{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.996178343949045,
  "eval_steps": 500,
  "global_step": 1470,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02038216560509554,
      "grad_norm": 7.3640559222825805,
      "learning_rate": 6.756756756756758e-07,
      "loss": 0.5218,
      "step": 10
    },
    {
      "epoch": 0.04076433121019108,
      "grad_norm": 1.9597929093946138,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 0.4442,
      "step": 20
    },
    {
      "epoch": 0.061146496815286625,
      "grad_norm": 1.366556978476813,
      "learning_rate": 2.0270270270270273e-06,
      "loss": 0.3968,
      "step": 30
    },
    {
      "epoch": 0.08152866242038216,
      "grad_norm": 1.5343177845993703,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.3717,
      "step": 40
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": 1.5235479557468576,
      "learning_rate": 3.3783783783783788e-06,
      "loss": 0.3573,
      "step": 50
    },
    {
      "epoch": 0.12229299363057325,
      "grad_norm": 1.5210742465140967,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 0.3447,
      "step": 60
    },
    {
      "epoch": 0.14267515923566879,
      "grad_norm": 1.4560884271057324,
      "learning_rate": 4.72972972972973e-06,
      "loss": 0.336,
      "step": 70
    },
    {
      "epoch": 0.16305732484076432,
      "grad_norm": 1.3653484275359835,
      "learning_rate": 4.999794894487084e-06,
      "loss": 0.3285,
      "step": 80
    },
    {
      "epoch": 0.18343949044585986,
      "grad_norm": 1.5231339353031599,
      "learning_rate": 4.998541607324267e-06,
      "loss": 0.3226,
      "step": 90
    },
    {
      "epoch": 0.20382165605095542,
      "grad_norm": 1.34927340034923,
      "learning_rate": 4.996149614425655e-06,
      "loss": 0.3234,
      "step": 100
    },
    {
      "epoch": 0.22420382165605096,
      "grad_norm": 1.3383365926789343,
      "learning_rate": 4.992620127143546e-06,
      "loss": 0.3159,
      "step": 110
    },
    {
      "epoch": 0.2445859872611465,
      "grad_norm": 1.279507514764783,
      "learning_rate": 4.987954932879781e-06,
      "loss": 0.3155,
      "step": 120
    },
    {
      "epoch": 0.26496815286624203,
      "grad_norm": 1.2523662594214922,
      "learning_rate": 4.982156394180578e-06,
      "loss": 0.3089,
      "step": 130
    },
    {
      "epoch": 0.28535031847133757,
      "grad_norm": 1.5508610615211977,
      "learning_rate": 4.975227447540084e-06,
      "loss": 0.3081,
      "step": 140
    },
    {
      "epoch": 0.3057324840764331,
      "grad_norm": 1.5577467324922831,
      "learning_rate": 4.967171601913286e-06,
      "loss": 0.2999,
      "step": 150
    },
    {
      "epoch": 0.32611464968152865,
      "grad_norm": 1.4024580607747494,
      "learning_rate": 4.957992936939001e-06,
      "loss": 0.3014,
      "step": 160
    },
    {
      "epoch": 0.3464968152866242,
      "grad_norm": 1.397084384608207,
      "learning_rate": 4.947696100873868e-06,
      "loss": 0.3003,
      "step": 170
    },
    {
      "epoch": 0.3668789808917197,
      "grad_norm": 1.2608713430895078,
      "learning_rate": 4.936286308238376e-06,
      "loss": 0.2962,
      "step": 180
    },
    {
      "epoch": 0.3872611464968153,
      "grad_norm": 1.4602055977294606,
