{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13087658370313204,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006431281754453662,
      "grad_norm": 264.8507844691241,
      "learning_rate": 2.910112359550562e-06,
      "loss": 1.4924835205078124,
      "step": 10
    },
    {
      "epoch": 0.0012862563508907324,
      "grad_norm": 88.15687006273669,
      "learning_rate": 3.921348314606742e-06,
      "loss": 0.9952472686767578,
      "step": 20
    },
    {
      "epoch": 0.0019293845263360988,
      "grad_norm": 21.15530249818695,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.889136791229248,
      "step": 30
    },
    {
      "epoch": 0.002572512701781465,
      "grad_norm": 76.3435856512596,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.8875094413757324,
      "step": 40
    },
    {
      "epoch": 0.003215640877226831,
      "grad_norm": 112.76291878162131,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.8803050994873047,
      "step": 50
    },
    {
      "epoch": 0.0038587690526721975,
      "grad_norm": 63.07959530117864,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.8109166145324707,
      "step": 60
    },
    {
      "epoch": 0.004501897228117563,
      "grad_norm": 32.36448507808977,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.8291963577270508,
      "step": 70
    },
    {
      "epoch": 0.00514502540356293,
      "grad_norm": 39.66677708538367,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.8319297790527344,
      "step": 80
    },
    {
      "epoch": 0.005788153579008296,
      "grad_norm": 15.73002157903958,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.8473474502563476,
      "step": 90
    },
    {
      "epoch": 0.006431281754453662,
      "grad_norm": 29.04799205808129,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.9536348342895508,
      "step": 100
    },
    {
      "epoch": 0.007074409929899029,
      "grad_norm": 12.933556167568856,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.8515434265136719,
      "step": 110
    },
    {
      "epoch": 0.007717538105344395,
      "grad_norm": 13.216488664960004,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.8182208061218261,
      "step": 120
    },
    {
      "epoch": 0.008360666280789762,
      "grad_norm": 12.840168166981233,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.8101629257202149,
      "step": 130
    },
    {
      "epoch": 0.009003794456235127,
      "grad_norm": 16.647322053470525,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.7964733123779297,
      "step": 140
    },
    {
      "epoch": 0.009646922631680493,
      "grad_norm": 8.26209213346245,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.8133392333984375,
      "step": 150
    },
    {
      "epoch": 0.01029005080712586,
      "grad_norm": 103.09422370567049,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.8019628524780273,
      "step": 160
    },
    {
      "epoch": 0.010933178982571226,
      "grad_norm": 135.25179279143012,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.8667960166931152,
      "step": 170
    },
    {
      "epoch": 0.011576307158016592,
      "grad_norm": 9.266415446110027,
      "learning_rate": 2e-05,
      "loss": 0.927884292602539,
      "step": 180
    },
    {
      "epoch": 0.012219435333461958,
      "grad_norm": 19.616452125470513,
      "learning_rate": 2e-05,
      "loss": 0.9137126922607421,
      "step": 190
    },
    {
      "epoch": 0.012862563508907325,
      "grad_norm": 9.521484959449038,
      "learning_rate": 2e-05,
      "loss": 0.9231036186218262,
      "step": 200
    },
    {
      "epoch": 0.013505691684352691,
      "grad_norm": 3.841058878335388,
      "learning_rate": 2e-05,
      "loss": 0.880716609954834,
      "step": 210
    },
    {
      "epoch": 0.014148819859798057,
      "grad_norm": 3.716737538053141,
      "learning_rate": 2e-05,
      "loss": 0.8603705406188965,
      "step": 220
    },
    {
      "epoch": 0.014791948035243424,
      "grad_norm": 2.192635493713876,
      "learning_rate": 2e-05,
      "loss": 0.8351604461669921,
      "step": 230
    },
    {
      "epoch": 0.01543507621068879,
      "grad_norm": 5.677647000147936,
      "learning_rate": 2e-05,
      "loss": 0.8132261276245117,
      "step": 240
    },
    {
      "epoch": 0.016078204386134158,
