{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9981447124304266,
  "eval_steps": 500,
  "global_step": 1212,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024737167594310452,
      "grad_norm": 3.4830790839772257,
      "learning_rate": 5e-06,
      "loss": 0.8916,
      "step": 10
    },
    {
      "epoch": 0.049474335188620905,
      "grad_norm": 6.942725060810088,
      "learning_rate": 5e-06,
      "loss": 0.7677,
      "step": 20
    },
    {
      "epoch": 0.07421150278293136,
      "grad_norm": 1.8951062871081399,
      "learning_rate": 5e-06,
      "loss": 0.7288,
      "step": 30
    },
    {
      "epoch": 0.09894867037724181,
      "grad_norm": 1.9357008010716068,
      "learning_rate": 5e-06,
      "loss": 0.7031,
      "step": 40
    },
    {
      "epoch": 0.12368583797155226,
      "grad_norm": 0.9499312221395673,
      "learning_rate": 5e-06,
      "loss": 0.6844,
      "step": 50
    },
    {
      "epoch": 0.14842300556586271,
      "grad_norm": 0.7455987403828673,
      "learning_rate": 5e-06,
      "loss": 0.6598,
      "step": 60
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 0.6470160824911549,
      "learning_rate": 5e-06,
      "loss": 0.6485,
      "step": 70
    },
    {
      "epoch": 0.19789734075448362,
      "grad_norm": 0.6635217517468123,
      "learning_rate": 5e-06,
      "loss": 0.6398,
      "step": 80
    },
    {
      "epoch": 0.22263450834879406,
      "grad_norm": 0.5563048334006576,
      "learning_rate": 5e-06,
      "loss": 0.6378,
      "step": 90
    },
    {
      "epoch": 0.24737167594310452,
      "grad_norm": 0.685513800699662,
      "learning_rate": 5e-06,
      "loss": 0.6307,
      "step": 100
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 0.8408848874695213,
      "learning_rate": 5e-06,
      "loss": 0.6176,
      "step": 110
    },
    {
      "epoch": 0.29684601113172543,
      "grad_norm": 0.6773751764933612,
      "learning_rate": 5e-06,
      "loss": 0.6178,
      "step": 120
    },
    {
      "epoch": 0.32158317872603587,
      "grad_norm": 0.7027587036277353,
      "learning_rate": 5e-06,
      "loss": 0.6133,
      "step": 130
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 0.6157245730205899,
      "learning_rate": 5e-06,
      "loss": 0.6092,
      "step": 140
    },
    {
      "epoch": 0.37105751391465674,
      "grad_norm": 0.5802260294344969,
      "learning_rate": 5e-06,
      "loss": 0.6046,
      "step": 150
    },
    {
      "epoch": 0.39579468150896724,
      "grad_norm": 0.6344807037013861,
      "learning_rate": 5e-06,
      "loss": 0.6009,
      "step": 160
    },
    {
      "epoch": 0.4205318491032777,
      "grad_norm": 0.48480545471576164,
      "learning_rate": 5e-06,
      "loss": 0.6082,
      "step": 170
    },
    {
      "epoch": 0.4452690166975881,
      "grad_norm": 0.6380631405566793,
      "learning_rate": 5e-06,
      "loss": 0.6004,
      "step": 180
    },
    {
      "epoch": 0.47000618429189855,
      "grad_norm": 0.5505169198792789,
      "learning_rate": 5e-06,
      "loss": 0.5994,
      "step": 190
    },
    {
      "epoch": 0.49474335188620905,
      "grad_norm": 0.6242896844382176,
      "learning_rate": 5e-06,
      "loss": 0.5985,
      "step": 200
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.5255950166858494,
      "learning_rate": 5e-06,
      "loss": 0.6022,
      "step": 210
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 0.5516723643293726,
      "learning_rate": 5e-06,
      "loss": 0.5927,
      "step": 220
    },
    {
      "epoch": 0.5689548546691404,
      "grad_norm": 0.584042711614131,
      "learning_rate": 5e-06,
      "loss": 0.5925,
      "step": 230
    },
    {
      "epoch": 0.5936920222634509,
      "grad_norm": 0.6260676537261808,
      "learning_rate": 5e-06,
      "loss": 0.5928,
      "step": 240
    },
    {
      "epoch": 0.6184291898577613,
      "grad_norm": 0.5176619963131881,
      "learning_rate": 5e-06,
      "loss": 0.5858,
      "step": 250