      "learning_rate": 4.923769337176137e-06,
      "loss": 0.2949,
      "step": 190
    },
    {
      "epoch": 0.40764331210191085,
      "grad_norm": 1.3574725912947458,
      "learning_rate": 4.910151526527711e-06,
      "loss": 0.2913,
      "step": 200
    },
    {
      "epoch": 0.4280254777070064,
      "grad_norm": 1.3255996037154008,
      "learning_rate": 4.895439772620496e-06,
      "loss": 0.2909,
      "step": 210
    },
    {
      "epoch": 0.4484076433121019,
      "grad_norm": 1.209522300925548,
      "learning_rate": 4.879641525776294e-06,
      "loss": 0.2874,
      "step": 220
    },
    {
      "epoch": 0.46878980891719746,
      "grad_norm": 1.3036670455198982,
      "learning_rate": 4.8627647865383185e-06,
      "loss": 0.2887,
      "step": 230
    },
    {
      "epoch": 0.489171974522293,
      "grad_norm": 1.4420527770171871,
      "learning_rate": 4.844818101619563e-06,
      "loss": 0.2893,
      "step": 240
    },
    {
      "epoch": 0.5095541401273885,
      "grad_norm": 1.5008539741569011,
      "learning_rate": 4.825810559574577e-06,
      "loss": 0.2831,
      "step": 250
    },
    {
      "epoch": 0.5299363057324841,
      "grad_norm": 1.1363685690254681,
      "learning_rate": 4.805751786196844e-06,
      "loss": 0.2781,
      "step": 260
    },
    {
      "epoch": 0.5503184713375796,
      "grad_norm": 1.3886569509043332,
      "learning_rate": 4.784651939644088e-06,
      "loss": 0.2812,
      "step": 270
    },
    {
      "epoch": 0.5707006369426751,
      "grad_norm": 1.208611174951388,
      "learning_rate": 4.762521705293985e-06,
      "loss": 0.2839,
      "step": 280
    },
    {
      "epoch": 0.5910828025477707,
      "grad_norm": 1.163584249987649,
      "learning_rate": 4.739372290332876e-06,
      "loss": 0.2772,
      "step": 290
    },
    {
      "epoch": 0.6114649681528662,
      "grad_norm": 1.2694569325884293,
      "learning_rate": 4.715215418080228e-06,
      "loss": 0.2774,
      "step": 300
    },
    {
      "epoch": 0.6318471337579618,
      "grad_norm": 1.1438695314175629,
      "learning_rate": 4.690063322051714e-06,
      "loss": 0.279,
      "step": 310
    },
    {
      "epoch": 0.6522292993630573,
      "grad_norm": 1.1455759975487239,
      "learning_rate": 4.6639287397639175e-06,
      "loss": 0.2762,
      "step": 320
    },
    {
      "epoch": 0.6726114649681528,
      "grad_norm": 1.44840804645582,
      "learning_rate": 4.636824906283807e-06,
      "loss": 0.2752,
      "step": 330
    },
    {
      "epoch": 0.6929936305732484,
      "grad_norm": 1.1318324006100882,
      "learning_rate": 4.608765547526235e-06,
      "loss": 0.2696,
      "step": 340
    },
    {
      "epoch": 0.7133757961783439,
      "grad_norm": 1.4105199522926484,
      "learning_rate": 4.5797648733028665e-06,
      "loss": 0.2714,
      "step": 350
    },
    {
      "epoch": 0.7337579617834394,
      "grad_norm": 1.1828019600051816,
      "learning_rate": 4.54983757012605e-06,
      "loss": 0.2675,
      "step": 360
    },
    {
      "epoch": 0.7541401273885351,
      "grad_norm": 1.1209568717673557,
      "learning_rate": 4.518998793771276e-06,
      "loss": 0.2698,
      "step": 370
    },
    {
      "epoch": 0.7745222929936306,
      "grad_norm": 1.3068840388262846,
      "learning_rate": 4.487264161601997e-06,
      "loss": 0.2666,
