{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1097863616745792,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005394907207596029,
      "grad_norm": 369.69301600900053,
      "learning_rate": 2.910112359550562e-06,
      "loss": 1.8730627059936524,
      "step": 10
    },
    {
      "epoch": 0.0010789814415192059,
      "grad_norm": 31.93478853689241,
      "learning_rate": 3.921348314606742e-06,
      "loss": 1.262525463104248,
      "step": 20
    },
    {
      "epoch": 0.0016184721622788088,
      "grad_norm": 141.7556466471986,
      "learning_rate": 4.932584269662922e-06,
      "loss": 1.0669395446777343,
      "step": 30
    },
    {
      "epoch": 0.0021579628830384117,
      "grad_norm": 127.98270782023548,
      "learning_rate": 5.943820224719102e-06,
      "loss": 1.1076365470886231,
      "step": 40
    },
    {
      "epoch": 0.002697453603798015,
      "grad_norm": 101.43748401214339,
      "learning_rate": 6.955056179775282e-06,
      "loss": 1.0109930038452148,
      "step": 50
    },
    {
      "epoch": 0.0032369443245576176,
      "grad_norm": 899.0086783565027,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.9515115737915039,
      "step": 60
    },
    {
      "epoch": 0.0037764350453172208,
      "grad_norm": 15.557933246692217,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.9290966987609863,
      "step": 70
    },
    {
      "epoch": 0.0043159257660768235,
      "grad_norm": 256.064896120912,
      "learning_rate": 9.988764044943822e-06,
      "loss": 1.1323322296142577,
      "step": 80
    },
    {
      "epoch": 0.004855416486836427,
      "grad_norm": 20.848525026966247,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 1.088106918334961,
      "step": 90
    },
    {
      "epoch": 0.00539490720759603,
      "grad_norm": 25.60593783327153,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.9955007553100585,
      "step": 100
    },
    {
      "epoch": 0.005934397928355632,
      "grad_norm": 11.664176937579581,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.942236328125,
      "step": 110
    },
    {
      "epoch": 0.006473888649115235,
      "grad_norm": 7.9248397322900646,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.9238415718078613,
      "step": 120
    },
    {
      "epoch": 0.007013379369874838,
      "grad_norm": 26.682291952362966,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.9361964225769043,
      "step": 130
    },
    {
      "epoch": 0.0075528700906344415,
      "grad_norm": 3.6691592434398466,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.927226448059082,
      "step": 140
    },
    {
      "epoch": 0.008092360811394044,
      "grad_norm": 15.191132047351614,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.9375665664672852,
      "step": 150
    },
    {
      "epoch": 0.008631851532153647,
      "grad_norm": 7.4209329049996455,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.9221304893493653,
      "step": 160
    },
    {
      "epoch": 0.00917134225291325,
      "grad_norm": 5.050234356436225,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.9327095031738282,
      "step": 170
    },
    {
      "epoch": 0.009710832973672853,
      "grad_norm": 2.532425838265676,
      "learning_rate": 2e-05,
      "loss": 0.90814208984375,
      "step": 180
    },
    {
      "epoch": 0.010250323694432456,
      "grad_norm": 2.8569985447993664,
      "learning_rate": 2e-05,
      "loss": 0.930181884765625,
      "step": 190
    },
    {
      "epoch": 0.01078981441519206,
      "grad_norm": 3.7217733328209746,
      "learning_rate": 2e-05,
      "loss": 0.9137080192565918,
      "step": 200
    },
    {
      "epoch": 0.011329305135951661,
      "grad_norm": 1.6856605125936686,
      "learning_rate": 2e-05,
      "loss": 0.9173044204711914,
      "step": 210
    },
    {
      "epoch": 0.011868795856711264,
      "grad_norm": 4.042279257566151,
      "learning_rate": 2e-05,
      "loss": 0.9044102668762207,
      "step": 220
    },
    {
      "epoch": 0.012408286577470867,
      "grad_norm": 7.693180928481417,
      "learning_rate": 2e-05,
      "loss": 0.9013534545898437,
      "step": 230
    },
    {
      "epoch": 0.01294777729823047,
      "grad_norm": 3.5295771823615647,