    },
    {
      "epoch": 0.6431663574520717,
      "grad_norm": 0.5024236252235582,
      "learning_rate": 5e-06,
      "loss": 0.5879,
      "step": 260
    },
    {
      "epoch": 0.6679035250463822,
      "grad_norm": 0.6803247050243845,
      "learning_rate": 5e-06,
      "loss": 0.5844,
      "step": 270
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 0.6015791834486387,
      "learning_rate": 5e-06,
      "loss": 0.5755,
      "step": 280
    },
    {
      "epoch": 0.717377860235003,
      "grad_norm": 0.5299909658526826,
      "learning_rate": 5e-06,
      "loss": 0.5843,
      "step": 290
    },
    {
      "epoch": 0.7421150278293135,
      "grad_norm": 0.5088932556423367,
      "learning_rate": 5e-06,
      "loss": 0.5864,
      "step": 300
    },
    {
      "epoch": 0.766852195423624,
      "grad_norm": 0.5964832923195739,
      "learning_rate": 5e-06,
      "loss": 0.5822,
      "step": 310
    },
    {
      "epoch": 0.7915893630179345,
      "grad_norm": 0.5860489284099033,
      "learning_rate": 5e-06,
      "loss": 0.5727,
      "step": 320
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.5219580208519626,
      "learning_rate": 5e-06,
      "loss": 0.5794,
      "step": 330
    },
    {
      "epoch": 0.8410636982065554,
      "grad_norm": 0.5269259293045121,
      "learning_rate": 5e-06,
      "loss": 0.5793,
      "step": 340
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 0.5291953882291388,
      "learning_rate": 5e-06,
      "loss": 0.5744,
      "step": 350
    },
    {
      "epoch": 0.8905380333951762,
      "grad_norm": 0.521358302515632,
      "learning_rate": 5e-06,
      "loss": 0.5707,
      "step": 360
    },
    {
      "epoch": 0.9152752009894867,
      "grad_norm": 0.5774675957700983,
      "learning_rate": 5e-06,
      "loss": 0.5765,
      "step": 370
    },
    {
      "epoch": 0.9400123685837971,
      "grad_norm": 0.5172232609124243,
      "learning_rate": 5e-06,
      "loss": 0.5714,
      "step": 380
    },
    {
      "epoch": 0.9647495361781077,
      "grad_norm": 0.5240273423167071,
      "learning_rate": 5e-06,
      "loss": 0.5682,
      "step": 390
    },
    {
      "epoch": 0.9894867037724181,
      "grad_norm": 0.6149272559928857,
      "learning_rate": 5e-06,
      "loss": 0.5719,
      "step": 400
    },
    {
      "epoch": 0.9993815708101422,
      "eval_loss": 0.5683358907699585,
      "eval_runtime": 219.0047,
      "eval_samples_per_second": 49.734,
      "eval_steps_per_second": 0.393,
      "step": 404
    },
    {
      "epoch": 1.0142238713667284,
      "grad_norm": 0.5073078170608074,
      "learning_rate": 5e-06,
      "loss": 0.547,
      "step": 410
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 0.6437533127258526,
      "learning_rate": 5e-06,
      "loss": 0.5316,
      "step": 420
    },
    {
      "epoch": 1.0636982065553493,
      "grad_norm": 0.6100879209869073,
      "learning_rate": 5e-06,
      "loss": 0.5301,
      "step": 430
    },
    {
      "epoch": 1.08843537414966,
      "grad_norm": 0.48108127450705374,
      "learning_rate": 5e-06,
      "loss": 0.5294,
      "step": 440
    },
    {
      "epoch": 1.1131725417439704,
      "grad_norm": 0.5868928526612365,
      "learning_rate": 5e-06,
      "loss": 0.5332,
      "step": 450
    },
    {
      "epoch": 1.1379097093382808,
      "grad_norm": 0.6202895625151273,
      "learning_rate": 5e-06,
      "loss": 0.535,
      "step": 460
    },
    {
      "epoch": 1.1626468769325913,
      "grad_norm": 0.5075954994852542,
      "learning_rate": 5e-06,
      "loss": 0.5326,
      "step": 470
    },
    {
      "epoch": 1.1873840445269017,
      "grad_norm": 0.4728741075680983,
      "learning_rate": 5e-06,
      "loss": 0.532,
      "step": 480
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.5081500756875807,
      "learning_rate": 5e-06,
      "loss": 0.5348,
      "step": 490
    },
    {
      "epoch": 1.2368583797155226,
      "grad_norm": 0.6910919006687529,