      "step": 380
    },
    {
      "epoch": 0.7949044585987262,
      "grad_norm": 1.40475775183392,
      "learning_rate": 4.454649744660687e-06,
      "loss": 0.2687,
      "step": 390
    },
    {
      "epoch": 0.8152866242038217,
      "grad_norm": 1.064147060517822,
      "learning_rate": 4.4211720595301474e-06,
      "loss": 0.2668,
      "step": 400
    },
    {
      "epoch": 0.8356687898089172,
      "grad_norm": 1.273665530555761,
      "learning_rate": 4.386848059969186e-06,
      "loss": 0.2655,
      "step": 410
    },
    {
      "epoch": 0.8560509554140128,
      "grad_norm": 1.2644936064921932,
      "learning_rate": 4.351695128326899e-06,
      "loss": 0.267,
      "step": 420
    },
    {
      "epoch": 0.8764331210191083,
      "grad_norm": 1.1524074004874778,
      "learning_rate": 4.315731066739907e-06,
      "loss": 0.2621,
      "step": 430
    },
    {
      "epoch": 0.8968152866242038,
      "grad_norm": 1.2734388359258864,
      "learning_rate": 4.278974088117002e-06,
      "loss": 0.2646,
      "step": 440
    },
    {
      "epoch": 0.9171974522292994,
      "grad_norm": 1.1535683141057886,
      "learning_rate": 4.241442806915776e-06,
      "loss": 0.2622,
      "step": 450
    },
    {
      "epoch": 0.9375796178343949,
      "grad_norm": 1.1270411566076795,
      "learning_rate": 4.203156229715885e-06,
      "loss": 0.2647,
      "step": 460
    },
    {
      "epoch": 0.9579617834394905,
      "grad_norm": 1.1492915594780593,
      "learning_rate": 4.164133745593752e-06,
      "loss": 0.2604,
      "step": 470
    },
    {
      "epoch": 0.978343949044586,
      "grad_norm": 1.1077787065388747,
      "learning_rate": 4.1243951163035515e-06,
      "loss": 0.2589,
      "step": 480
    },
    {
      "epoch": 0.9987261146496815,
      "grad_norm": 1.04425073531816,
      "learning_rate": 4.083960466269468e-06,
      "loss": 0.2567,
      "step": 490
    },
    {
      "epoch": 0.9987261146496815,
      "eval_loss": 0.032234665006399155,
      "eval_runtime": 329.9438,
      "eval_samples_per_second": 40.07,
      "eval_steps_per_second": 0.627,
      "step": 490
    },
    {
      "epoch": 1.019108280254777,
      "grad_norm": 1.4452926570009665,
      "learning_rate": 4.042850272394296e-06,
      "loss": 0.1917,
      "step": 500
    },
    {
      "epoch": 1.0394904458598726,
      "grad_norm": 1.1692376024393614,
      "learning_rate": 4.001085353689527e-06,
      "loss": 0.1828,
      "step": 510
    },
    {
      "epoch": 1.0598726114649681,
      "grad_norm": 1.2077457145616015,
      "learning_rate": 3.958686860732198e-06,
      "loss": 0.1823,
      "step": 520
    },
    {
      "epoch": 1.0802547770700637,
      "grad_norm": 1.1829681497737912,
      "learning_rate": 3.915676264953819e-06,
      "loss": 0.1824,
      "step": 530
    },
    {
      "epoch": 1.1006369426751592,
      "grad_norm": 1.212198809480288,
      "learning_rate": 3.8720753477668174e-06,
      "loss": 0.1835,
      "step": 540
    },
    {
      "epoch": 1.1210191082802548,
      "grad_norm": 1.4514789562338672,
      "learning_rate": 3.8279061895340065e-06,
      "loss": 0.1838,
      "step": 550
    },
    {
      "epoch": 1.1414012738853503,
      "grad_norm": 1.2292597073935565,
      "learning_rate": 3.783191158386649e-06,
      "loss": 0.1799,
