{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004092034400369192,
  "eval_steps": 500,
  "global_step": 2250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.818681955719641e-05,
      "grad_norm": 1.608859896659851,
      "learning_rate": 0.0002,
      "loss": 3.3372,
      "step": 10
    },
    {
      "epoch": 3.637363911439282e-05,
      "grad_norm": 0.9594001770019531,
      "learning_rate": 0.0002,
      "loss": 0.1895,
      "step": 20
    },
    {
      "epoch": 5.4560458671589234e-05,
      "grad_norm": 0.7858404517173767,
      "learning_rate": 0.0002,
      "loss": 0.1819,
      "step": 30
    },
    {
      "epoch": 7.274727822878565e-05,
      "grad_norm": 0.05236278474330902,
      "learning_rate": 0.0002,
      "loss": 0.0967,
      "step": 40
    },
    {
      "epoch": 9.093409778598205e-05,
      "grad_norm": 0.00239331996999681,
      "learning_rate": 0.0002,
      "loss": 0.0001,
      "step": 50
    },
    {
      "epoch": 0.00010912091734317847,
      "grad_norm": 0.6015797853469849,
      "learning_rate": 0.0002,
      "loss": 0.9137,
      "step": 60
    },
    {
      "epoch": 0.00012730773690037487,
      "grad_norm": 0.2916141152381897,
      "learning_rate": 0.0002,
      "loss": 0.1584,
      "step": 70
    },
    {
      "epoch": 0.0001454945564575713,
      "grad_norm": 0.22034427523612976,
      "learning_rate": 0.0002,
      "loss": 0.1212,
      "step": 80
    },
    {
      "epoch": 0.0001636813760147677,
      "grad_norm": 0.05342680215835571,
      "learning_rate": 0.0002,
      "loss": 0.0933,
      "step": 90
    },
    {
      "epoch": 0.0001818681955719641,
      "grad_norm": 0.0009122246992774308,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 100
    },
    {
      "epoch": 0.00020005501512916052,
      "grad_norm": 0.30845287442207336,
      "learning_rate": 0.0002,
      "loss": 0.8141,
      "step": 110
    },
    {
      "epoch": 0.00021824183468635694,
      "grad_norm": 0.1849660873413086,
      "learning_rate": 0.0002,
      "loss": 0.1604,
      "step": 120
    },
    {
      "epoch": 0.00023642865424355333,
      "grad_norm": 0.09605516493320465,
      "learning_rate": 0.0002,
      "loss": 0.1163,
      "step": 130
    },
    {
      "epoch": 0.00025461547380074975,
      "grad_norm": 0.4438878893852234,
      "learning_rate": 0.0002,
      "loss": 0.1043,
      "step": 140
    },
    {
      "epoch": 0.00027280229335794617,
      "grad_norm": 0.0012718827929347754,
      "learning_rate": 0.0002,
      "loss": 0.0018,
      "step": 150
    },
    {
      "epoch": 0.0002909891129151426,
      "grad_norm": 0.19092628359794617,
      "learning_rate": 0.0002,
      "loss": 0.6226,
      "step": 160
    },
    {
      "epoch": 0.000309175932472339,
      "grad_norm": 0.04102358967065811,
      "learning_rate": 0.0002,
      "loss": 0.1575,
      "step": 170
    },
    {
      "epoch": 0.0003273627520295354,
      "grad_norm": 0.06057624891400337,
      "learning_rate": 0.0002,
      "loss": 0.1119,
      "step": 180
    },
    {
      "epoch": 0.0003455495715867318,
      "grad_norm": 0.13942261040210724,
      "learning_rate": 0.0002,
      "loss": 0.0781,
      "step": 190
    },
    {
      "epoch": 0.0003637363911439282,
      "grad_norm": 0.005650315433740616,
      "learning_rate": 0.0002,
      "loss": 0.0013,
      "step": 200
    },
    {
      "epoch": 0.0003819232107011246,
      "grad_norm": 0.6245204210281372,
      "learning_rate": 0.0002,
      "loss": 0.7091,
      "step": 210
    },
    {
      "epoch": 0.00040011003025832104,
      "grad_norm": 0.058550119400024414,
      "learning_rate": 0.0002,
      "loss": 0.1411,
      "step": 220
    },
    {
      "epoch": 0.00041829684981551746,
      "grad_norm": 0.08625461906194687,
      "learning_rate": 0.0002,
      "loss": 0.1138,
      "step": 230
    },
    {
      "epoch": 0.0004364836693727139,
      "grad_norm": 0.06455521285533905,
      "learning_rate": 0.0002,
      "loss": 0.0805,
      "step": 240
    },
    {
      "epoch": 0.0004546704889299103,
      "grad_norm": 0.0020822149235755205,
      "learning_rate": 0.0002,
      "loss": 0.0013,
      "step": 250
    },
    {
      "epoch": 0.00047285730848710666,
      "grad_norm": 0.1977258324623108,
      "learning_rate": 0.0002,
      "loss": 0.5558,
      "step": 260
    },
    {
      "epoch": 0.0004910441280443031,
      "grad_norm": 0.20794034004211426,
      "learning_rate": 0.0002,
      "loss": 0.1263,
      "step": 270
    },
    {
      "epoch": 0.0005092309476014995,
      "grad_norm": 0.08760973066091537,