      "grad_norm": 1.5356879007633566,
      "learning_rate": 2e-05,
      "loss": 0.8112307548522949,
      "step": 250
    },
    {
      "epoch": 0.016721332561579524,
      "grad_norm": 1.751089237236811,
      "learning_rate": 2e-05,
      "loss": 0.7884010314941406,
      "step": 260
    },
    {
      "epoch": 0.01736446073702489,
      "grad_norm": 3.480172236841913,
      "learning_rate": 2e-05,
      "loss": 0.7914746761322021,
      "step": 270
    },
    {
      "epoch": 0.018007588912470254,
      "grad_norm": 2.0628477216575267,
      "learning_rate": 2e-05,
      "loss": 0.8090205192565918,
      "step": 280
    },
    {
      "epoch": 0.01865071708791562,
      "grad_norm": 2.780990923043418,
      "learning_rate": 2e-05,
      "loss": 0.8231932640075683,
      "step": 290
    },
    {
      "epoch": 0.019293845263360986,
      "grad_norm": 5.662473120221767,
      "learning_rate": 2e-05,
      "loss": 0.8489857673645019,
      "step": 300
    },
    {
      "epoch": 0.019936973438806353,
      "grad_norm": 2.4856170219885727,
      "learning_rate": 2e-05,
      "loss": 0.8187873840332032,
      "step": 310
    },
    {
      "epoch": 0.02058010161425172,
      "grad_norm": 1.8272788861417755,
      "learning_rate": 2e-05,
      "loss": 0.8340753555297852,
      "step": 320
    },
    {
      "epoch": 0.021223229789697085,
      "grad_norm": 1.7623855646455684,
      "learning_rate": 2e-05,
      "loss": 0.7915143013000489,
      "step": 330
    },
    {
      "epoch": 0.02186635796514245,
      "grad_norm": 1.9529760399471496,
      "learning_rate": 2e-05,
      "loss": 0.806821632385254,
      "step": 340
    },
    {
      "epoch": 0.022509486140587818,
      "grad_norm": 3.908266701430372,
      "learning_rate": 2e-05,
      "loss": 0.7811341762542725,
      "step": 350
    },
    {
      "epoch": 0.023152614316033184,
      "grad_norm": 6.946061799441667,
      "learning_rate": 2e-05,
      "loss": 0.8082803726196289,
      "step": 360
    },
    {
      "epoch": 0.02379574249147855,
      "grad_norm": 4.948502227773737,
      "learning_rate": 2e-05,
      "loss": 0.8174592971801757,
      "step": 370
    },
    {
      "epoch": 0.024438870666923917,
      "grad_norm": 10.39411913582579,
      "learning_rate": 2e-05,
      "loss": 0.7916179180145264,
      "step": 380
    },
    {
      "epoch": 0.025081998842369283,
      "grad_norm": 2.157269114934209,
      "learning_rate": 2e-05,
      "loss": 0.8338122367858887,
      "step": 390
    },
    {
      "epoch": 0.02572512701781465,
      "grad_norm": 5.266447865073407,
      "learning_rate": 2e-05,
      "loss": 0.827884578704834,
      "step": 400
    },
    {
      "epoch": 0.026368255193260016,
      "grad_norm": 2.2186077419502372,
      "learning_rate": 2e-05,
      "loss": 0.811268424987793,
      "step": 410
    },
    {
      "epoch": 0.027011383368705382,
      "grad_norm": 3.8503522479510415,
      "learning_rate": 2e-05,
      "loss": 0.7956947326660156,
      "step": 420
    },
    {
      "epoch": 0.02765451154415075,
      "grad_norm": 4.682678958377554,
      "learning_rate": 2e-05,
      "loss": 0.823284912109375,
      "step": 430
    },
    {
      "epoch": 0.028297639719596115,
      "grad_norm": 16.1664579170008,
      "learning_rate": 2e-05,
      "loss": 0.790956974029541,
      "step": 440
    },
    {
      "epoch": 0.02894076789504148,
      "grad_norm": 9.145864327657529,
      "learning_rate": 2e-05,
      "loss": 0.8481451988220214,
      "step": 450
    },
    {
      "epoch": 0.029583896070486847,
      "grad_norm": 9.984067276500117,
      "learning_rate": 2e-05,
      "loss": 0.8152891159057617,
      "step": 460
    },
    {
      "epoch": 0.030227024245932214,
      "grad_norm": 7.200814844093958,
      "learning_rate": 2e-05,
      "loss": 0.8899850845336914,
      "step": 470
    },
    {
      "epoch": 0.03087015242137758,
      "grad_norm": 4.2706772329543154,
      "learning_rate": 2e-05,
      "loss": 0.874454402923584,
      "step": 480
    },
    {
      "epoch": 0.03151328059682295,
      "grad_norm": 1.8811353914333682,
      "learning_rate": 2e-05,
      "loss": 0.8309457778930665,
      "step": 490
    },
    {
      "epoch": 0.032156408772268316,
      "grad_norm": 3.6385280608953763,
      "learning_rate": 2e-05,
      "loss": 0.8326511383056641,
      "step": 500
    },
    {