      "step": 560
    },
    {
      "epoch": 1.1617834394904458,
      "grad_norm": 1.091816482106913,
      "learning_rate": 3.7379528988968004e-06,
      "loss": 0.1797,
      "step": 570
    },
    {
      "epoch": 1.1821656050955414,
      "grad_norm": 1.1348703066662176,
      "learning_rate": 3.6922143206096463e-06,
      "loss": 0.1814,
      "step": 580
    },
    {
      "epoch": 1.202547770700637,
      "grad_norm": 1.2696934307053864,
      "learning_rate": 3.645998586441664e-06,
      "loss": 0.1814,
      "step": 590
    },
    {
      "epoch": 1.2229299363057324,
      "grad_norm": 1.1409724326559059,
      "learning_rate": 3.5993291009504583e-06,
      "loss": 0.1828,
      "step": 600
    },
    {
      "epoch": 1.243312101910828,
      "grad_norm": 1.2402396526237325,
      "learning_rate": 3.5522294984822414e-06,
      "loss": 0.1842,
      "step": 610
    },
    {
      "epoch": 1.2636942675159235,
      "grad_norm": 1.289864855038617,
      "learning_rate": 3.504723631202927e-06,
      "loss": 0.1824,
      "step": 620
    },
    {
      "epoch": 1.284076433121019,
      "grad_norm": 1.1569779602515864,
      "learning_rate": 3.4568355570189293e-06,
      "loss": 0.1833,
      "step": 630
    },
    {
      "epoch": 1.3044585987261146,
      "grad_norm": 1.1664095681219364,
      "learning_rate": 3.4085895273937616e-06,
      "loss": 0.1822,
      "step": 640
    },
    {
      "epoch": 1.3248407643312101,
      "grad_norm": 1.1062062982676109,
      "learning_rate": 3.3600099750666186e-06,
      "loss": 0.1801,
      "step": 650
    },
    {
      "epoch": 1.3452229299363057,
      "grad_norm": 1.0870703803021455,
      "learning_rate": 3.3111215016791615e-06,
      "loss": 0.1811,
      "step": 660
    },
    {
      "epoch": 1.3656050955414012,
      "grad_norm": 1.070032061400707,
      "learning_rate": 3.2619488653167524e-06,
      "loss": 0.1816,
      "step": 670
    },
    {
      "epoch": 1.385987261146497,
      "grad_norm": 1.3367455282881715,
      "learning_rate": 3.2125169679704816e-06,
      "loss": 0.1813,
      "step": 680
    },
    {
      "epoch": 1.4063694267515925,
      "grad_norm": 1.187247916290702,
      "learning_rate": 3.1628508429263055e-06,
      "loss": 0.1779,
      "step": 690
    },
    {
      "epoch": 1.426751592356688,
      "grad_norm": 1.1091917590396907,
      "learning_rate": 3.112975642087696e-06,
      "loss": 0.1802,
      "step": 700
    },
    {
      "epoch": 1.4471337579617836,
      "grad_norm": 1.123698745710789,
      "learning_rate": 3.0629166232382244e-06,
      "loss": 0.1814,
      "step": 710
    },
    {
      "epoch": 1.467515923566879,
      "grad_norm": 1.1042223426325448,
      "learning_rate": 3.012699137250523e-06,
      "loss": 0.1824,
      "step": 720
    },
    {
      "epoch": 1.4878980891719746,
      "grad_norm": 1.050554441234522,
      "learning_rate": 2.962348615248099e-06,
      "loss": 0.1796,
      "step": 730
    },
    {
      "epoch": 1.5082802547770702,
      "grad_norm": 1.2199041359267095,
      "learning_rate": 2.9118905557265194e-06,
      "loss": 0.181,
      "step": 740
    },
    {
      "epoch": 1.5286624203821657,
      "grad_norm": 1.1808278399972332,
      "learning_rate": 2.861350511640466e-06,
      "loss": 0.1803,
      "step": 750
    },
    {