      "learning_rate": 0.0002,
      "loss": 0.1118,
      "step": 280
    },
    {
      "epoch": 0.0005274177671586959,
      "grad_norm": 0.299059122800827,
      "learning_rate": 0.0002,
      "loss": 0.0804,
      "step": 290
    },
    {
      "epoch": 0.0005456045867158923,
      "grad_norm": 0.002420844743028283,
      "learning_rate": 0.0002,
      "loss": 0.0022,
      "step": 300
    },
    {
      "epoch": 0.0005637914062730887,
      "grad_norm": 2.2061026096343994,
      "learning_rate": 0.0002,
      "loss": 0.5624,
      "step": 310
    },
    {
      "epoch": 0.0005819782258302852,
      "grad_norm": 0.7011717557907104,
      "learning_rate": 0.0002,
      "loss": 0.1177,
      "step": 320
    },
    {
      "epoch": 0.0006001650453874816,
      "grad_norm": 0.37657421827316284,
      "learning_rate": 0.0002,
      "loss": 0.1005,
      "step": 330
    },
    {
      "epoch": 0.000618351864944678,
      "grad_norm": 0.048011403530836105,
      "learning_rate": 0.0002,
      "loss": 0.079,
      "step": 340
    },
    {
      "epoch": 0.0006365386845018744,
      "grad_norm": 0.002076848642900586,
      "learning_rate": 0.0002,
      "loss": 0.0018,
      "step": 350
    },
    {
      "epoch": 0.0006547255040590708,
      "grad_norm": 0.721218466758728,
      "learning_rate": 0.0002,
      "loss": 0.5647,
      "step": 360
    },
    {
      "epoch": 0.0006729123236162671,
      "grad_norm": 0.09965512156486511,
      "learning_rate": 0.0002,
      "loss": 0.1403,
      "step": 370
    },
    {
      "epoch": 0.0006910991431734636,
      "grad_norm": 0.21733985841274261,
      "learning_rate": 0.0002,
      "loss": 0.1024,
      "step": 380
    },
    {
      "epoch": 0.00070928596273066,
      "grad_norm": 0.003134253202006221,
      "learning_rate": 0.0002,
      "loss": 0.0707,
      "step": 390
    },
    {
      "epoch": 0.0007274727822878564,
      "grad_norm": 0.0011866611894220114,
      "learning_rate": 0.0002,
      "loss": 0.0003,
      "step": 400
    },
    {
      "epoch": 0.0007456596018450528,
      "grad_norm": 0.37573525309562683,
      "learning_rate": 0.0002,
      "loss": 0.6122,
      "step": 410
    },
    {
      "epoch": 0.0007638464214022492,
      "grad_norm": 0.34029653668403625,
      "learning_rate": 0.0002,
      "loss": 0.1149,
      "step": 420
    },
    {
      "epoch": 0.0007820332409594457,
      "grad_norm": 0.35701191425323486,
      "learning_rate": 0.0002,
      "loss": 0.0972,
      "step": 430
    },
    {
      "epoch": 0.0008002200605166421,
      "grad_norm": 0.06324547529220581,
      "learning_rate": 0.0002,
      "loss": 0.0722,
      "step": 440
    },
    {
      "epoch": 0.0008184068800738385,
      "grad_norm": 0.0011920438846573234,
      "learning_rate": 0.0002,
      "loss": 0.0011,
      "step": 450
    },
    {
      "epoch": 0.0008365936996310349,
      "grad_norm": 0.861393392086029,
      "learning_rate": 0.0002,
      "loss": 0.4433,
      "step": 460
    },
    {
      "epoch": 0.0008547805191882313,
      "grad_norm": 0.16104361414909363,
      "learning_rate": 0.0002,
      "loss": 0.1176,
      "step": 470
    },
    {
      "epoch": 0.0008729673387454278,
      "grad_norm": 0.28712376952171326,
      "learning_rate": 0.0002,
      "loss": 0.0983,
      "step": 480
    },
    {
      "epoch": 0.0008911541583026242,
      "grad_norm": 0.07980292290449142,
      "learning_rate": 0.0002,
      "loss": 0.0721,
      "step": 490
    },
    {
      "epoch": 0.0009093409778598206,
      "grad_norm": 0.0018368292367085814,
      "learning_rate": 0.0002,
      "loss": 0.0019,
      "step": 500
    },
    {
      "epoch": 0.000927527797417017,
      "grad_norm": 0.05152284353971481,
      "learning_rate": 0.0002,
      "loss": 0.2823,
      "step": 510
    },
    {
      "epoch": 0.0009457146169742133,
      "grad_norm": 0.04693318158388138,
      "learning_rate": 0.0002,
      "loss": 0.1179,
      "step": 520
    },
    {
      "epoch": 0.0009639014365314097,
      "grad_norm": 0.10586889833211899,
      "learning_rate": 0.0002,
      "loss": 0.1094,
      "step": 530
    },
    {
      "epoch": 0.0009820882560886062,
      "grad_norm": 0.006325385998934507,
      "learning_rate": 0.0002,
      "loss": 0.0706,
      "step": 540
    },
    {
      "epoch": 0.0010002750756458027,
      "grad_norm": 4.665973028750159e-05,
      "learning_rate": 0.0002,
      "loss": 0.0002,
      "step": 550
    },
    {
      "epoch": 0.001018461895202999,
      "grad_norm": 0.293944776058197,
      "learning_rate": 0.0002,