      "epoch": 0.03279953694771368,
      "grad_norm": 1.3990140763602645,
      "learning_rate": 2e-05,
      "loss": 0.8103435516357422,
      "step": 510
    },
    {
      "epoch": 0.03344266512315905,
      "grad_norm": 2.9528430814571807,
      "learning_rate": 2e-05,
      "loss": 0.8075934410095215,
      "step": 520
    },
    {
      "epoch": 0.034085793298604415,
      "grad_norm": 1.7217483375429188,
      "learning_rate": 2e-05,
      "loss": 0.8287566184997559,
      "step": 530
    },
    {
      "epoch": 0.03472892147404978,
      "grad_norm": 5.998438084861422,
      "learning_rate": 2e-05,
      "loss": 0.8061090469360351,
      "step": 540
    },
    {
      "epoch": 0.03537204964949515,
      "grad_norm": 3.8694678808258725,
      "learning_rate": 2e-05,
      "loss": 0.8062751770019532,
      "step": 550
    },
    {
      "epoch": 0.03601517782494051,
      "grad_norm": 2.9933818726818253,
      "learning_rate": 2e-05,
      "loss": 0.7965433120727539,
      "step": 560
    },
    {
      "epoch": 0.036658306000385874,
      "grad_norm": 3.6993272754271627,
      "learning_rate": 2e-05,
      "loss": 0.8091463088989258,
      "step": 570
    },
    {
      "epoch": 0.03730143417583124,
      "grad_norm": 1.261375926095548,
      "learning_rate": 2e-05,
      "loss": 0.7848992824554444,
      "step": 580
    },
    {
      "epoch": 0.037944562351276606,
      "grad_norm": 1.2808782089307036,
      "learning_rate": 2e-05,
      "loss": 0.7949764251708984,
      "step": 590
    },
    {
      "epoch": 0.03858769052672197,
      "grad_norm": 1.5363171733181304,
      "learning_rate": 2e-05,
      "loss": 0.7794778347015381,
      "step": 600
    },
    {
      "epoch": 0.03923081870216734,
      "grad_norm": 1.692974926087992,
      "learning_rate": 2e-05,
      "loss": 0.7702068328857422,
      "step": 610
    },
    {
      "epoch": 0.039873946877612705,
      "grad_norm": 2.212928194205319,
      "learning_rate": 2e-05,
      "loss": 0.8085812568664551,
      "step": 620
    },
    {
      "epoch": 0.04051707505305807,
      "grad_norm": 1.2629369394284296,
      "learning_rate": 2e-05,
      "loss": 0.7806320190429688,
      "step": 630
    },
    {
      "epoch": 0.04116020322850344,
      "grad_norm": 1.3484483120225834,
      "learning_rate": 2e-05,
      "loss": 0.8086847305297852,
      "step": 640
    },
    {
      "epoch": 0.041803331403948804,
      "grad_norm": 3.702908463061738,
      "learning_rate": 2e-05,
      "loss": 0.7896449565887451,
      "step": 650
    },
    {
      "epoch": 0.04244645957939417,
      "grad_norm": 6.029659806191006,
      "learning_rate": 2e-05,
      "loss": 0.8226722717285156,
      "step": 660
    },
    {
      "epoch": 0.04308958775483954,
      "grad_norm": 7.370459449597133,
      "learning_rate": 2e-05,
      "loss": 0.7921708106994629,
      "step": 670
    },
    {
      "epoch": 0.0437327159302849,
      "grad_norm": 2.7983562630986714,
      "learning_rate": 2e-05,
      "loss": 0.7904531478881835,
      "step": 680
    },
    {
      "epoch": 0.04437584410573027,
      "grad_norm": 2.0098922533957477,
      "learning_rate": 2e-05,
      "loss": 0.7867809295654297,
      "step": 690
    },
    {
      "epoch": 0.045018972281175636,
      "grad_norm": 5.897837867051966,
      "learning_rate": 2e-05,
      "loss": 0.758472204208374,
      "step": 700
    },
    {
      "epoch": 0.045662100456621,
      "grad_norm": 3.7159389044440885,
      "learning_rate": 2e-05,
      "loss": 0.8133069992065429,
      "step": 710
    },
    {
      "epoch": 0.04630522863206637,
      "grad_norm": 2.906657663938742,
      "learning_rate": 2e-05,
      "loss": 0.7981234550476074,
      "step": 720
    },
    {
      "epoch": 0.046948356807511735,
      "grad_norm": 2.826396533617791,
      "learning_rate": 2e-05,
      "loss": 0.7824822902679444,
      "step": 730
    },
    {
      "epoch": 0.0475914849829571,
      "grad_norm": 2.164462884511523,
      "learning_rate": 2e-05,
      "loss": 0.7825541973114014,
      "step": 740
    },
    {
      "epoch": 0.04823461315840247,
      "grad_norm": 19.66583604658485,
      "learning_rate": 2e-05,
      "loss": 0.7757862091064454,
      "step": 750
    },
    {
      "epoch": 0.048877741333847834,
      "grad_norm": 1.6390436767603138,
      "learning_rate": 2e-05,
      "loss": 0.7854133605957031,