      "learning_rate": 5e-06,
      "loss": 0.5197,
      "step": 500
    },
    {
      "epoch": 1.261595547309833,
      "grad_norm": 0.5501274010525514,
      "learning_rate": 5e-06,
      "loss": 0.5222,
      "step": 510
    },
    {
      "epoch": 1.2863327149041435,
      "grad_norm": 0.7316007600357546,
      "learning_rate": 5e-06,
      "loss": 0.5335,
      "step": 520
    },
    {
      "epoch": 1.311069882498454,
      "grad_norm": 0.5057200127850379,
      "learning_rate": 5e-06,
      "loss": 0.5288,
      "step": 530
    },
    {
      "epoch": 1.3358070500927643,
      "grad_norm": 0.5719065403986006,
      "learning_rate": 5e-06,
      "loss": 0.529,
      "step": 540
    },
    {
      "epoch": 1.3605442176870748,
      "grad_norm": 0.5660341689340015,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 550
    },
    {
      "epoch": 1.3852813852813852,
      "grad_norm": 0.7015838028229988,
      "learning_rate": 5e-06,
      "loss": 0.5296,
      "step": 560
    },
    {
      "epoch": 1.4100185528756957,
      "grad_norm": 0.5640160639184895,
      "learning_rate": 5e-06,
      "loss": 0.531,
      "step": 570
    },
    {
      "epoch": 1.434755720470006,
      "grad_norm": 0.5241187267275058,
      "learning_rate": 5e-06,
      "loss": 0.5277,
      "step": 580
    },
    {
      "epoch": 1.4594928880643168,
      "grad_norm": 0.5322661450321486,
      "learning_rate": 5e-06,
      "loss": 0.5223,
      "step": 590
    },
    {
      "epoch": 1.4842300556586272,
      "grad_norm": 0.5414175662054105,
      "learning_rate": 5e-06,
      "loss": 0.5253,
      "step": 600
    },
    {
      "epoch": 1.5089672232529376,
      "grad_norm": 0.5120018621643256,
      "learning_rate": 5e-06,
      "loss": 0.5171,
      "step": 610
    },
    {
      "epoch": 1.533704390847248,
      "grad_norm": 0.5872164754716582,
      "learning_rate": 5e-06,
      "loss": 0.5263,
      "step": 620
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 0.4661784659324605,
      "learning_rate": 5e-06,
      "loss": 0.5217,
      "step": 630
    },
    {
      "epoch": 1.583178726035869,
      "grad_norm": 0.464230352567236,
      "learning_rate": 5e-06,
      "loss": 0.5204,
      "step": 640
    },
    {
      "epoch": 1.6079158936301794,
      "grad_norm": 0.5032827937357744,
      "learning_rate": 5e-06,
      "loss": 0.5216,
      "step": 650
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 0.4996792160145028,
      "learning_rate": 5e-06,
      "loss": 0.5218,
      "step": 660
    },
    {
      "epoch": 1.6573902288188003,
      "grad_norm": 0.5271632514608294,
      "learning_rate": 5e-06,
      "loss": 0.5226,
      "step": 670
    },
    {
      "epoch": 1.6821273964131107,
      "grad_norm": 0.49347623420693476,
      "learning_rate": 5e-06,
      "loss": 0.5193,
      "step": 680
    },
    {
      "epoch": 1.7068645640074211,
      "grad_norm": 0.6049309413421875,
      "learning_rate": 5e-06,
      "loss": 0.5247,
      "step": 690
    },
    {
      "epoch": 1.7316017316017316,
      "grad_norm": 0.5973360853484692,
      "learning_rate": 5e-06,
      "loss": 0.516,
      "step": 700
    },
    {
      "epoch": 1.756338899196042,
      "grad_norm": 0.49072766464621603,
      "learning_rate": 5e-06,
      "loss": 0.5179,
      "step": 710
    },
    {
      "epoch": 1.7810760667903525,
      "grad_norm": 0.5091642966772914,
      "learning_rate": 5e-06,
      "loss": 0.5181,
      "step": 720
    },
    {
      "epoch": 1.805813234384663,
      "grad_norm": 0.5801588473122157,
      "learning_rate": 5e-06,
      "loss": 0.5177,
      "step": 730
    },
    {
      "epoch": 1.8305504019789733,
      "grad_norm": 0.48516680968832,
      "learning_rate": 5e-06,
      "loss": 0.5231,
      "step": 740
    },
    {
      "epoch": 1.8552875695732838,
      "grad_norm": 0.46039086459013556,
      "learning_rate": 5e-06,
      "loss": 0.5249,
      "step": 750
    },
    {
      "epoch": 1.8800247371675942,