      "loss": 0.732,
      "step": 560
    },
    {
      "epoch": 0.0010366487147601955,
      "grad_norm": 0.22614754736423492,
      "learning_rate": 0.0002,
      "loss": 0.1226,
      "step": 570
    },
    {
      "epoch": 0.0010548355343173918,
      "grad_norm": 0.10801248252391815,
      "learning_rate": 0.0002,
      "loss": 0.1065,
      "step": 580
    },
    {
      "epoch": 0.0010730223538745881,
      "grad_norm": 0.04501640051603317,
      "learning_rate": 0.0002,
      "loss": 0.0759,
      "step": 590
    },
    {
      "epoch": 0.0010912091734317847,
      "grad_norm": 0.00014656950952485204,
      "learning_rate": 0.0002,
      "loss": 0.0001,
      "step": 600
    },
    {
      "epoch": 0.001109395992988981,
      "grad_norm": 0.2490423321723938,
      "learning_rate": 0.0002,
      "loss": 0.4868,
      "step": 610
    },
    {
      "epoch": 0.0011275828125461775,
      "grad_norm": 0.026224857196211815,
      "learning_rate": 0.0002,
      "loss": 0.1242,
      "step": 620
    },
    {
      "epoch": 0.0011457696321033738,
      "grad_norm": 0.11845973134040833,
      "learning_rate": 0.0002,
      "loss": 0.1153,
      "step": 630
    },
    {
      "epoch": 0.0011639564516605703,
      "grad_norm": 0.8349707722663879,
      "learning_rate": 0.0002,
      "loss": 0.1229,
      "step": 640
    },
    {
      "epoch": 0.0011821432712177666,
      "grad_norm": 0.00733955716714263,
      "learning_rate": 0.0002,
      "loss": 0.0016,
      "step": 650
    },
    {
      "epoch": 0.0012003300907749632,
      "grad_norm": 0.3534531891345978,
      "learning_rate": 0.0002,
      "loss": 0.4961,
      "step": 660
    },
    {
      "epoch": 0.0012185169103321595,
      "grad_norm": 0.3938736915588379,
      "learning_rate": 0.0002,
      "loss": 0.126,
      "step": 670
    },
    {
      "epoch": 0.001236703729889356,
      "grad_norm": 0.16779105365276337,
      "learning_rate": 0.0002,
      "loss": 0.1217,
      "step": 680
    },
    {
      "epoch": 0.0012548905494465523,
      "grad_norm": 0.6998353600502014,
      "learning_rate": 0.0002,
      "loss": 0.1171,
      "step": 690
    },
    {
      "epoch": 0.0012730773690037488,
      "grad_norm": 0.0005113715888001025,
      "learning_rate": 0.0002,
      "loss": 0.0143,
      "step": 700
    },
    {
      "epoch": 0.0012912641885609452,
      "grad_norm": 0.4034057557582855,
      "learning_rate": 0.0002,
      "loss": 0.6274,
      "step": 710
    },
    {
      "epoch": 0.0013094510081181417,
      "grad_norm": 0.08985241502523422,
      "learning_rate": 0.0002,
      "loss": 0.1295,
      "step": 720
    },
    {
      "epoch": 0.001327637827675338,
      "grad_norm": 0.20418916642665863,
      "learning_rate": 0.0002,
      "loss": 0.1234,
      "step": 730
    },
    {
      "epoch": 0.0013458246472325343,
      "grad_norm": 1.0206961631774902,
      "learning_rate": 0.0002,
      "loss": 0.1107,
      "step": 740
    },
    {
      "epoch": 0.0013640114667897308,
      "grad_norm": 0.0008244478958658874,
      "learning_rate": 0.0002,
      "loss": 0.0087,
      "step": 750
    },
    {
      "epoch": 0.0013821982863469271,
      "grad_norm": 3.696362018585205,
      "learning_rate": 0.0002,
      "loss": 0.9078,
      "step": 760
    },
    {
      "epoch": 0.0014003851059041237,
      "grad_norm": 0.8782555460929871,
      "learning_rate": 0.0002,
      "loss": 0.1732,
      "step": 770
    },
    {
      "epoch": 0.00141857192546132,
      "grad_norm": 0.18350496888160706,
      "learning_rate": 0.0002,
      "loss": 0.1205,
      "step": 780
    },
    {
      "epoch": 0.0014367587450185165,
      "grad_norm": 0.634567141532898,
      "learning_rate": 0.0002,
      "loss": 0.0997,
      "step": 790
    },
    {
      "epoch": 0.0014549455645757128,
      "grad_norm": 0.01041293516755104,
      "learning_rate": 0.0002,
      "loss": 0.0065,
      "step": 800
    },
    {
      "epoch": 0.0014731323841329093,
      "grad_norm": 3.0739810466766357,
      "learning_rate": 0.0002,
      "loss": 0.7739,
      "step": 810
    },
    {
      "epoch": 0.0014913192036901056,
      "grad_norm": 0.4407779276371002,
      "learning_rate": 0.0002,
      "loss": 0.2848,
      "step": 820
    },
    {
      "epoch": 0.0015095060232473022,
      "grad_norm": 0.25743165612220764,
      "learning_rate": 0.0002,
      "loss": 0.1318,
      "step": 830
    },
    {
      "epoch": 0.0015276928428044985,
      "grad_norm": 2.0397753715515137,
      "learning_rate": 0.0002,
      "loss": 0.1385,
      "step": 840
    },
    {