      "step": 760
    },
    {
      "epoch": 0.0495208695092932,
      "grad_norm": 4.120236130301234,
      "learning_rate": 2e-05,
      "loss": 0.7875580787658691,
      "step": 770
    },
    {
      "epoch": 0.050163997684738566,
      "grad_norm": 1.6380084823946195,
      "learning_rate": 2e-05,
      "loss": 0.7962754726409912,
      "step": 780
    },
    {
      "epoch": 0.05080712586018393,
      "grad_norm": 2.6234563124222348,
      "learning_rate": 2e-05,
      "loss": 0.787530517578125,
      "step": 790
    },
    {
      "epoch": 0.0514502540356293,
      "grad_norm": 4.114884694757611,
      "learning_rate": 2e-05,
      "loss": 0.805137825012207,
      "step": 800
    },
    {
      "epoch": 0.052093382211074665,
      "grad_norm": 2.170132077686732,
      "learning_rate": 2e-05,
      "loss": 0.8011256217956543,
      "step": 810
    },
    {
      "epoch": 0.05273651038652003,
      "grad_norm": 2.9542903597482884,
      "learning_rate": 2e-05,
      "loss": 0.7881402492523193,
      "step": 820
    },
    {
      "epoch": 0.0533796385619654,
      "grad_norm": 6.152172836766025,
      "learning_rate": 2e-05,
      "loss": 0.8165565490722656,
      "step": 830
    },
    {
      "epoch": 0.054022766737410764,
      "grad_norm": 2.6587595790131235,
      "learning_rate": 2e-05,
      "loss": 0.8002906799316406,
      "step": 840
    },
    {
      "epoch": 0.05466589491285613,
      "grad_norm": 15.727752869746313,
      "learning_rate": 2e-05,
      "loss": 0.7681012153625488,
      "step": 850
    },
    {
      "epoch": 0.0553090230883015,
      "grad_norm": 3.2974201088925668,
      "learning_rate": 2e-05,
      "loss": 0.7994019985198975,
      "step": 860
    },
    {
      "epoch": 0.05595215126374686,
      "grad_norm": 2.6425295630258514,
      "learning_rate": 2e-05,
      "loss": 0.8333459854125976,
      "step": 870
    },
    {
      "epoch": 0.05659527943919223,
      "grad_norm": 4.544009663459626,
      "learning_rate": 2e-05,
      "loss": 0.817692756652832,
      "step": 880
    },
    {
      "epoch": 0.057238407614637596,
      "grad_norm": 5.041701731508353,
      "learning_rate": 2e-05,
      "loss": 0.8127239227294922,
      "step": 890
    },
    {
      "epoch": 0.05788153579008296,
      "grad_norm": 14.446895711089793,
      "learning_rate": 2e-05,
      "loss": 0.7857817649841309,
      "step": 900
    },
    {
      "epoch": 0.05852466396552833,
      "grad_norm": 4.651863422153641,
      "learning_rate": 2e-05,
      "loss": 0.7850156307220459,
      "step": 910
    },
    {
      "epoch": 0.059167792140973695,
      "grad_norm": 13.407365054787249,
      "learning_rate": 2e-05,
      "loss": 0.7831117153167725,
      "step": 920
    },
    {
      "epoch": 0.05981092031641906,
      "grad_norm": 4.625228730773092,
      "learning_rate": 2e-05,
      "loss": 0.8246305465698243,
      "step": 930
    },
    {
      "epoch": 0.06045404849186443,
      "grad_norm": 2.6404931195979318,
      "learning_rate": 2e-05,
      "loss": 0.8151409149169921,
      "step": 940
    },
    {
      "epoch": 0.061097176667309794,
      "grad_norm": 2.8606521849156867,
      "learning_rate": 2e-05,
      "loss": 0.803957748413086,
      "step": 950
    },
    {
      "epoch": 0.06174030484275516,
      "grad_norm": 3.8845917481687176,
      "learning_rate": 2e-05,
      "loss": 0.7963566780090332,
      "step": 960
    },
    {
      "epoch": 0.062383433018200526,
      "grad_norm": 6.292344120130513,
      "learning_rate": 2e-05,
      "loss": 0.7799639701843262,
      "step": 970
    },
    {
      "epoch": 0.0630265611936459,
      "grad_norm": 3.7170800116374756,
      "learning_rate": 2e-05,
      "loss": 0.789764404296875,
      "step": 980
    },
    {
      "epoch": 0.06366968936909126,
      "grad_norm": 19.199030147508488,
      "learning_rate": 2e-05,
      "loss": 0.8285154342651367,
      "step": 990
    },
    {
      "epoch": 0.06431281754453663,
      "grad_norm": 3.928846417575705,
      "learning_rate": 2e-05,
      "loss": 0.8127799034118652,
      "step": 1000
    },
    {
      "epoch": 0.06495594571998199,
      "grad_norm": 3.755271687428537,
      "learning_rate": 2e-05,
      "loss": 0.8010581970214844,
      "step": 1010
    },
    {
      "epoch": 0.06559907389542736,
      "grad_norm": 2.913559778112332,
      "learning_rate": 2e-05,