      "learning_rate": 2e-05,
      "loss": 0.9148492813110352,
      "step": 240
    },
    {
      "epoch": 0.013487268018990074,
      "grad_norm": 7.839029508109661,
      "learning_rate": 2e-05,
      "loss": 0.9837350845336914,
      "step": 250
    },
    {
      "epoch": 0.014026758739749677,
      "grad_norm": 3.670914514568096,
      "learning_rate": 2e-05,
      "loss": 0.9146605491638183,
      "step": 260
    },
    {
      "epoch": 0.01456624946050928,
      "grad_norm": 3.5577694379027,
      "learning_rate": 2e-05,
      "loss": 0.9401106834411621,
      "step": 270
    },
    {
      "epoch": 0.015105740181268883,
      "grad_norm": 2.453202809896575,
      "learning_rate": 2e-05,
      "loss": 0.9477849960327148,
      "step": 280
    },
    {
      "epoch": 0.015645230902028486,
      "grad_norm": 1.9729075743285769,
      "learning_rate": 2e-05,
      "loss": 0.9066492080688476,
      "step": 290
    },
    {
      "epoch": 0.016184721622788088,
      "grad_norm": 2.8099192390223795,
      "learning_rate": 2e-05,
      "loss": 0.9063838958740235,
      "step": 300
    },
    {
      "epoch": 0.016724212343547692,
      "grad_norm": 4.236623113420927,
      "learning_rate": 2e-05,
      "loss": 0.8637477874755859,
      "step": 310
    },
    {
      "epoch": 0.017263703064307294,
      "grad_norm": 4.167628129961564,
      "learning_rate": 2e-05,
      "loss": 0.9061297416687012,
      "step": 320
    },
    {
      "epoch": 0.017803193785066895,
      "grad_norm": 6.935834245033307,
      "learning_rate": 2e-05,
      "loss": 0.8871530532836914,
      "step": 330
    },
    {
      "epoch": 0.0183426845058265,
      "grad_norm": 3.2423751981314384,
      "learning_rate": 2e-05,
      "loss": 0.9223550796508789,
      "step": 340
    },
    {
      "epoch": 0.0188821752265861,
      "grad_norm": 30.606793216440163,
      "learning_rate": 2e-05,
      "loss": 3.54920654296875,
      "step": 350
    },
    {
      "epoch": 0.019421665947345707,
      "grad_norm": 4.550939608135107,
      "learning_rate": 2e-05,
      "loss": 0.9992364883422852,
      "step": 360
    },
    {
      "epoch": 0.019961156668105308,
      "grad_norm": 10.355788989674835,
      "learning_rate": 2e-05,
      "loss": 0.9463441848754883,
      "step": 370
    },
    {
      "epoch": 0.020500647388864913,
      "grad_norm": 9.470092673566741,
      "learning_rate": 2e-05,
      "loss": 0.9165935516357422,
      "step": 380
    },
    {
      "epoch": 0.021040138109624514,
      "grad_norm": 16.04366173130251,
      "learning_rate": 2e-05,
      "loss": 0.9199161529541016,
      "step": 390
    },
    {
      "epoch": 0.02157962883038412,
      "grad_norm": 16.276111063417574,
      "learning_rate": 2e-05,
      "loss": 0.8900386810302734,
      "step": 400
    },
    {
      "epoch": 0.02211911955114372,
      "grad_norm": 14.653812444903842,
      "learning_rate": 2e-05,
      "loss": 0.8979652404785157,
      "step": 410
    },
    {
      "epoch": 0.022658610271903322,
      "grad_norm": 2.6977548589169094,
      "learning_rate": 2e-05,
      "loss": 0.9128728866577148,
      "step": 420
    },
    {
      "epoch": 0.023198100992662927,
      "grad_norm": 23.582887550971233,
      "learning_rate": 2e-05,
      "loss": 0.8891826629638672,
      "step": 430
    },
    {
      "epoch": 0.023737591713422528,
      "grad_norm": 2.9436146384915443,
      "learning_rate": 2e-05,
      "loss": 0.9091741561889648,
      "step": 440
    },
    {
      "epoch": 0.024277082434182133,
      "grad_norm": 3.8178614247451996,
      "learning_rate": 2e-05,
      "loss": 0.9071731567382812,
      "step": 450
    },
    {
      "epoch": 0.024816573154941735,
      "grad_norm": 9.900017833351434,
      "learning_rate": 2e-05,
      "loss": 0.8803417205810546,
      "step": 460
    },
    {
      "epoch": 0.02535606387570134,
      "grad_norm": 11.377800042408293,
      "learning_rate": 2e-05,
      "loss": 0.9077526092529297,
      "step": 470
    },
    {
      "epoch": 0.02589555459646094,
      "grad_norm": 4.425640907224202,
      "learning_rate": 2e-05,
      "loss": 0.8951313018798828,
      "step": 480
    },
    {
      "epoch": 0.026435045317220542,
      "grad_norm": 5.543696039922662,
      "learning_rate": 2e-05,