      "epoch": 0.001545879662361695,
      "grad_norm": 0.060638878494501114,
      "learning_rate": 0.0002,
      "loss": 0.047,
      "step": 850
    },
    {
      "epoch": 0.0015640664819188913,
      "grad_norm": 2.5641930103302,
      "learning_rate": 0.0002,
      "loss": 0.5497,
      "step": 860
    },
    {
      "epoch": 0.0015822533014760878,
      "grad_norm": 0.9419782161712646,
      "learning_rate": 0.0002,
      "loss": 0.1626,
      "step": 870
    },
    {
      "epoch": 0.0016004401210332842,
      "grad_norm": 0.1152188628911972,
      "learning_rate": 0.0002,
      "loss": 0.1063,
      "step": 880
    },
    {
      "epoch": 0.0016186269405904805,
      "grad_norm": 0.6502537131309509,
      "learning_rate": 0.0002,
      "loss": 0.0871,
      "step": 890
    },
    {
      "epoch": 0.001636813760147677,
      "grad_norm": 0.023487605154514313,
      "learning_rate": 0.0002,
      "loss": 0.0094,
      "step": 900
    },
    {
      "epoch": 0.0016550005797048733,
      "grad_norm": 1.9080859422683716,
      "learning_rate": 0.0002,
      "loss": 0.5073,
      "step": 910
    },
    {
      "epoch": 0.0016731873992620698,
      "grad_norm": 0.44722509384155273,
      "learning_rate": 0.0002,
      "loss": 0.167,
      "step": 920
    },
    {
      "epoch": 0.0016913742188192661,
      "grad_norm": 0.24151289463043213,
      "learning_rate": 0.0002,
      "loss": 0.1237,
      "step": 930
    },
    {
      "epoch": 0.0017095610383764627,
      "grad_norm": 1.1394294500350952,
      "learning_rate": 0.0002,
      "loss": 0.1014,
      "step": 940
    },
    {
      "epoch": 0.001727747857933659,
      "grad_norm": 0.011057032272219658,
      "learning_rate": 0.0002,
      "loss": 0.0069,
      "step": 950
    },
    {
      "epoch": 0.0017459346774908555,
      "grad_norm": 4.32397985458374,
      "learning_rate": 0.0002,
      "loss": 0.7672,
      "step": 960
    },
    {
      "epoch": 0.0017641214970480518,
      "grad_norm": 0.9529788494110107,
      "learning_rate": 0.0002,
      "loss": 0.3286,
      "step": 970
    },
    {
      "epoch": 0.0017823083166052483,
      "grad_norm": 0.27676528692245483,
      "learning_rate": 0.0002,
      "loss": 0.126,
      "step": 980
    },
    {
      "epoch": 0.0018004951361624446,
      "grad_norm": 0.62413090467453,
      "learning_rate": 0.0002,
      "loss": 0.0844,
      "step": 990
    },
    {
      "epoch": 0.0018186819557196412,
      "grad_norm": 0.010768013074994087,
      "learning_rate": 0.0002,
      "loss": 0.0038,
      "step": 1000
    },
    {
      "epoch": 0.0018368687752768375,
      "grad_norm": 4.500253200531006,
      "learning_rate": 0.0002,
      "loss": 0.8415,
      "step": 1010
    },
    {
      "epoch": 0.001855055594834034,
      "grad_norm": 0.4661908447742462,
      "learning_rate": 0.0002,
      "loss": 0.2552,
      "step": 1020
    },
    {
      "epoch": 0.0018732424143912303,
      "grad_norm": 0.17337530851364136,
      "learning_rate": 0.0002,
      "loss": 0.1032,
      "step": 1030
    },
    {
      "epoch": 0.0018914292339484266,
      "grad_norm": 0.3994196355342865,
      "learning_rate": 0.0002,
      "loss": 0.0814,
      "step": 1040
    },
    {
      "epoch": 0.0019096160535056232,
      "grad_norm": 0.025604812428355217,
      "learning_rate": 0.0002,
      "loss": 0.0077,
      "step": 1050
    },
    {
      "epoch": 0.0019278028730628195,
      "grad_norm": 3.7293856143951416,
      "learning_rate": 0.0002,
      "loss": 0.6543,
      "step": 1060
    },
    {
      "epoch": 0.001945989692620016,
      "grad_norm": 1.2915587425231934,
      "learning_rate": 0.0002,
      "loss": 0.3782,
      "step": 1070
    },
    {
      "epoch": 0.0019641765121772123,
      "grad_norm": 1.0336438417434692,
      "learning_rate": 0.0002,
      "loss": 0.1515,
      "step": 1080
    },
    {
      "epoch": 0.0019823633317344086,
      "grad_norm": 1.6816803216934204,
      "learning_rate": 0.0002,
      "loss": 0.1173,
      "step": 1090
    },
    {
      "epoch": 0.0020005501512916054,
      "grad_norm": 0.015431606210768223,
      "learning_rate": 0.0002,
      "loss": 0.0165,
      "step": 1100
    },
    {
      "epoch": 0.0020187369708488017,
      "grad_norm": 3.059936046600342,
      "learning_rate": 0.0002,
      "loss": 0.6981,
      "step": 1110
    },
    {
      "epoch": 0.002036923790405998,
      "grad_norm": 0.5564419031143188,
      "learning_rate": 0.0002,
      "loss": 0.2193,
      "step": 1120
    },
    {
      "epoch": 0.0020551106099631943,
      "grad_norm": 0.11465179920196533,
