180
    },
    {
      "epoch": 2.9799749687108887,
      "grad_norm": 0.5986204550852365,
      "learning_rate": 5e-06,
      "loss": 0.6976,
      "step": 1190
    },
    {
      "epoch": 2.997496871088861,
      "eval_loss": 0.770167887210846,
      "eval_runtime": 267.216,
      "eval_samples_per_second": 40.282,
      "eval_steps_per_second": 0.632,
      "step": 1197
    },
    {
      "epoch": 2.997496871088861,
      "step": 1197,
      "total_flos": 2004810203136000.0,
      "train_loss": 0.7593094730934902,
      "train_runtime": 39147.1454,
      "train_samples_per_second": 15.671,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 1197,
  "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": 2004810203136000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}