      "loss": 0.9170653343200683,
      "step": 490
    },
    {
      "epoch": 0.026974536037980147,
      "grad_norm": 6.637675684831988,
      "learning_rate": 2e-05,
      "loss": 0.9328924179077148,
      "step": 500
    },
    {
      "epoch": 0.02751402675873975,
      "grad_norm": 4.541587002846055,
      "learning_rate": 2e-05,
      "loss": 0.9184404373168945,
      "step": 510
    },
    {
      "epoch": 0.028053517479499353,
      "grad_norm": 4.834955555833834,
      "learning_rate": 2e-05,
      "loss": 0.94840087890625,
      "step": 520
    },
    {
      "epoch": 0.028593008200258955,
      "grad_norm": 2.7476196554801118,
      "learning_rate": 2e-05,
      "loss": 0.9112020492553711,
      "step": 530
    },
    {
      "epoch": 0.02913249892101856,
      "grad_norm": 3.729222437612153,
      "learning_rate": 2e-05,
      "loss": 0.8715265274047852,
      "step": 540
    },
    {
      "epoch": 0.02967198964177816,
      "grad_norm": 1.8986444153489899,
      "learning_rate": 2e-05,
      "loss": 0.8817804336547852,
      "step": 550
    },
    {
      "epoch": 0.030211480362537766,
      "grad_norm": 19.652863197507482,
      "learning_rate": 2e-05,
      "loss": 0.9034578323364257,
      "step": 560
    },
    {
      "epoch": 0.030750971083297367,
      "grad_norm": 4.893935787998432,
      "learning_rate": 2e-05,
      "loss": 0.9201476097106933,
      "step": 570
    },
    {
      "epoch": 0.03129046180405697,
      "grad_norm": 2.121315677688142,
      "learning_rate": 2e-05,
      "loss": 0.9087504386901856,
      "step": 580
    },
    {
      "epoch": 0.031829952524816574,
      "grad_norm": 1.6805303205822455,
      "learning_rate": 2e-05,
      "loss": 0.8938014030456543,
      "step": 590
    },
    {
      "epoch": 0.032369443245576175,
      "grad_norm": 2.091016561123043,
      "learning_rate": 2e-05,
      "loss": 0.8701451301574707,
      "step": 600
    },
    {
      "epoch": 0.03290893396633578,
      "grad_norm": 4.4795444497420345,
      "learning_rate": 2e-05,
      "loss": 0.8988707542419434,
      "step": 610
    },
    {
      "epoch": 0.033448424687095385,
      "grad_norm": 1.40755956780777,
      "learning_rate": 2e-05,
      "loss": 0.8736795425415039,
      "step": 620
    },
    {
      "epoch": 0.033987915407854986,
      "grad_norm": 1.9677540233275401,
      "learning_rate": 2e-05,
      "loss": 0.8994430541992188,
      "step": 630
    },
    {
      "epoch": 0.03452740612861459,
      "grad_norm": 2.8537882081306605,
      "learning_rate": 2e-05,
      "loss": 0.8869138717651367,
      "step": 640
    },
    {
      "epoch": 0.03506689684937419,
      "grad_norm": 2.3406412447640133,
      "learning_rate": 2e-05,
      "loss": 0.8736772537231445,
      "step": 650
    },
    {
      "epoch": 0.03560638757013379,
      "grad_norm": 2.7002297840083647,
      "learning_rate": 2e-05,
      "loss": 0.8878070831298828,
      "step": 660
    },
    {
      "epoch": 0.0361458782908934,
      "grad_norm": 5.478051955992026,
      "learning_rate": 2e-05,
      "loss": 0.9007582664489746,
      "step": 670
    },
    {
      "epoch": 0.036685369011653,
      "grad_norm": 5.987775578117277,
      "learning_rate": 2e-05,
      "loss": 0.877619457244873,
      "step": 680
    },
    {
      "epoch": 0.0372248597324126,
      "grad_norm": 4.062183705280081,
      "learning_rate": 2e-05,
      "loss": 0.9615988731384277,
      "step": 690
    },
    {
      "epoch": 0.0377643504531722,
      "grad_norm": 1.7304116921547956,
      "learning_rate": 2e-05,
      "loss": 0.8999065399169922,
      "step": 700
    },
    {
      "epoch": 0.03830384117393181,
      "grad_norm": 10.224091687714415,
      "learning_rate": 2e-05,
      "loss": 0.8775262832641602,
      "step": 710
    },
    {
      "epoch": 0.03884333189469141,
      "grad_norm": 2.6973024084894885,
      "learning_rate": 2e-05,
      "loss": 0.88863525390625,
      "step": 720
    },
    {
      "epoch": 0.039382822615451014,
      "grad_norm": 3.0097373941657186,
      "learning_rate": 2e-05,
      "loss": 0.8921207427978516,
      "step": 730
    },
    {
      "epoch": 0.039922313336210616,
      "grad_norm": 2.4929780841655207,
      "learning_rate": 2e-05,
      "loss": 0.8870817184448242,