      "learning_rate": 0.0002,
      "loss": 0.1157,
      "step": 1130
    },
    {
      "epoch": 0.002073297429520391,
      "grad_norm": 1.7084763050079346,
      "learning_rate": 0.0002,
      "loss": 0.0997,
      "step": 1140
    },
    {
      "epoch": 0.0020914842490775873,
      "grad_norm": 0.00997951254248619,
      "learning_rate": 0.0002,
      "loss": 0.0185,
      "step": 1150
    },
    {
      "epoch": 0.0021096710686347836,
      "grad_norm": 4.252767086029053,
      "learning_rate": 0.0002,
      "loss": 0.6719,
      "step": 1160
    },
    {
      "epoch": 0.00212785788819198,
      "grad_norm": 0.7261558175086975,
      "learning_rate": 0.0002,
      "loss": 0.1939,
      "step": 1170
    },
    {
      "epoch": 0.0021460447077491763,
      "grad_norm": 0.3190513253211975,
      "learning_rate": 0.0002,
      "loss": 0.0981,
      "step": 1180
    },
    {
      "epoch": 0.002164231527306373,
      "grad_norm": 0.5305098295211792,
      "learning_rate": 0.0002,
      "loss": 0.0756,
      "step": 1190
    },
    {
      "epoch": 0.0021824183468635693,
      "grad_norm": 0.03356161713600159,
      "learning_rate": 0.0002,
      "loss": 0.0064,
      "step": 1200
    },
    {
      "epoch": 0.0022006051664207656,
      "grad_norm": 3.8724617958068848,
      "learning_rate": 0.0002,
      "loss": 0.6282,
      "step": 1210
    },
    {
      "epoch": 0.002218791985977962,
      "grad_norm": 1.3044495582580566,
      "learning_rate": 0.0002,
      "loss": 0.3827,
      "step": 1220
    },
    {
      "epoch": 0.0022369788055351587,
      "grad_norm": 0.18937312066555023,
      "learning_rate": 0.0002,
      "loss": 0.1412,
      "step": 1230
    },
    {
      "epoch": 0.002255165625092355,
      "grad_norm": 2.488002061843872,
      "learning_rate": 0.0002,
      "loss": 0.1299,
      "step": 1240
    },
    {
      "epoch": 0.0022733524446495513,
      "grad_norm": 0.05979600548744202,
      "learning_rate": 0.0002,
      "loss": 0.0276,
      "step": 1250
    },
    {
      "epoch": 0.0022915392642067476,
      "grad_norm": 4.089362144470215,
      "learning_rate": 0.0002,
      "loss": 0.6152,
      "step": 1260
    },
    {
      "epoch": 0.0023097260837639444,
      "grad_norm": 0.2717827260494232,
      "learning_rate": 0.0002,
      "loss": 0.277,
      "step": 1270
    },
    {
      "epoch": 0.0023279129033211407,
      "grad_norm": 0.40145063400268555,
      "learning_rate": 0.0002,
      "loss": 0.113,
      "step": 1280
    },
    {
      "epoch": 0.002346099722878337,
      "grad_norm": 0.8193599581718445,
      "learning_rate": 0.0002,
      "loss": 0.0952,
      "step": 1290
    },
    {
      "epoch": 0.0023642865424355333,
      "grad_norm": 0.03877554461359978,
      "learning_rate": 0.0002,
      "loss": 0.0187,
      "step": 1300
    },
    {
      "epoch": 0.00238247336199273,
      "grad_norm": 3.7022697925567627,
      "learning_rate": 0.0002,
      "loss": 0.6711,
      "step": 1310
    },
    {
      "epoch": 0.0024006601815499263,
      "grad_norm": 1.0773606300354004,
      "learning_rate": 0.0002,
      "loss": 0.3495,
      "step": 1320
    },
    {
      "epoch": 0.0024188470011071227,
      "grad_norm": 0.46499383449554443,
      "learning_rate": 0.0002,
      "loss": 0.1181,
      "step": 1330
    },
    {
      "epoch": 0.002437033820664319,
      "grad_norm": 0.7035688757896423,
      "learning_rate": 0.0002,
      "loss": 0.08,
      "step": 1340
    },
    {
      "epoch": 0.0024552206402215153,
      "grad_norm": 0.022035669535398483,
      "learning_rate": 0.0002,
      "loss": 0.0102,
      "step": 1350
    },
    {
      "epoch": 0.002473407459778712,
      "grad_norm": 3.3636128902435303,
      "learning_rate": 0.0002,
      "loss": 0.6578,
      "step": 1360
    },
    {
      "epoch": 0.0024915942793359083,
      "grad_norm": 0.21912692487239838,
      "learning_rate": 0.0002,
      "loss": 0.2275,
      "step": 1370
    },
    {
      "epoch": 0.0025097810988931046,
      "grad_norm": 0.1632055938243866,
      "learning_rate": 0.0002,
      "loss": 0.1015,
      "step": 1380
    },
    {
      "epoch": 0.002527967918450301,
      "grad_norm": 0.44282346963882446,
      "learning_rate": 0.0002,
      "loss": 0.103,
      "step": 1390
    },
    {
      "epoch": 0.0025461547380074977,
      "grad_norm": 0.17366968095302582,
      "learning_rate": 0.0002,
      "loss": 0.0322,
      "step": 1400
    },
    {
      "epoch": 0.002564341557564694,
      "grad_norm": 1.816606879234314,
      "learning_rate": 0.0002,