      "loss": 0.7750132560729981,
      "step": 1020
    },
    {
      "epoch": 0.06624220207087272,
      "grad_norm": 10.071576934081813,
      "learning_rate": 2e-05,
      "loss": 0.7811709403991699,
      "step": 1030
    },
    {
      "epoch": 0.0668853302463181,
      "grad_norm": 3.587970695691555,
      "learning_rate": 2e-05,
      "loss": 0.7697386741638184,
      "step": 1040
    },
    {
      "epoch": 0.06752845842176346,
      "grad_norm": 1.862423666481207,
      "learning_rate": 2e-05,
      "loss": 0.7978693962097168,
      "step": 1050
    },
    {
      "epoch": 0.06817158659720883,
      "grad_norm": 2.9439913752393987,
      "learning_rate": 2e-05,
      "loss": 0.7703286647796631,
      "step": 1060
    },
    {
      "epoch": 0.06881471477265419,
      "grad_norm": 5.602785502496395,
      "learning_rate": 2e-05,
      "loss": 0.7832149505615235,
      "step": 1070
    },
    {
      "epoch": 0.06945784294809956,
      "grad_norm": 6.444227507124694,
      "learning_rate": 2e-05,
      "loss": 0.7846955776214599,
      "step": 1080
    },
    {
      "epoch": 0.07010097112354492,
      "grad_norm": 8.49026324059516,
      "learning_rate": 2e-05,
      "loss": 0.8015947341918945,
      "step": 1090
    },
    {
      "epoch": 0.0707440992989903,
      "grad_norm": 4.090223667504171,
      "learning_rate": 2e-05,
      "loss": 0.8186767578125,
      "step": 1100
    },
    {
      "epoch": 0.07138722747443565,
      "grad_norm": 2.7765862343897587,
      "learning_rate": 2e-05,
      "loss": 0.7696638107299805,
      "step": 1110
    },
    {
      "epoch": 0.07203035564988101,
      "grad_norm": 13.741738631565209,
      "learning_rate": 2e-05,
      "loss": 0.8072344779968261,
      "step": 1120
    },
    {
      "epoch": 0.07267348382532639,
      "grad_norm": 4.540314995023613,
      "learning_rate": 2e-05,
      "loss": 0.8362739562988282,
      "step": 1130
    },
    {
      "epoch": 0.07331661200077175,
      "grad_norm": 1.9835520642143039,
      "learning_rate": 2e-05,
      "loss": 0.7769340515136719,
      "step": 1140
    },
    {
      "epoch": 0.07395974017621712,
      "grad_norm": 11.174659008141319,
      "learning_rate": 2e-05,
      "loss": 0.7873312950134277,
      "step": 1150
    },
    {
      "epoch": 0.07460286835166248,
      "grad_norm": 35.01627971607914,
      "learning_rate": 2e-05,
      "loss": 0.8206969261169433,
      "step": 1160
    },
    {
      "epoch": 0.07524599652710785,
      "grad_norm": 2.8190948682505033,
      "learning_rate": 2e-05,
      "loss": 0.8351315498352051,
      "step": 1170
    },
    {
      "epoch": 0.07588912470255321,
      "grad_norm": 2.060661918032204,
      "learning_rate": 2e-05,
      "loss": 0.8220281600952148,
      "step": 1180
    },
    {
      "epoch": 0.07653225287799859,
      "grad_norm": 1.6772537547463753,
      "learning_rate": 2e-05,
      "loss": 0.7766014099121094,
      "step": 1190
    },
    {
      "epoch": 0.07717538105344394,
      "grad_norm": 1.7149818496545355,
      "learning_rate": 2e-05,
      "loss": 0.7847399711608887,
      "step": 1200
    },
    {
      "epoch": 0.07781850922888932,
      "grad_norm": 1.842032079580061,
      "learning_rate": 2e-05,
      "loss": 0.7880351543426514,
      "step": 1210
    },
    {
      "epoch": 0.07846163740433468,
      "grad_norm": 7.628369058899049,
      "learning_rate": 2e-05,
      "loss": 0.8086511611938476,
      "step": 1220
    },
    {
      "epoch": 0.07910476557978005,
      "grad_norm": 3.8447978426923006,
      "learning_rate": 2e-05,
      "loss": 0.7901057243347168,
      "step": 1230
    },
    {
      "epoch": 0.07974789375522541,
      "grad_norm": 5.063451031975492,
      "learning_rate": 2e-05,
      "loss": 0.783748197555542,
      "step": 1240
    },
    {
      "epoch": 0.08039102193067078,
      "grad_norm": 3.751566360170122,
      "learning_rate": 2e-05,
      "loss": 0.7723451614379883,
      "step": 1250
    },
    {
      "epoch": 0.08103415010611614,
      "grad_norm": 3.2156103176700626,
      "learning_rate": 2e-05,
      "loss": 0.7751105785369873,
      "step": 1260
    },
    {
      "epoch": 0.08167727828156152,
      "grad_norm": 2.6025577293652815,
      "learning_rate": 2e-05,
      "loss": 0.7603851318359375,
      "step": 1270
    },
    {
      "epoch": 0.08232040645700688,