      "step": 740
    },
    {
      "epoch": 0.04046180405697022,
      "grad_norm": 2.680211035148592,
      "learning_rate": 2e-05,
      "loss": 0.8718931198120117,
      "step": 750
    },
    {
      "epoch": 0.041001294777729826,
      "grad_norm": 3.314725765838302,
      "learning_rate": 2e-05,
      "loss": 0.8696352005004883,
      "step": 760
    },
    {
      "epoch": 0.04154078549848943,
      "grad_norm": 2.8067410842808824,
      "learning_rate": 2e-05,
      "loss": 0.8808348655700684,
      "step": 770
    },
    {
      "epoch": 0.04208027621924903,
      "grad_norm": 4.568417784852867,
      "learning_rate": 2e-05,
      "loss": 0.8762812614440918,
      "step": 780
    },
    {
      "epoch": 0.04261976694000863,
      "grad_norm": 1.591466243191371,
      "learning_rate": 2e-05,
      "loss": 0.8897010803222656,
      "step": 790
    },
    {
      "epoch": 0.04315925766076824,
      "grad_norm": 1.7378624546635357,
      "learning_rate": 2e-05,
      "loss": 0.8871335983276367,
      "step": 800
    },
    {
      "epoch": 0.04369874838152784,
      "grad_norm": 5.282884941300159,
      "learning_rate": 2e-05,
      "loss": 0.8862749099731445,
      "step": 810
    },
    {
      "epoch": 0.04423823910228744,
      "grad_norm": 1.4282666163813993,
      "learning_rate": 2e-05,
      "loss": 0.9045479774475098,
      "step": 820
    },
    {
      "epoch": 0.04477772982304704,
      "grad_norm": 1.804678546954577,
      "learning_rate": 2e-05,
      "loss": 0.8669574737548829,
      "step": 830
    },
    {
      "epoch": 0.045317220543806644,
      "grad_norm": 2.7003745816690836,
      "learning_rate": 2e-05,
      "loss": 0.8664716720581055,
      "step": 840
    },
    {
      "epoch": 0.04585671126456625,
      "grad_norm": 2.8347718319860626,
      "learning_rate": 2e-05,
      "loss": 0.8740848541259766,
      "step": 850
    },
    {
      "epoch": 0.046396201985325854,
      "grad_norm": 2.3599301199842655,
      "learning_rate": 2e-05,
      "loss": 0.8661260604858398,
      "step": 860
    },
    {
      "epoch": 0.046935692706085455,
      "grad_norm": 2.675130769028597,
      "learning_rate": 2e-05,
      "loss": 0.8940586090087891,
      "step": 870
    },
    {
      "epoch": 0.047475183426845056,
      "grad_norm": 2.13219637159858,
      "learning_rate": 2e-05,
      "loss": 0.8656101226806641,
      "step": 880
    },
    {
      "epoch": 0.04801467414760466,
      "grad_norm": 5.746935578097955,
      "learning_rate": 2e-05,
      "loss": 0.9049406051635742,
      "step": 890
    },
    {
      "epoch": 0.048554164868364266,
      "grad_norm": 3.040442087390683,
      "learning_rate": 2e-05,
      "loss": 0.8673805236816406,
      "step": 900
    },
    {
      "epoch": 0.04909365558912387,
      "grad_norm": 1.8033864790060448,
      "learning_rate": 2e-05,
      "loss": 0.9076686859130859,
      "step": 910
    },
    {
      "epoch": 0.04963314630988347,
      "grad_norm": 3.7270371618478446,
      "learning_rate": 2e-05,
      "loss": 0.8856944084167481,
      "step": 920
    },
    {
      "epoch": 0.05017263703064307,
      "grad_norm": 18.34533608060895,
      "learning_rate": 2e-05,
      "loss": 0.8803435325622558,
      "step": 930
    },
    {
      "epoch": 0.05071212775140268,
      "grad_norm": 7.031326732375769,
      "learning_rate": 2e-05,
      "loss": 0.8922122955322266,
      "step": 940
    },
    {
      "epoch": 0.05125161847216228,
      "grad_norm": 1.271585738790212,
      "learning_rate": 2e-05,
      "loss": 0.8702299118041992,
      "step": 950
    },
    {
      "epoch": 0.05179110919292188,
      "grad_norm": 3.1087560610639984,
      "learning_rate": 2e-05,
      "loss": 0.869837474822998,
      "step": 960
    },
    {
      "epoch": 0.05233059991368148,
      "grad_norm": 1.336885754811761,
      "learning_rate": 2e-05,
      "loss": 0.8768095016479492,
      "step": 970
    },
    {
      "epoch": 0.052870090634441085,
      "grad_norm": 1.2937187665672654,
      "learning_rate": 2e-05,
      "loss": 0.8737648010253907,
      "step": 980
    },
    {
      "epoch": 0.05340958135520069,
      "grad_norm": 6.496337599049736,
      "learning_rate": 2e-05,
      "loss": 0.8852460861206055,
      "step": 990