      "loss": 0.3914,
      "step": 1410
    },
    {
      "epoch": 0.0025825283771218903,
      "grad_norm": 0.6741718649864197,
      "learning_rate": 0.0002,
      "loss": 0.2593,
      "step": 1420
    },
    {
      "epoch": 0.0026007151966790866,
      "grad_norm": 0.580172598361969,
      "learning_rate": 0.0002,
      "loss": 0.151,
      "step": 1430
    },
    {
      "epoch": 0.0026189020162362834,
      "grad_norm": 1.500544548034668,
      "learning_rate": 0.0002,
      "loss": 0.1266,
      "step": 1440
    },
    {
      "epoch": 0.0026370888357934797,
      "grad_norm": 0.03482064977288246,
      "learning_rate": 0.0002,
      "loss": 0.0209,
      "step": 1450
    },
    {
      "epoch": 0.002655275655350676,
      "grad_norm": 1.9266266822814941,
      "learning_rate": 0.0002,
      "loss": 0.5335,
      "step": 1460
    },
    {
      "epoch": 0.0026734624749078723,
      "grad_norm": 0.6076328158378601,
      "learning_rate": 0.0002,
      "loss": 0.1771,
      "step": 1470
    },
    {
      "epoch": 0.0026916492944650686,
      "grad_norm": 0.047803062945604324,
      "learning_rate": 0.0002,
      "loss": 0.1312,
      "step": 1480
    },
    {
      "epoch": 0.0027098361140222653,
      "grad_norm": 2.2670884132385254,
      "learning_rate": 0.0002,
      "loss": 0.1303,
      "step": 1490
    },
    {
      "epoch": 0.0027280229335794617,
      "grad_norm": 0.4342607259750366,
      "learning_rate": 0.0002,
      "loss": 0.0709,
      "step": 1500
    },
    {
      "epoch": 0.002746209753136658,
      "grad_norm": 1.5955005884170532,
      "learning_rate": 0.0002,
      "loss": 0.2632,
      "step": 1510
    },
    {
      "epoch": 0.0027643965726938543,
      "grad_norm": 0.20393006503582,
      "learning_rate": 0.0002,
      "loss": 0.1324,
      "step": 1520
    },
    {
      "epoch": 0.002782583392251051,
      "grad_norm": 0.2312391996383667,
      "learning_rate": 0.0002,
      "loss": 0.1056,
      "step": 1530
    },
    {
      "epoch": 0.0028007702118082473,
      "grad_norm": 1.2107295989990234,
      "learning_rate": 0.0002,
      "loss": 0.1038,
      "step": 1540
    },
    {
      "epoch": 0.0028189570313654436,
      "grad_norm": 0.07030847668647766,
      "learning_rate": 0.0002,
      "loss": 0.032,
      "step": 1550
    },
    {
      "epoch": 0.00283714385092264,
      "grad_norm": 3.563960552215576,
      "learning_rate": 0.0002,
      "loss": 0.5389,
      "step": 1560
    },
    {
      "epoch": 0.0028553306704798367,
      "grad_norm": 0.6965789794921875,
      "learning_rate": 0.0002,
      "loss": 0.2889,
      "step": 1570
    },
    {
      "epoch": 0.002873517490037033,
      "grad_norm": 0.5975427031517029,
      "learning_rate": 0.0002,
      "loss": 0.1235,
      "step": 1580
    },
    {
      "epoch": 0.0028917043095942293,
      "grad_norm": 1.371771216392517,
      "learning_rate": 0.0002,
      "loss": 0.0971,
      "step": 1590
    },
    {
      "epoch": 0.0029098911291514256,
      "grad_norm": 0.01906588114798069,
      "learning_rate": 0.0002,
      "loss": 0.0172,
      "step": 1600
    },
    {
      "epoch": 0.002928077948708622,
      "grad_norm": 3.8812315464019775,
      "learning_rate": 0.0002,
      "loss": 0.621,
      "step": 1610
    },
    {
      "epoch": 0.0029462647682658187,
      "grad_norm": 0.41589802503585815,
      "learning_rate": 0.0002,
      "loss": 0.2029,
      "step": 1620
    },
    {
      "epoch": 0.002964451587823015,
      "grad_norm": 0.24198026955127716,
      "learning_rate": 0.0002,
      "loss": 0.1042,
      "step": 1630
    },
    {
      "epoch": 0.0029826384073802113,
      "grad_norm": 0.8711221814155579,
      "learning_rate": 0.0002,
      "loss": 0.0904,
      "step": 1640
    },
    {
      "epoch": 0.0030008252269374076,
      "grad_norm": 0.06849978119134903,
      "learning_rate": 0.0002,
      "loss": 0.0226,
      "step": 1650
    },
    {
      "epoch": 0.0030190120464946043,
      "grad_norm": 3.912189483642578,
      "learning_rate": 0.0002,
      "loss": 0.5554,
      "step": 1660
    },
    {
      "epoch": 0.0030371988660518007,
      "grad_norm": 1.076832890510559,
      "learning_rate": 0.0002,
      "loss": 0.2968,
      "step": 1670
    },
    {
      "epoch": 0.003055385685608997,
      "grad_norm": 0.3734837472438812,
      "learning_rate": 0.0002,
      "loss": 0.1151,
      "step": 1680
    },
    {
      "epoch": 0.0030735725051661933,
      "grad_norm": 0.8407588005065918,
      "learning_rate": 0.0002,
      "loss": 0.0897,
      "step": 1690
    },
    {