      "grad_norm": 0.5083902833654592,
      "learning_rate": 5e-06,
      "loss": 0.518,
      "step": 760
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.5109759169478353,
      "learning_rate": 5e-06,
      "loss": 0.5177,
      "step": 770
    },
    {
      "epoch": 1.929499072356215,
      "grad_norm": 0.4767006976535441,
      "learning_rate": 5e-06,
      "loss": 0.5132,
      "step": 780
    },
    {
      "epoch": 1.9542362399505255,
      "grad_norm": 0.5035389849175771,
      "learning_rate": 5e-06,
      "loss": 0.5181,
      "step": 790
    },
    {
      "epoch": 1.978973407544836,
      "grad_norm": 0.5072097192727141,
      "learning_rate": 5e-06,
      "loss": 0.5166,
      "step": 800
    },
    {
      "epoch": 1.9987631416202845,
      "eval_loss": 0.5430302023887634,
      "eval_runtime": 219.3095,
      "eval_samples_per_second": 49.665,
      "eval_steps_per_second": 0.392,
      "step": 808
    },
    {
      "epoch": 2.0037105751391464,
      "grad_norm": 0.5742594976510665,
      "learning_rate": 5e-06,
      "loss": 0.5105,
      "step": 810
    },
    {
      "epoch": 2.028447742733457,
      "grad_norm": 0.5679263759068595,
      "learning_rate": 5e-06,
      "loss": 0.4801,
      "step": 820
    },
    {
      "epoch": 2.0531849103277673,
      "grad_norm": 0.5672377634558515,
      "learning_rate": 5e-06,
      "loss": 0.4818,
      "step": 830
    },
    {
      "epoch": 2.0779220779220777,
      "grad_norm": 0.6793815683511014,
      "learning_rate": 5e-06,
      "loss": 0.4756,
      "step": 840
    },
    {
      "epoch": 2.102659245516388,
      "grad_norm": 0.5158458141043201,
      "learning_rate": 5e-06,
      "loss": 0.4768,
      "step": 850
    },
    {
      "epoch": 2.1273964131106986,
      "grad_norm": 0.6722479592255648,
      "learning_rate": 5e-06,
      "loss": 0.481,
      "step": 860
    },
    {
      "epoch": 2.1521335807050095,
      "grad_norm": 0.622090680752648,
      "learning_rate": 5e-06,
      "loss": 0.4806,
      "step": 870
    },
    {
      "epoch": 2.17687074829932,
      "grad_norm": 0.5446538279562969,
      "learning_rate": 5e-06,
      "loss": 0.4792,
      "step": 880
    },
    {
      "epoch": 2.2016079158936304,
      "grad_norm": 0.9897157820333273,
      "learning_rate": 5e-06,
      "loss": 0.4743,
      "step": 890
    },
    {
      "epoch": 2.226345083487941,
      "grad_norm": 0.5709797478235871,
      "learning_rate": 5e-06,
      "loss": 0.4745,
      "step": 900
    },
    {
      "epoch": 2.2510822510822512,
      "grad_norm": 0.5508207898306552,
      "learning_rate": 5e-06,
      "loss": 0.4825,
      "step": 910
    },
    {
      "epoch": 2.2758194186765617,
      "grad_norm": 0.4968712039591529,
      "learning_rate": 5e-06,
      "loss": 0.4805,
      "step": 920
    },
    {
      "epoch": 2.300556586270872,
      "grad_norm": 0.5588550182736718,
      "learning_rate": 5e-06,
      "loss": 0.4816,
      "step": 930
    },
    {
      "epoch": 2.3252937538651826,
      "grad_norm": 0.6560301930501052,
      "learning_rate": 5e-06,
      "loss": 0.4834,
      "step": 940
    },
    {
      "epoch": 2.350030921459493,
      "grad_norm": 0.47583877726868273,
      "learning_rate": 5e-06,
      "loss": 0.4785,
      "step": 950
    },
    {
      "epoch": 2.3747680890538034,
      "grad_norm": 0.5212062104260379,
      "learning_rate": 5e-06,
      "loss": 0.4787,
      "step": 960
    },
    {
      "epoch": 2.399505256648114,
      "grad_norm": 0.47451320868129626,
      "learning_rate": 5e-06,
      "loss": 0.4829,
      "step": 970
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.4830738101162483,
      "learning_rate": 5e-06,
      "loss": 0.4843,
      "step": 980
    },
    {
      "epoch": 2.4489795918367347,
      "grad_norm": 0.5182106761363315,
      "learning_rate": 5e-06,
      "loss": 0.4757,
      "step": 990
    },
    {
      "epoch": 2.473716759431045,
      "grad_norm": 0.5153536365130167,
      "learning_rate": 5e-06,