    },
    {
      "epoch": 0.053949072075960294,
      "grad_norm": 2.314909026977299,
      "learning_rate": 2e-05,
      "loss": 0.9168342590332031,
      "step": 1000
    },
    {
      "epoch": 0.054488562796719896,
      "grad_norm": 1.3797589526126182,
      "learning_rate": 2e-05,
      "loss": 0.9012920379638671,
      "step": 1010
    },
    {
      "epoch": 0.0550280535174795,
      "grad_norm": 1.7456393044082175,
      "learning_rate": 2e-05,
      "loss": 0.8839190483093262,
      "step": 1020
    },
    {
      "epoch": 0.055567544238239105,
      "grad_norm": 2.2368924316262913,
      "learning_rate": 2e-05,
      "loss": 0.8841041564941406,
      "step": 1030
    },
    {
      "epoch": 0.05610703495899871,
      "grad_norm": 2.3060976347623408,
      "learning_rate": 2e-05,
      "loss": 0.9180487632751465,
      "step": 1040
    },
    {
      "epoch": 0.05664652567975831,
      "grad_norm": 2.2473033744197655,
      "learning_rate": 2e-05,
      "loss": 0.8983830451965332,
      "step": 1050
    },
    {
      "epoch": 0.05718601640051791,
      "grad_norm": 3.33794913543599,
      "learning_rate": 2e-05,
      "loss": 0.9058303833007812,
      "step": 1060
    },
    {
      "epoch": 0.05772550712127751,
      "grad_norm": 2.1863704996804874,
      "learning_rate": 2e-05,
      "loss": 0.8500079154968262,
      "step": 1070
    },
    {
      "epoch": 0.05826499784203712,
      "grad_norm": 5.464104262184261,
      "learning_rate": 2e-05,
      "loss": 0.86676025390625,
      "step": 1080
    },
    {
      "epoch": 0.05880448856279672,
      "grad_norm": 1.2580865472126652,
      "learning_rate": 2e-05,
      "loss": 0.8795917510986329,
      "step": 1090
    },
    {
      "epoch": 0.05934397928355632,
      "grad_norm": 1.5392878698728925,
      "learning_rate": 2e-05,
      "loss": 0.855427360534668,
      "step": 1100
    },
    {
      "epoch": 0.059883470004315924,
      "grad_norm": 1.6600456111757242,
      "learning_rate": 2e-05,
      "loss": 0.8580084800720215,
      "step": 1110
    },
    {
      "epoch": 0.06042296072507553,
      "grad_norm": 1.9728666357091431,
      "learning_rate": 2e-05,
      "loss": 0.8592136383056641,
      "step": 1120
    },
    {
      "epoch": 0.060962451445835134,
      "grad_norm": 2.622532245761096,
      "learning_rate": 2e-05,
      "loss": 0.8778785705566406,
      "step": 1130
    },
    {
      "epoch": 0.061501942166594735,
      "grad_norm": 2.436300801764917,
      "learning_rate": 2e-05,
      "loss": 0.8558690071105957,
      "step": 1140
    },
    {
      "epoch": 0.062041432887354336,
      "grad_norm": 2.072486307736441,
      "learning_rate": 2e-05,
      "loss": 0.8554096221923828,
      "step": 1150
    },
    {
      "epoch": 0.06258092360811394,
      "grad_norm": 2.9578754600495105,
      "learning_rate": 2e-05,
      "loss": 0.8688982963562012,
      "step": 1160
    },
    {
      "epoch": 0.06312041432887354,
      "grad_norm": 2.2185001887709106,
      "learning_rate": 2e-05,
      "loss": 0.8960395812988281,
      "step": 1170
    },
    {
      "epoch": 0.06365990504963315,
      "grad_norm": 2.39317741084652,
      "learning_rate": 2e-05,
      "loss": 0.8809322357177735,
      "step": 1180
    },
    {
      "epoch": 0.06419939577039276,
      "grad_norm": 7.053593954669792,
      "learning_rate": 2e-05,
      "loss": 0.8588828086853028,
      "step": 1190
    },
    {
      "epoch": 0.06473888649115235,
      "grad_norm": 2.8316276030407392,
      "learning_rate": 2e-05,
      "loss": 0.863832664489746,
      "step": 1200
    },
    {
      "epoch": 0.06527837721191196,
      "grad_norm": 55.263846840104094,
      "learning_rate": 2e-05,
      "loss": 0.8467828750610351,
      "step": 1210
    },
    {
      "epoch": 0.06581786793267155,
      "grad_norm": 1.891195934618861,
      "learning_rate": 2e-05,
      "loss": 0.8810437202453614,
      "step": 1220
    },
    {
      "epoch": 0.06635735865343116,
      "grad_norm": 4.262649131447584,
      "learning_rate": 2e-05,
      "loss": 0.8573444366455079,
      "step": 1230
    },
    {
      "epoch": 0.06689684937419077,
      "grad_norm": 5.280398859967369,
      "learning_rate": 2e-05,
      "loss": 0.8775759696960449,
      "step": 1240
    },