      "grad_norm": 1.3919904079149132,
      "learning_rate": 2e-05,
      "loss": 0.7791646957397461,
      "step": 1280
    },
    {
      "epoch": 0.08296353463245225,
      "grad_norm": 1.672301310016778,
      "learning_rate": 2e-05,
      "loss": 0.7866832733154296,
      "step": 1290
    },
    {
      "epoch": 0.08360666280789761,
      "grad_norm": 1.7978359862977575,
      "learning_rate": 2e-05,
      "loss": 0.7824535369873047,
      "step": 1300
    },
    {
      "epoch": 0.08424979098334298,
      "grad_norm": 1.164265222279358,
      "learning_rate": 2e-05,
      "loss": 0.757862663269043,
      "step": 1310
    },
    {
      "epoch": 0.08489291915878834,
      "grad_norm": 6.39635222930186,
      "learning_rate": 2e-05,
      "loss": 0.7761935234069824,
      "step": 1320
    },
    {
      "epoch": 0.08553604733423371,
      "grad_norm": 1.5835398014458386,
      "learning_rate": 2e-05,
      "loss": 0.7623611450195312,
      "step": 1330
    },
    {
      "epoch": 0.08617917550967907,
      "grad_norm": 1.9528892284475325,
      "learning_rate": 2e-05,
      "loss": 0.7652930736541748,
      "step": 1340
    },
    {
      "epoch": 0.08682230368512445,
      "grad_norm": 1.170982466023762,
      "learning_rate": 2e-05,
      "loss": 0.7785554885864258,
      "step": 1350
    },
    {
      "epoch": 0.0874654318605698,
      "grad_norm": 1.3315886378379231,
      "learning_rate": 2e-05,
      "loss": 0.7762284755706788,
      "step": 1360
    },
    {
      "epoch": 0.08810856003601518,
      "grad_norm": 3.4644691896641033,
      "learning_rate": 2e-05,
      "loss": 0.7717214107513428,
      "step": 1370
    },
    {
      "epoch": 0.08875168821146054,
      "grad_norm": 2.4638970172558263,
      "learning_rate": 2e-05,
      "loss": 0.7678469657897949,
      "step": 1380
    },
    {
      "epoch": 0.08939481638690591,
      "grad_norm": 1.6678660828792848,
      "learning_rate": 2e-05,
      "loss": 0.7703881740570069,
      "step": 1390
    },
    {
      "epoch": 0.09003794456235127,
      "grad_norm": 1.2703517703114975,
      "learning_rate": 2e-05,
      "loss": 0.7905326843261719,
      "step": 1400
    },
    {
      "epoch": 0.09068107273779664,
      "grad_norm": 2.7492971396954964,
      "learning_rate": 2e-05,
      "loss": 0.7528151512145996,
      "step": 1410
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 1.85122344862107,
      "learning_rate": 2e-05,
      "loss": 0.7600863456726075,
      "step": 1420
    },
    {
      "epoch": 0.09196732908868738,
      "grad_norm": 1.121790046409357,
      "learning_rate": 2e-05,
      "loss": 0.771851921081543,
      "step": 1430
    },
    {
      "epoch": 0.09261045726413274,
      "grad_norm": 1.5662881662547643,
      "learning_rate": 2e-05,
      "loss": 0.783432149887085,
      "step": 1440
    },
    {
      "epoch": 0.09325358543957811,
      "grad_norm": 2.0639305477971446,
      "learning_rate": 2e-05,
      "loss": 0.76649169921875,
      "step": 1450
    },
    {
      "epoch": 0.09389671361502347,
      "grad_norm": 1.6044380184600715,
      "learning_rate": 2e-05,
      "loss": 0.7608757972717285,
      "step": 1460
    },
    {
      "epoch": 0.09453984179046884,
      "grad_norm": 1.1572139692941597,
      "learning_rate": 2e-05,
      "loss": 0.7706125259399415,
      "step": 1470
    },
    {
      "epoch": 0.0951829699659142,
      "grad_norm": 1.8138858808035307,
      "learning_rate": 2e-05,
      "loss": 0.7700668334960937,
      "step": 1480
    },
    {
      "epoch": 0.09582609814135958,
      "grad_norm": 1.454983551543918,
      "learning_rate": 2e-05,
      "loss": 0.7904407501220703,
      "step": 1490
    },
    {
      "epoch": 0.09646922631680493,
      "grad_norm": 2.0901094734966796,
      "learning_rate": 2e-05,
      "loss": 0.7803089141845703,
      "step": 1500
    },
    {
      "epoch": 0.09711235449225031,
      "grad_norm": 2.567975717980828,
      "learning_rate": 2e-05,
      "loss": 0.7728228569030762,
      "step": 1510
    },
    {
      "epoch": 0.09775548266769567,
      "grad_norm": 1.780447312937554,
      "learning_rate": 2e-05,
      "loss": 0.8009782791137695,
      "step": 1520
    },
    {
      "epoch": 0.09839861084314104,
      "grad_norm": 6.2870046446647,
      "learning_rate": 2e-05,
      "loss": 0.7996140480041504,
      "step": 1530
    },