      "epoch": 1.5490445859872612,
      "grad_norm": 1.0852792148234631,
      "learning_rate": 2.81075407746322e-06,
      "loss": 0.1798,
      "step": 760
    },
    {
      "epoch": 1.5694267515923568,
      "grad_norm": 1.1397500179113436,
      "learning_rate": 2.760126876225113e-06,
      "loss": 0.1794,
      "step": 770
    },
    {
      "epoch": 1.5898089171974523,
      "grad_norm": 1.0868979078693752,
      "learning_rate": 2.7094945465375237e-06,
      "loss": 0.1784,
      "step": 780
    },
    {
      "epoch": 1.6101910828025479,
      "grad_norm": 1.185135837873844,
      "learning_rate": 2.6588827296089765e-06,
      "loss": 0.1796,
      "step": 790
    },
    {
      "epoch": 1.6305732484076434,
      "grad_norm": 1.0667742842947785,
      "learning_rate": 2.608317056259933e-06,
      "loss": 0.1778,
      "step": 800
    },
    {
      "epoch": 1.650955414012739,
      "grad_norm": 1.1263879048027836,
      "learning_rate": 2.557823133942836e-06,
      "loss": 0.1818,
      "step": 810
    },
    {
      "epoch": 1.6713375796178345,
      "grad_norm": 1.164600608354229,
      "learning_rate": 2.507426533773994e-06,
      "loss": 0.1818,
      "step": 820
    },
    {
      "epoch": 1.69171974522293,
      "grad_norm": 1.1434673428111148,
      "learning_rate": 2.4571527775838637e-06,
      "loss": 0.1785,
      "step": 830
    },
    {
      "epoch": 1.7121019108280255,
      "grad_norm": 1.1080982356818843,
      "learning_rate": 2.407027324992293e-06,
      "loss": 0.1767,
      "step": 840
    },
    {
      "epoch": 1.732484076433121,
      "grad_norm": 1.1236879328083964,
      "learning_rate": 2.357075560515267e-06,
      "loss": 0.1764,
      "step": 850
    },
    {
      "epoch": 1.7528662420382166,
      "grad_norm": 1.07775485257901,
      "learning_rate": 2.3073227807096903e-06,
      "loss": 0.1766,
      "step": 860
    },
    {
      "epoch": 1.7732484076433122,
      "grad_norm": 1.0978325229339359,
      "learning_rate": 2.2577941813627137e-06,
      "loss": 0.1776,
      "step": 870
    },
    {
      "epoch": 1.7936305732484077,
      "grad_norm": 1.0266269472342355,
      "learning_rate": 2.2085148447320886e-06,
      "loss": 0.1763,
      "step": 880
    },
    {
      "epoch": 1.8140127388535032,
      "grad_norm": 1.075781931859834,
      "learning_rate": 2.1595097268440215e-06,
      "loss": 0.1761,
      "step": 890
    },
    {
      "epoch": 1.8343949044585988,
      "grad_norm": 1.1486032295285624,
      "learning_rate": 2.110803644854949e-06,
      "loss": 0.1756,
      "step": 900
    },
    {
      "epoch": 1.8547770700636943,
      "grad_norm": 1.0561746481203738,
      "learning_rate": 2.062421264483641e-06,
      "loss": 0.1754,
      "step": 910
    },
    {
      "epoch": 1.8751592356687898,
      "grad_norm": 1.1673017813466813,
      "learning_rate": 2.0143870875199952e-06,
      "loss": 0.1764,
      "step": 920
    },
    {
      "epoch": 1.8955414012738854,
      "grad_norm": 1.1439217602579965,
      "learning_rate": 1.9667254394168497e-06,
      "loss": 0.1742,
      "step": 930
    },
    {
      "epoch": 1.915923566878981,
      "grad_norm": 1.1584206154770065,
      "learning_rate": 1.9194604569710933e-06,
      "loss": 0.1795,
      "step": 940
    },
    {
      "epoch": 1.9363057324840764,