      "epoch": 0.00309175932472339,
      "grad_norm": 0.023632407188415527,
      "learning_rate": 0.0002,
      "loss": 0.0113,
      "step": 1700
    },
    {
      "epoch": 0.0031099461442805863,
      "grad_norm": 4.268885612487793,
      "learning_rate": 0.0002,
      "loss": 0.6717,
      "step": 1710
    },
    {
      "epoch": 0.0031281329638377826,
      "grad_norm": 0.3088800013065338,
      "learning_rate": 0.0002,
      "loss": 0.2635,
      "step": 1720
    },
    {
      "epoch": 0.003146319783394979,
      "grad_norm": 0.05659230053424835,
      "learning_rate": 0.0002,
      "loss": 0.0987,
      "step": 1730
    },
    {
      "epoch": 0.0031645066029521757,
      "grad_norm": 0.5756633281707764,
      "learning_rate": 0.0002,
      "loss": 0.0949,
      "step": 1740
    },
    {
      "epoch": 0.003182693422509372,
      "grad_norm": 0.23241274058818817,
      "learning_rate": 0.0002,
      "loss": 0.044,
      "step": 1750
    },
    {
      "epoch": 0.0032008802420665683,
      "grad_norm": 2.2380006313323975,
      "learning_rate": 0.0002,
      "loss": 0.3458,
      "step": 1760
    },
    {
      "epoch": 0.0032190670616237646,
      "grad_norm": 0.4196106493473053,
      "learning_rate": 0.0002,
      "loss": 0.2116,
      "step": 1770
    },
    {
      "epoch": 0.003237253881180961,
      "grad_norm": 0.3544403612613678,
      "learning_rate": 0.0002,
      "loss": 0.1011,
      "step": 1780
    },
    {
      "epoch": 0.0032554407007381577,
      "grad_norm": 0.6422521471977234,
      "learning_rate": 0.0002,
      "loss": 0.084,
      "step": 1790
    },
    {
      "epoch": 0.003273627520295354,
      "grad_norm": 0.03676289692521095,
      "learning_rate": 0.0002,
      "loss": 0.0115,
      "step": 1800
    },
    {
      "epoch": 0.0032918143398525503,
      "grad_norm": 3.173424243927002,
      "learning_rate": 0.0002,
      "loss": 0.5644,
      "step": 1810
    },
    {
      "epoch": 0.0033100011594097466,
      "grad_norm": 0.14629468321800232,
      "learning_rate": 0.0002,
      "loss": 0.2249,
      "step": 1820
    },
    {
      "epoch": 0.0033281879789669433,
      "grad_norm": 0.27524232864379883,
      "learning_rate": 0.0002,
      "loss": 0.0965,
      "step": 1830
    },
    {
      "epoch": 0.0033463747985241397,
      "grad_norm": 0.5685613751411438,
      "learning_rate": 0.0002,
      "loss": 0.0949,
      "step": 1840
    },
    {
      "epoch": 0.003364561618081336,
      "grad_norm": 0.19684627652168274,
      "learning_rate": 0.0002,
      "loss": 0.0423,
      "step": 1850
    },
    {
      "epoch": 0.0033827484376385323,
      "grad_norm": 2.0270469188690186,
      "learning_rate": 0.0002,
      "loss": 0.3322,
      "step": 1860
    },
    {
      "epoch": 0.003400935257195729,
      "grad_norm": 0.3960348963737488,
      "learning_rate": 0.0002,
      "loss": 0.1933,
      "step": 1870
    },
    {
      "epoch": 0.0034191220767529253,
      "grad_norm": 0.8636507391929626,
      "learning_rate": 0.0002,
      "loss": 0.1056,
      "step": 1880
    },
    {
      "epoch": 0.0034373088963101216,
      "grad_norm": 0.7978588342666626,
      "learning_rate": 0.0002,
      "loss": 0.0812,
      "step": 1890
    },
    {
      "epoch": 0.003455495715867318,
      "grad_norm": 0.020584411919116974,
      "learning_rate": 0.0002,
      "loss": 0.0098,
      "step": 1900
    },
    {
      "epoch": 0.0034736825354245143,
      "grad_norm": 2.648928165435791,
      "learning_rate": 0.0002,
      "loss": 0.5485,
      "step": 1910
    },
    {
      "epoch": 0.003491869354981711,
      "grad_norm": 0.5433089137077332,
      "learning_rate": 0.0002,
      "loss": 0.1546,
      "step": 1920
    },
    {
      "epoch": 0.0035100561745389073,
      "grad_norm": 0.2638677656650543,
      "learning_rate": 0.0002,
      "loss": 0.0935,
      "step": 1930
    },
    {
      "epoch": 0.0035282429940961036,
      "grad_norm": 0.4292812943458557,
      "learning_rate": 0.0002,
      "loss": 0.0879,
      "step": 1940
    },
    {
      "epoch": 0.0035464298136533,
      "grad_norm": 0.09974557906389236,
      "learning_rate": 0.0002,
      "loss": 0.0234,
      "step": 1950
    },
    {
      "epoch": 0.0035646166332104967,
      "grad_norm": 1.626259446144104,
      "learning_rate": 0.0002,
      "loss": 0.4046,
      "step": 1960
    },
    {
      "epoch": 0.003582803452767693,
      "grad_norm": 0.7747110724449158,
      "learning_rate": 0.0002,
      "loss": 0.2436,
      "step": 1970
    },
    {
      "epoch": 0.0036009902723248893,