    {
      "epoch": 0.0990417390185864,
      "grad_norm": 2.156771416116291,
      "learning_rate": 2e-05,
      "loss": 0.7783120632171631,
      "step": 1540
    },
    {
      "epoch": 0.09968486719403177,
      "grad_norm": 1.2275704688595095,
      "learning_rate": 2e-05,
      "loss": 0.7634446620941162,
      "step": 1550
    },
    {
      "epoch": 0.10032799536947713,
      "grad_norm": 1.793131326578086,
      "learning_rate": 2e-05,
      "loss": 0.7803597927093506,
      "step": 1560
    },
    {
      "epoch": 0.1009711235449225,
      "grad_norm": 1.2370786940553424,
      "learning_rate": 2e-05,
      "loss": 0.7557382106781005,
      "step": 1570
    },
    {
      "epoch": 0.10161425172036787,
      "grad_norm": 2.2314399766443676,
      "learning_rate": 2e-05,
      "loss": 0.7821496486663818,
      "step": 1580
    },
    {
      "epoch": 0.10225737989581324,
      "grad_norm": 2.3186973460423723,
      "learning_rate": 2e-05,
      "loss": 0.7797545433044434,
      "step": 1590
    },
    {
      "epoch": 0.1029005080712586,
      "grad_norm": 1.462537448976435,
      "learning_rate": 2e-05,
      "loss": 0.7844183921813965,
      "step": 1600
    },
    {
      "epoch": 0.10354363624670397,
      "grad_norm": 1.5205367367748963,
      "learning_rate": 2e-05,
      "loss": 0.7902626037597656,
      "step": 1610
    },
    {
      "epoch": 0.10418676442214933,
      "grad_norm": 3.5432682320386655,
      "learning_rate": 2e-05,
      "loss": 0.7723273277282715,
      "step": 1620
    },
    {
      "epoch": 0.1048298925975947,
      "grad_norm": 1.609507484917306,
      "learning_rate": 2e-05,
      "loss": 0.7709271430969238,
      "step": 1630
    },
    {
      "epoch": 0.10547302077304006,
      "grad_norm": 1.1002224278546247,
      "learning_rate": 2e-05,
      "loss": 0.7905303955078125,
      "step": 1640
    },
    {
      "epoch": 0.10611614894848544,
      "grad_norm": 2.884940398494792,
      "learning_rate": 2e-05,
      "loss": 0.7871637344360352,
      "step": 1650
    },
    {
      "epoch": 0.1067592771239308,
      "grad_norm": 1.2020747081839562,
      "learning_rate": 2e-05,
      "loss": 0.7405866146087646,
      "step": 1660
    },
    {
      "epoch": 0.10740240529937617,
      "grad_norm": 6.606063972824954,
      "learning_rate": 2e-05,
      "loss": 0.7357051849365235,
      "step": 1670
    },
    {
      "epoch": 0.10804553347482153,
      "grad_norm": 3.5578842158542865,
      "learning_rate": 2e-05,
      "loss": 0.7682039260864257,
      "step": 1680
    },
    {
      "epoch": 0.1086886616502669,
      "grad_norm": 1.3072327175477532,
      "learning_rate": 2e-05,
      "loss": 0.7714582443237304,
      "step": 1690
    },
    {
      "epoch": 0.10933178982571226,
      "grad_norm": 1.3765783821951507,
      "learning_rate": 2e-05,
      "loss": 0.7503826141357421,
      "step": 1700
    },
    {
      "epoch": 0.10997491800115763,
      "grad_norm": 4.459887753306068,
      "learning_rate": 2e-05,
      "loss": 0.7501479148864746,
      "step": 1710
    },
    {
      "epoch": 0.110618046176603,
      "grad_norm": 2.70029059251659,
      "learning_rate": 2e-05,
      "loss": 0.8093817710876465,
      "step": 1720
    },
    {
      "epoch": 0.11126117435204837,
      "grad_norm": 1.7062222278246155,
      "learning_rate": 2e-05,
      "loss": 0.7766101360321045,
      "step": 1730
    },
    {
      "epoch": 0.11190430252749373,
      "grad_norm": 1.328579668130039,
      "learning_rate": 2e-05,
      "loss": 0.7427976608276368,
      "step": 1740
    },
    {
      "epoch": 0.1125474307029391,
      "grad_norm": 4.778582308508733,
      "learning_rate": 2e-05,
      "loss": 0.781195592880249,
      "step": 1750
    },
    {
      "epoch": 0.11319055887838446,
      "grad_norm": 1.9035347037479093,
      "learning_rate": 2e-05,
      "loss": 0.7611964702606201,
      "step": 1760
    },
    {
      "epoch": 0.11383368705382983,
      "grad_norm": 1.869590411200461,
      "learning_rate": 2e-05,
      "loss": 0.7906878471374512,
      "step": 1770
    },
    {
      "epoch": 0.11447681522927519,
      "grad_norm": 1.551688435499546,
      "learning_rate": 2e-05,
      "loss": 0.7423989295959472,
      "step": 1780
    },
    {
      "epoch": 0.11511994340472056,
      "grad_norm": 5.098013550894126,
      "learning_rate": 2e-05,