    {
      "epoch": 0.06743634009495036,
      "grad_norm": 13.161950494331434,
      "learning_rate": 2e-05,
      "loss": 0.8802067756652832,
      "step": 1250
    },
    {
      "epoch": 0.06797583081570997,
      "grad_norm": 2.3840227633253708,
      "learning_rate": 2e-05,
      "loss": 0.8745565414428711,
      "step": 1260
    },
    {
      "epoch": 0.06851532153646957,
      "grad_norm": 2.578881266139901,
      "learning_rate": 2e-05,
      "loss": 0.8929662704467773,
      "step": 1270
    },
    {
      "epoch": 0.06905481225722918,
      "grad_norm": 1.3551093714665399,
      "learning_rate": 2e-05,
      "loss": 0.8856276512145996,
      "step": 1280
    },
    {
      "epoch": 0.06959430297798878,
      "grad_norm": 1.421718866393892,
      "learning_rate": 2e-05,
      "loss": 0.8779384613037109,
      "step": 1290
    },
    {
      "epoch": 0.07013379369874838,
      "grad_norm": 1.3412253586411367,
      "learning_rate": 2e-05,
      "loss": 0.8418590545654296,
      "step": 1300
    },
    {
      "epoch": 0.07067328441950799,
      "grad_norm": 1.3164576570437523,
      "learning_rate": 2e-05,
      "loss": 0.8589597702026367,
      "step": 1310
    },
    {
      "epoch": 0.07121277514026758,
      "grad_norm": 5.63391297375713,
      "learning_rate": 2e-05,
      "loss": 0.8794595718383789,
      "step": 1320
    },
    {
      "epoch": 0.07175226586102719,
      "grad_norm": 1.3610004564150833,
      "learning_rate": 2e-05,
      "loss": 0.8666675567626954,
      "step": 1330
    },
    {
      "epoch": 0.0722917565817868,
      "grad_norm": 1.7200672230946694,
      "learning_rate": 2e-05,
      "loss": 0.8707124710083007,
      "step": 1340
    },
    {
      "epoch": 0.07283124730254639,
      "grad_norm": 1.3160601308789588,
      "learning_rate": 2e-05,
      "loss": 0.8457590103149414,
      "step": 1350
    },
    {
      "epoch": 0.073370738023306,
      "grad_norm": 1.7778775450463142,
      "learning_rate": 2e-05,
      "loss": 0.8669673919677734,
      "step": 1360
    },
    {
      "epoch": 0.0739102287440656,
      "grad_norm": 2.2742353103065485,
      "learning_rate": 2e-05,
      "loss": 0.920014762878418,
      "step": 1370
    },
    {
      "epoch": 0.0744497194648252,
      "grad_norm": 4.185305052537614,
      "learning_rate": 2e-05,
      "loss": 0.9066905021667481,
      "step": 1380
    },
    {
      "epoch": 0.07498921018558481,
      "grad_norm": 7.045183411349042,
      "learning_rate": 2e-05,
      "loss": 0.8720160484313965,
      "step": 1390
    },
    {
      "epoch": 0.0755287009063444,
      "grad_norm": 2.377204425821727,
      "learning_rate": 2e-05,
      "loss": 0.9035792350769043,
      "step": 1400
    },
    {
      "epoch": 0.07606819162710401,
      "grad_norm": 1.5514726466038995,
      "learning_rate": 2e-05,
      "loss": 0.8550067901611328,
      "step": 1410
    },
    {
      "epoch": 0.07660768234786362,
      "grad_norm": 3.2194246326766627,
      "learning_rate": 2e-05,
      "loss": 0.8613847732543946,
      "step": 1420
    },
    {
      "epoch": 0.07714717306862322,
      "grad_norm": 2.191413489389274,
      "learning_rate": 2e-05,
      "loss": 0.8483789443969727,
      "step": 1430
    },
    {
      "epoch": 0.07768666378938283,
      "grad_norm": 2.561083258333701,
      "learning_rate": 2e-05,
      "loss": 0.8561199188232422,
      "step": 1440
    },
    {
      "epoch": 0.07822615451014242,
      "grad_norm": 2.799486266864444,
      "learning_rate": 2e-05,
      "loss": 0.8749614715576172,
      "step": 1450
    },
    {
      "epoch": 0.07876564523090203,
      "grad_norm": 1.6625068228812598,
      "learning_rate": 2e-05,
      "loss": 0.8524051666259765,
      "step": 1460
    },
    {
      "epoch": 0.07930513595166164,
      "grad_norm": 1.5627273498445615,
      "learning_rate": 2e-05,
      "loss": 0.8613437652587891,
      "step": 1470
    },
    {
      "epoch": 0.07984462667242123,
      "grad_norm": 3.1187718040693815,
      "learning_rate": 2e-05,
      "loss": 0.8489472389221191,
      "step": 1480
    },
    {
      "epoch": 0.08038411739318084,
      "grad_norm": 1.999242227430214,
      "learning_rate": 2e-05,
      "loss": 0.8557394027709961,
      "step": 1490
    },
    {