      "grad_norm": 1.0480077245390713,
      "learning_rate": 1.8726160761003172e-06,
      "loss": 0.1748,
      "step": 950
    },
    {
      "epoch": 1.956687898089172,
      "grad_norm": 1.1162273428280736,
      "learning_rate": 1.8262160197211954e-06,
      "loss": 0.1761,
      "step": 960
    },
    {
      "epoch": 1.9770700636942675,
      "grad_norm": 1.1160462930422237,
      "learning_rate": 1.780283785735729e-06,
      "loss": 0.174,
      "step": 970
    },
    {
      "epoch": 1.997452229299363,
      "grad_norm": 1.062423344058906,
      "learning_rate": 1.734842635131455e-06,
      "loss": 0.1749,
      "step": 980
    },
    {
      "epoch": 1.9994904458598726,
      "eval_loss": 0.030678020790219307,
      "eval_runtime": 338.9213,
      "eval_samples_per_second": 39.009,
      "eval_steps_per_second": 0.611,
      "step": 981
    },
    {
      "epoch": 2.0178343949044586,
      "grad_norm": 1.4150638555592978,
      "learning_rate": 1.689915580201614e-06,
      "loss": 0.1179,
      "step": 990
    },
    {
      "epoch": 2.038216560509554,
      "grad_norm": 1.230931823658668,
      "learning_rate": 1.6455253728912765e-06,
      "loss": 0.106,
      "step": 1000
    },
    {
      "epoch": 2.0585987261146497,
      "grad_norm": 1.078514779623916,
      "learning_rate": 1.6016944932753123e-06,
      "loss": 0.1055,
      "step": 1010
    },
    {
      "epoch": 2.078980891719745,
      "grad_norm": 1.1594743845163793,
      "learning_rate": 1.558445138174033e-06,
      "loss": 0.1068,
      "step": 1020
    },
    {
      "epoch": 2.0993630573248407,
      "grad_norm": 1.1071569450433687,
      "learning_rate": 1.5157992099122896e-06,
      "loss": 0.1061,
      "step": 1030
    },
    {
      "epoch": 2.1197452229299363,
      "grad_norm": 1.1427254217014393,
      "learning_rate": 1.4737783052277017e-06,
      "loss": 0.1054,
      "step": 1040
    },
    {
      "epoch": 2.140127388535032,
      "grad_norm": 1.1862335656291514,
      "learning_rate": 1.432403704333643e-06,
      "loss": 0.1056,
      "step": 1050
    },
    {
      "epoch": 2.1605095541401274,
      "grad_norm": 1.1251247878141808,
      "learning_rate": 1.3916963601425293e-06,
      "loss": 0.1058,
      "step": 1060
    },
    {
      "epoch": 2.180891719745223,
      "grad_norm": 1.1084298272819255,
      "learning_rate": 1.3516768876548404e-06,
      "loss": 0.1068,
      "step": 1070
    },
    {
      "epoch": 2.2012738853503184,
      "grad_norm": 1.1823405832071576,
      "learning_rate": 1.3123655535192873e-06,
      "loss": 0.1059,
      "step": 1080
    },
    {
      "epoch": 2.221656050955414,
      "grad_norm": 1.1309238431972,
      "learning_rate": 1.2737822657693763e-06,
      "loss": 0.106,
      "step": 1090
    },
    {
      "epoch": 2.2420382165605095,
      "grad_norm": 1.1830449008249062,
      "learning_rate": 1.235946563741594e-06,
      "loss": 0.106,
      "step": 1100
    },
    {
      "epoch": 2.262420382165605,
      "grad_norm": 1.1465025990749025,
      "learning_rate": 1.1988776081802975e-06,
      "loss": 0.1049,
      "step": 1110
    },
    {
      "epoch": 2.2828025477707006,
      "grad_norm": 1.183957689341336,
      "learning_rate": 1.1625941715343404e-06,
      "loss": 0.1054,
      "step": 1120
    },
    {
      "epoch": 2.303184713375796,