      "grad_norm": 1.130542516708374,
      "learning_rate": 0.0002,
      "loss": 0.1371,
      "step": 1980
    },
    {
      "epoch": 0.0036191770918820856,
      "grad_norm": 2.542160987854004,
      "learning_rate": 0.0002,
      "loss": 0.1204,
      "step": 1990
    },
    {
      "epoch": 0.0036373639114392823,
      "grad_norm": 0.1563112586736679,
      "learning_rate": 0.0002,
      "loss": 0.0343,
      "step": 2000
    },
    {
      "epoch": 0.0036555507309964787,
      "grad_norm": 3.1544902324676514,
      "learning_rate": 0.0002,
      "loss": 0.4769,
      "step": 2010
    },
    {
      "epoch": 0.003673737550553675,
      "grad_norm": 1.0212864875793457,
      "learning_rate": 0.0002,
      "loss": 0.2462,
      "step": 2020
    },
    {
      "epoch": 0.0036919243701108713,
      "grad_norm": 0.3565104305744171,
      "learning_rate": 0.0002,
      "loss": 0.1209,
      "step": 2030
    },
    {
      "epoch": 0.003710111189668068,
      "grad_norm": 1.3275020122528076,
      "learning_rate": 0.0002,
      "loss": 0.1064,
      "step": 2040
    },
    {
      "epoch": 0.0037282980092252643,
      "grad_norm": 0.11180760711431503,
      "learning_rate": 0.0002,
      "loss": 0.0326,
      "step": 2050
    },
    {
      "epoch": 0.0037464848287824606,
      "grad_norm": 1.9683802127838135,
      "learning_rate": 0.0002,
      "loss": 0.3878,
      "step": 2060
    },
    {
      "epoch": 0.003764671648339657,
      "grad_norm": 0.7875238060951233,
      "learning_rate": 0.0002,
      "loss": 0.1145,
      "step": 2070
    },
    {
      "epoch": 0.0037828584678968533,
      "grad_norm": 0.4307851195335388,
      "learning_rate": 0.0002,
      "loss": 0.0891,
      "step": 2080
    },
    {
      "epoch": 0.00380104528745405,
      "grad_norm": 0.6907076239585876,
      "learning_rate": 0.0002,
      "loss": 0.0801,
      "step": 2090
    },
    {
      "epoch": 0.0038192321070112463,
      "grad_norm": 0.04466943070292473,
      "learning_rate": 0.0002,
      "loss": 0.0148,
      "step": 2100
    },
    {
      "epoch": 0.0038374189265684426,
      "grad_norm": 2.8212766647338867,
      "learning_rate": 0.0002,
      "loss": 0.501,
      "step": 2110
    },
    {
      "epoch": 0.003855605746125639,
      "grad_norm": 0.4052332639694214,
      "learning_rate": 0.0002,
      "loss": 0.2379,
      "step": 2120
    },
    {
      "epoch": 0.0038737925656828357,
      "grad_norm": 0.5726248621940613,
      "learning_rate": 0.0002,
      "loss": 0.0925,
      "step": 2130
    },
    {
      "epoch": 0.003891979385240032,
      "grad_norm": 0.7385726571083069,
      "learning_rate": 0.0002,
      "loss": 0.0744,
      "step": 2140
    },
    {
      "epoch": 0.003910166204797228,
      "grad_norm": 0.01478211022913456,
      "learning_rate": 0.0002,
      "loss": 0.0094,
      "step": 2150
    },
    {
      "epoch": 0.003928353024354425,
      "grad_norm": 4.001941204071045,
      "learning_rate": 0.0002,
      "loss": 0.5398,
      "step": 2160
    },
    {
      "epoch": 0.003946539843911621,
      "grad_norm": 0.5501906275749207,
      "learning_rate": 0.0002,
      "loss": 0.1502,
      "step": 2170
    },
    {
      "epoch": 0.003964726663468817,
      "grad_norm": 0.05887573957443237,
      "learning_rate": 0.0002,
      "loss": 0.1137,
      "step": 2180
    },
    {
      "epoch": 0.003982913483026014,
      "grad_norm": 0.6087843179702759,
      "learning_rate": 0.0002,
      "loss": 0.0738,
      "step": 2190
    },
    {
      "epoch": 0.004001100302583211,
      "grad_norm": 0.027440447360277176,
      "learning_rate": 0.0002,
      "loss": 0.0122,
      "step": 2200
    },
    {
      "epoch": 0.004019287122140407,
      "grad_norm": 3.8189752101898193,
      "learning_rate": 0.0002,
      "loss": 0.5507,
      "step": 2210
    },
    {
      "epoch": 0.004037473941697603,
      "grad_norm": 0.7837066054344177,
      "learning_rate": 0.0002,
      "loss": 0.2931,
      "step": 2220
    },
    {
      "epoch": 0.0040556607612548,
      "grad_norm": 0.4113297462463379,
      "learning_rate": 0.0002,
      "loss": 0.1169,
      "step": 2230
    },
    {
      "epoch": 0.004073847580811996,
      "grad_norm": 0.9759702086448669,
      "learning_rate": 0.0002,
      "loss": 0.0902,
      "step": 2240
    },
    {
      "epoch": 0.004092034400369192,
      "grad_norm": 0.03002658113837242,
      "learning_rate": 0.0002,
      "loss": 0.0165,
      "step": 2250
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3899519044675994e+17,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}