      "epoch": 0.08092360811394043,
      "grad_norm": 2.1662789248263086,
      "learning_rate": 2e-05,
      "loss": 0.8410913467407226,
      "step": 1500
    },
    {
      "epoch": 0.08146309883470004,
      "grad_norm": 1.117593071600269,
      "learning_rate": 2e-05,
      "loss": 0.8719884872436523,
      "step": 1510
    },
    {
      "epoch": 0.08200258955545965,
      "grad_norm": 1.7282463420500256,
      "learning_rate": 2e-05,
      "loss": 0.8429347991943359,
      "step": 1520
    },
    {
      "epoch": 0.08254208027621925,
      "grad_norm": 1.10160222981424,
      "learning_rate": 2e-05,
      "loss": 0.8589319229125977,
      "step": 1530
    },
    {
      "epoch": 0.08308157099697885,
      "grad_norm": 1.657648568922712,
      "learning_rate": 2e-05,
      "loss": 0.8519350051879883,
      "step": 1540
    },
    {
      "epoch": 0.08362106171773845,
      "grad_norm": 1.2061011251185034,
      "learning_rate": 2e-05,
      "loss": 0.8548383712768555,
      "step": 1550
    },
    {
      "epoch": 0.08416055243849806,
      "grad_norm": 1.6503845091419074,
      "learning_rate": 2e-05,
      "loss": 0.8504886627197266,
      "step": 1560
    },
    {
      "epoch": 0.08470004315925767,
      "grad_norm": 1.650450748636652,
      "learning_rate": 2e-05,
      "loss": 0.8272921562194824,
      "step": 1570
    },
    {
      "epoch": 0.08523953388001726,
      "grad_norm": 1.2153538779996496,
      "learning_rate": 2e-05,
      "loss": 0.8586090087890625,
      "step": 1580
    },
    {
      "epoch": 0.08577902460077687,
      "grad_norm": 1.4119654167230689,
      "learning_rate": 2e-05,
      "loss": 0.8150126457214355,
      "step": 1590
    },
    {
      "epoch": 0.08631851532153648,
      "grad_norm": 2.0481812733972435,
      "learning_rate": 2e-05,
      "loss": 0.8605268478393555,
      "step": 1600
    },
    {
      "epoch": 0.08685800604229607,
      "grad_norm": 1.3493621359452488,
      "learning_rate": 2e-05,
      "loss": 0.8761652946472168,
      "step": 1610
    },
    {
      "epoch": 0.08739749676305568,
      "grad_norm": 1.937128776151837,
      "learning_rate": 2e-05,
      "loss": 0.8717695236206054,
      "step": 1620
    },
    {
      "epoch": 0.08793698748381527,
      "grad_norm": 1.2331164884742856,
      "learning_rate": 2e-05,
      "loss": 0.8695238113403321,
      "step": 1630
    },
    {
      "epoch": 0.08847647820457488,
      "grad_norm": 1.0766868462241113,
      "learning_rate": 2e-05,
      "loss": 0.8439886093139648,
      "step": 1640
    },
    {
      "epoch": 0.08901596892533449,
      "grad_norm": 4.825188821823706,
      "learning_rate": 2e-05,
      "loss": 0.8383602142333985,
      "step": 1650
    },
    {
      "epoch": 0.08955545964609408,
      "grad_norm": 1.0473009888263762,
      "learning_rate": 2e-05,
      "loss": 0.8446158409118653,
      "step": 1660
    },
    {
      "epoch": 0.0900949503668537,
      "grad_norm": 2.1550692634060407,
      "learning_rate": 2e-05,
      "loss": 0.8526595115661622,
      "step": 1670
    },
    {
      "epoch": 0.09063444108761329,
      "grad_norm": 1.1805712525240586,
      "learning_rate": 2e-05,
      "loss": 0.8445590019226075,
      "step": 1680
    },
    {
      "epoch": 0.0911739318083729,
      "grad_norm": 1.3154682778410502,
      "learning_rate": 2e-05,
      "loss": 0.8289753913879394,
      "step": 1690
    },
    {
      "epoch": 0.0917134225291325,
      "grad_norm": 1.7425671016352309,
      "learning_rate": 2e-05,
      "loss": 0.8550616264343261,
      "step": 1700
    },
    {
      "epoch": 0.0922529132498921,
      "grad_norm": 1.809326593705475,
      "learning_rate": 2e-05,
      "loss": 0.8592042922973633,
      "step": 1710
    },
    {
      "epoch": 0.09279240397065171,
      "grad_norm": 2.294726987915818,
      "learning_rate": 2e-05,
      "loss": 0.8464397430419922,
      "step": 1720
    },
    {
      "epoch": 0.0933318946914113,
      "grad_norm": 1.3341335707857838,
      "learning_rate": 2e-05,
      "loss": 0.8401545524597168,
      "step": 1730
    },
    {
      "epoch": 0.09387138541217091,
      "grad_norm": 1.7059856939535623,
      "learning_rate": 2e-05,
      "loss": 0.850313663482666,
      "step": 1740
    },
    {