      "grad_norm": 1.1333744410647408,
      "learning_rate": 1.1271146284503326e-06,
      "loss": 0.1055,
      "step": 1130
    },
    {
      "epoch": 2.3235668789808916,
      "grad_norm": 1.1879433920175209,
      "learning_rate": 1.0924569464673593e-06,
      "loss": 0.1055,
      "step": 1140
    },
    {
      "epoch": 2.343949044585987,
      "grad_norm": 1.146900632019417,
      "learning_rate": 1.0586386769178644e-06,
      "loss": 0.106,
      "step": 1150
    },
    {
      "epoch": 2.3643312101910827,
      "grad_norm": 1.132036422681508,
      "learning_rate": 1.0256769460393087e-06,
      "loss": 0.1056,
      "step": 1160
    },
    {
      "epoch": 2.3847133757961783,
      "grad_norm": 1.0853627031360338,
      "learning_rate": 9.935884463011108e-07,
      "loss": 0.1045,
      "step": 1170
    },
    {
      "epoch": 2.405095541401274,
      "grad_norm": 1.1322288498135122,
      "learning_rate": 9.623894279512455e-07,
      "loss": 0.1054,
      "step": 1180
    },
    {
      "epoch": 2.4254777070063693,
      "grad_norm": 1.0894698960326725,
      "learning_rate": 9.320956907868051e-07,
      "loss": 0.1056,
      "step": 1190
    },
    {
      "epoch": 2.445859872611465,
      "grad_norm": 1.1474536034439595,
      "learning_rate": 9.027225761526653e-07,
      "loss": 0.1043,
      "step": 1200
    },
    {
      "epoch": 2.4662420382165604,
      "grad_norm": 1.1143668115183167,
      "learning_rate": 8.742849591723315e-07,
      "loss": 0.1065,
      "step": 1210
    },
    {
      "epoch": 2.486624203821656,
      "grad_norm": 1.1060933833835738,
      "learning_rate": 8.467972412148767e-07,
      "loss": 0.1049,
      "step": 1220
    },
    {
      "epoch": 2.5070063694267515,
      "grad_norm": 1.1258549382443122,
      "learning_rate": 8.202733426018117e-07,
      "loss": 0.1039,
      "step": 1230
    },
    {
      "epoch": 2.527388535031847,
      "grad_norm": 1.1747748534183018,
      "learning_rate": 7.947266955575562e-07,
      "loss": 0.1061,
      "step": 1240
    },
    {
      "epoch": 2.5477707006369426,
      "grad_norm": 1.1215150862371803,
      "learning_rate": 7.701702374070962e-07,
      "loss": 0.1054,
      "step": 1250
    },
    {
      "epoch": 2.568152866242038,
      "grad_norm": 1.1567778163976754,
      "learning_rate": 7.466164040242694e-07,
      "loss": 0.104,
      "step": 1260
    },
    {
      "epoch": 2.5885350318471336,
      "grad_norm": 1.1338966482025068,
      "learning_rate": 7.24077123533992e-07,
      "loss": 0.1048,
      "step": 1270
    },
    {
      "epoch": 2.608917197452229,
      "grad_norm": 1.0699364001483016,
      "learning_rate": 7.025638102716238e-07,
      "loss": 0.1046,
      "step": 1280
    },
    {
      "epoch": 2.6292993630573247,
      "grad_norm": 1.085055290267827,
      "learning_rate": 6.820873590025216e-07,
      "loss": 0.1042,
      "step": 1290
    },
    {
      "epoch": 2.6496815286624202,
      "grad_norm": 1.085099277831117,
      "learning_rate": 6.626581394047174e-07,
      "loss": 0.1043,
      "step": 1300
    },
    {
      "epoch": 2.6700636942675158,
      "grad_norm": 1.1741130632881172,
      "learning_rate": 6.442859908175084e-07,
      "loss": 0.1053,
      "step": 1310
    },
    {
      "epoch": 2.6904458598726113,
      "grad_norm": 1.086080275618794,