      "loss": 0.4768,
      "step": 1000
    },
    {
      "epoch": 2.4984539270253556,
      "grad_norm": 0.5417873882437457,
      "learning_rate": 5e-06,
      "loss": 0.4782,
      "step": 1010
    },
    {
      "epoch": 2.523191094619666,
      "grad_norm": 0.5527273801359924,
      "learning_rate": 5e-06,
      "loss": 0.475,
      "step": 1020
    },
    {
      "epoch": 2.5479282622139765,
      "grad_norm": 0.5335187564602286,
      "learning_rate": 5e-06,
      "loss": 0.4792,
      "step": 1030
    },
    {
      "epoch": 2.572665429808287,
      "grad_norm": 0.5000885945895702,
      "learning_rate": 5e-06,
      "loss": 0.4769,
      "step": 1040
    },
    {
      "epoch": 2.5974025974025974,
      "grad_norm": 0.518335000088379,
      "learning_rate": 5e-06,
      "loss": 0.4771,
      "step": 1050
    },
    {
      "epoch": 2.622139764996908,
      "grad_norm": 0.5506780400189991,
      "learning_rate": 5e-06,
      "loss": 0.4813,
      "step": 1060
    },
    {
      "epoch": 2.6468769325912183,
      "grad_norm": 0.5009935325893752,
      "learning_rate": 5e-06,
      "loss": 0.479,
      "step": 1070
    },
    {
      "epoch": 2.6716141001855287,
      "grad_norm": 0.5265944850039301,
      "learning_rate": 5e-06,
      "loss": 0.4808,
      "step": 1080
    },
    {
      "epoch": 2.696351267779839,
      "grad_norm": 0.5426869881704958,
      "learning_rate": 5e-06,
      "loss": 0.4798,
      "step": 1090
    },
    {
      "epoch": 2.7210884353741496,
      "grad_norm": 0.6372802273548948,
      "learning_rate": 5e-06,
      "loss": 0.4824,
      "step": 1100
    },
    {
      "epoch": 2.74582560296846,
      "grad_norm": 0.5506322753225094,
      "learning_rate": 5e-06,
      "loss": 0.4748,
      "step": 1110
    },
    {
      "epoch": 2.7705627705627704,
      "grad_norm": 0.6432775550069307,
      "learning_rate": 5e-06,
      "loss": 0.4785,
      "step": 1120
    },
    {
      "epoch": 2.795299938157081,
      "grad_norm": 0.5422596013158468,
      "learning_rate": 5e-06,
      "loss": 0.4756,
      "step": 1130
    },
    {
      "epoch": 2.8200371057513913,
      "grad_norm": 0.5766402488022242,
      "learning_rate": 5e-06,
      "loss": 0.4813,
      "step": 1140
    },
    {
      "epoch": 2.8447742733457018,
      "grad_norm": 0.6098697051701109,
      "learning_rate": 5e-06,
      "loss": 0.4813,
      "step": 1150
    },
    {
      "epoch": 2.869511440940012,
      "grad_norm": 0.6756833035066511,
      "learning_rate": 5e-06,
      "loss": 0.4774,
      "step": 1160
    },
    {
      "epoch": 2.8942486085343226,
      "grad_norm": 0.6408060819703033,
      "learning_rate": 5e-06,
      "loss": 0.4762,
      "step": 1170
    },
    {
      "epoch": 2.9189857761286335,
      "grad_norm": 0.5130121997574635,
      "learning_rate": 5e-06,
      "loss": 0.4764,
      "step": 1180
    },
    {
      "epoch": 2.9437229437229435,
      "grad_norm": 0.5162312463500585,
      "learning_rate": 5e-06,
      "loss": 0.4777,
      "step": 1190
    },
    {
      "epoch": 2.9684601113172544,
      "grad_norm": 0.5924512448077986,
      "learning_rate": 5e-06,
      "loss": 0.4791,
      "step": 1200
    },
    {
      "epoch": 2.9931972789115644,
      "grad_norm": 0.502845968511808,
      "learning_rate": 5e-06,
      "loss": 0.4761,
      "step": 1210
    },
    {
      "epoch": 2.9981447124304266,
      "eval_loss": 0.537095308303833,
      "eval_runtime": 219.5171,
      "eval_samples_per_second": 49.618,
      "eval_steps_per_second": 0.392,
      "step": 1212
    },
    {
      "epoch": 2.9981447124304266,
      "step": 1212,
      "total_flos": 2029726382161920.0,
      "train_loss": 0.5400018749063952,
      "train_runtime": 36478.2162,
      "train_samples_per_second": 17.019,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 10,
  "max_steps": 1212,
  "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": 2029726382161920.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}