      "loss": 0.7568299293518066,
      "step": 1790
    },
    {
      "epoch": 0.11576307158016592,
      "grad_norm": 2.5007704043329495,
      "learning_rate": 2e-05,
      "loss": 0.7778056621551513,
      "step": 1800
    },
    {
      "epoch": 0.1164061997556113,
      "grad_norm": 1.52922937116661,
      "learning_rate": 2e-05,
      "loss": 0.799095630645752,
      "step": 1810
    },
    {
      "epoch": 0.11704932793105666,
      "grad_norm": 18.126018555580437,
      "learning_rate": 2e-05,
      "loss": 0.7876038551330566,
      "step": 1820
    },
    {
      "epoch": 0.11769245610650203,
      "grad_norm": 1.282142333991493,
      "learning_rate": 2e-05,
      "loss": 0.7696383476257325,
      "step": 1830
    },
    {
      "epoch": 0.11833558428194739,
      "grad_norm": 1.7962688003308664,
      "learning_rate": 2e-05,
      "loss": 0.7794070720672608,
      "step": 1840
    },
    {
      "epoch": 0.11897871245739276,
      "grad_norm": 1.0874142410284557,
      "learning_rate": 2e-05,
      "loss": 0.768028450012207,
      "step": 1850
    },
    {
      "epoch": 0.11962184063283812,
      "grad_norm": 1.2554969962658076,
      "learning_rate": 2e-05,
      "loss": 0.7807290077209472,
      "step": 1860
    },
    {
      "epoch": 0.1202649688082835,
      "grad_norm": 1.503617789481177,
      "learning_rate": 2e-05,
      "loss": 0.7617989540100097,
      "step": 1870
    },
    {
      "epoch": 0.12090809698372885,
      "grad_norm": 1.3236598847407397,
      "learning_rate": 2e-05,
      "loss": 0.7619621276855468,
      "step": 1880
    },
    {
      "epoch": 0.12155122515917423,
      "grad_norm": 1.3278805791234929,
      "learning_rate": 2e-05,
      "loss": 0.7731639862060546,
      "step": 1890
    },
    {
      "epoch": 0.12219435333461959,
      "grad_norm": 1.3336901969204897,
      "learning_rate": 2e-05,
      "loss": 0.7973304748535156,
      "step": 1900
    },
    {
      "epoch": 0.12283748151006496,
      "grad_norm": 1.2081432983403761,
      "learning_rate": 2e-05,
      "loss": 0.732518196105957,
      "step": 1910
    },
    {
      "epoch": 0.12348060968551032,
      "grad_norm": 1.0660544450914864,
      "learning_rate": 2e-05,
      "loss": 0.7558794975280761,
      "step": 1920
    },
    {
      "epoch": 0.1241237378609557,
      "grad_norm": 1.073493051686456,
      "learning_rate": 2e-05,
      "loss": 0.770344877243042,
      "step": 1930
    },
    {
      "epoch": 0.12476686603640105,
      "grad_norm": 1.0266721503860259,
      "learning_rate": 2e-05,
      "loss": 0.7605429649353027,
      "step": 1940
    },
    {
      "epoch": 0.12540999421184643,
      "grad_norm": 1.6219397326505027,
      "learning_rate": 2e-05,
      "loss": 0.7637803077697753,
      "step": 1950
    },
    {
      "epoch": 0.1260531223872918,
      "grad_norm": 1.319161229050353,
      "learning_rate": 2e-05,
      "loss": 0.7486878871917725,
      "step": 1960
    },
    {
      "epoch": 0.12669625056273714,
      "grad_norm": 1.4547728573258885,
      "learning_rate": 2e-05,
      "loss": 0.7947936534881592,
      "step": 1970
    },
    {
      "epoch": 0.12733937873818252,
      "grad_norm": 3.0621373300129897,
      "learning_rate": 2e-05,
      "loss": 0.7795517921447754,
      "step": 1980
    },
    {
      "epoch": 0.1279825069136279,
      "grad_norm": 1.288805293411811,
      "learning_rate": 2e-05,
      "loss": 0.7543374538421631,
      "step": 1990
    },
    {
      "epoch": 0.12862563508907326,
      "grad_norm": 1.8078110077721685,
      "learning_rate": 2e-05,
      "loss": 0.7700879096984863,
      "step": 2000
    },
    {
      "epoch": 0.1292687632645186,
      "grad_norm": 1.5167799524227923,
      "learning_rate": 2e-05,
      "loss": 0.756030797958374,
      "step": 2010
    },
    {
      "epoch": 0.12991189143996398,
      "grad_norm": 5.4727720008288365,
      "learning_rate": 2e-05,
      "loss": 0.7306814193725586,
      "step": 2020
    },
    {
      "epoch": 0.13055501961540936,
      "grad_norm": 1.8434468283827343,
      "learning_rate": 2e-05,
      "loss": 0.7443379878997802,
      "step": 2030
    }
  ],
  "logging_steps": 10,
  "max_steps": 5935,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2035,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 963613493821440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}