      "learning_rate": 6.269802172586215e-07,
      "loss": 0.1055,
      "step": 1320
    },
    {
      "epoch": 2.710828025477707,
      "grad_norm": 1.1054751783303671,
      "learning_rate": 6.107495827124764e-07,
      "loss": 0.1041,
      "step": 1330
    },
    {
      "epoch": 2.7312101910828024,
      "grad_norm": 1.0983120768210253,
      "learning_rate": 5.956023066919313e-07,
      "loss": 0.1026,
      "step": 1340
    },
    {
      "epoch": 2.7515923566878984,
      "grad_norm": 1.109557569000835,
      "learning_rate": 5.815460600757599e-07,
      "loss": 0.1037,
      "step": 1350
    },
    {
      "epoch": 2.771974522292994,
      "grad_norm": 1.1282912667207265,
      "learning_rate": 5.685879612239649e-07,
      "loss": 0.1057,
      "step": 1360
    },
    {
      "epoch": 2.7923566878980894,
      "grad_norm": 1.0863425429571905,
      "learning_rate": 5.567345723729062e-07,
      "loss": 0.1047,
      "step": 1370
    },
    {
      "epoch": 2.812738853503185,
      "grad_norm": 1.0546515835835897,
      "learning_rate": 5.459918963120477e-07,
      "loss": 0.1042,
      "step": 1380
    },
    {
      "epoch": 2.8331210191082805,
      "grad_norm": 1.0748377352085035,
      "learning_rate": 5.363653733440328e-07,
      "loss": 0.1057,
      "step": 1390
    },
    {
      "epoch": 2.853503184713376,
      "grad_norm": 1.0869969236098675,
      "learning_rate": 5.278598785296044e-07,
      "loss": 0.105,
      "step": 1400
    },
    {
      "epoch": 2.8738853503184716,
      "grad_norm": 1.0525214029938958,
      "learning_rate": 5.2047971921878e-07,
      "loss": 0.1039,
      "step": 1410
    },
    {
      "epoch": 2.894267515923567,
      "grad_norm": 1.0788702761102988,
      "learning_rate": 5.142286328695235e-07,
      "loss": 0.105,
      "step": 1420
    },
    {
      "epoch": 2.9146496815286627,
      "grad_norm": 1.0984819174990816,
      "learning_rate": 5.091097851550239e-07,
      "loss": 0.1032,
      "step": 1430
    },
    {
      "epoch": 2.935031847133758,
      "grad_norm": 1.072624641241873,
      "learning_rate": 5.051257683605363e-07,
      "loss": 0.1036,
      "step": 1440
    },
    {
      "epoch": 2.9554140127388537,
      "grad_norm": 1.116104824847335,
      "learning_rate": 5.022786000705963e-07,
      "loss": 0.1027,
      "step": 1450
    },
    {
      "epoch": 2.9757961783439493,
      "grad_norm": 1.0814921699434623,
      "learning_rate": 5.005697221472769e-07,
      "loss": 0.1029,
      "step": 1460
    },
    {
      "epoch": 2.996178343949045,
      "grad_norm": 1.0668548799222997,
      "learning_rate": 5e-07,
      "loss": 0.1027,
      "step": 1470
    },
    {
      "epoch": 2.996178343949045,
      "eval_loss": 0.03400026634335518,
      "eval_runtime": 335.9006,
      "eval_samples_per_second": 39.36,
      "eval_steps_per_second": 0.616,
      "step": 1470
    },
    {
      "epoch": 2.996178343949045,
      "step": 1470,
      "total_flos": 2462095371141120.0,
      "train_loss": 0.19492420712295844,
      "train_runtime": 47387.4935,
      "train_samples_per_second": 15.902,
      "train_steps_per_second": 0.031
    }
  ],
  "logging_steps": 10,
  "max_steps": 1470,
  "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": 2462095371141120.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}