      "epoch": 0.09441087613293052,
      "grad_norm": 1.1913305227905306,
      "learning_rate": 2e-05,
      "loss": 0.8246526718139648,
      "step": 1750
    },
    {
      "epoch": 0.09495036685369011,
      "grad_norm": 2.4712263811656063,
      "learning_rate": 2e-05,
      "loss": 0.8324945449829102,
      "step": 1760
    },
    {
      "epoch": 0.09548985757444972,
      "grad_norm": 1.2460535060628168,
      "learning_rate": 2e-05,
      "loss": 0.83499755859375,
      "step": 1770
    },
    {
      "epoch": 0.09602934829520932,
      "grad_norm": 0.9541283688175325,
      "learning_rate": 2e-05,
      "loss": 0.8438259124755859,
      "step": 1780
    },
    {
      "epoch": 0.09656883901596892,
      "grad_norm": 4.15270429876545,
      "learning_rate": 2e-05,
      "loss": 0.8374526977539063,
      "step": 1790
    },
    {
      "epoch": 0.09710832973672853,
      "grad_norm": 1.2843301784727401,
      "learning_rate": 2e-05,
      "loss": 0.855588722229004,
      "step": 1800
    },
    {
      "epoch": 0.09764782045748813,
      "grad_norm": 1.2852787584009888,
      "learning_rate": 2e-05,
      "loss": 0.8446294784545898,
      "step": 1810
    },
    {
      "epoch": 0.09818731117824774,
      "grad_norm": 1.1732513743084148,
      "learning_rate": 2e-05,
      "loss": 0.8550775527954102,
      "step": 1820
    },
    {
      "epoch": 0.09872680189900734,
      "grad_norm": 1.0484004988454474,
      "learning_rate": 2e-05,
      "loss": 0.8461496353149414,
      "step": 1830
    },
    {
      "epoch": 0.09926629261976694,
      "grad_norm": 1.1796374157652922,
      "learning_rate": 2e-05,
      "loss": 0.8495699882507324,
      "step": 1840
    },
    {
      "epoch": 0.09980578334052655,
      "grad_norm": 1.530009834654909,
      "learning_rate": 2e-05,
      "loss": 0.8529845237731933,
      "step": 1850
    },
    {
      "epoch": 0.10034527406128614,
      "grad_norm": 1.3821515513567662,
      "learning_rate": 2e-05,
      "loss": 0.8383827209472656,
      "step": 1860
    },
    {
      "epoch": 0.10088476478204575,
      "grad_norm": 1.433339075396923,
      "learning_rate": 2e-05,
      "loss": 0.8441427230834961,
      "step": 1870
    },
    {
      "epoch": 0.10142425550280536,
      "grad_norm": 1.4202627926244262,
      "learning_rate": 2e-05,
      "loss": 0.8355476379394531,
      "step": 1880
    },
    {
      "epoch": 0.10196374622356495,
      "grad_norm": 1.275529436709381,
      "learning_rate": 2e-05,
      "loss": 0.8475621223449707,
      "step": 1890
    },
    {
      "epoch": 0.10250323694432456,
      "grad_norm": 4.886608266675648,
      "learning_rate": 2e-05,
      "loss": 0.8222907066345215,
      "step": 1900
    },
    {
      "epoch": 0.10304272766508416,
      "grad_norm": 1.1032859405565207,
      "learning_rate": 2e-05,
      "loss": 0.8717263221740723,
      "step": 1910
    },
    {
      "epoch": 0.10358221838584376,
      "grad_norm": 1.4792708796316567,
      "learning_rate": 2e-05,
      "loss": 0.8422025680541992,
      "step": 1920
    },
    {
      "epoch": 0.10412170910660337,
      "grad_norm": 1.052829235330944,
      "learning_rate": 2e-05,
      "loss": 0.8275224685668945,
      "step": 1930
    },
    {
      "epoch": 0.10466119982736297,
      "grad_norm": 1.5243538008576782,
      "learning_rate": 2e-05,
      "loss": 0.8201045989990234,
      "step": 1940
    },
    {
      "epoch": 0.10520069054812257,
      "grad_norm": 1.8549508993672652,
      "learning_rate": 2e-05,
      "loss": 0.8507599830627441,
      "step": 1950
    },
    {
      "epoch": 0.10574018126888217,
      "grad_norm": 3.2676775863279293,
      "learning_rate": 2e-05,
      "loss": 0.8315736770629882,
      "step": 1960
    },
    {
      "epoch": 0.10627967198964178,
      "grad_norm": 3.170505632566329,
      "learning_rate": 2e-05,
      "loss": 0.8597011566162109,
      "step": 1970
    },
    {
      "epoch": 0.10681916271040139,
      "grad_norm": 1.225518275743383,
      "learning_rate": 2e-05,
      "loss": 0.8449475288391113,
      "step": 1980
    },
    {
      "epoch": 0.10735865343116098,
      "grad_norm": 1.7639666202458668,
      "learning_rate": 2e-05,
      "loss": 0.8267492294311524,
      "step": 1990
    },
    {
      "epoch": 0.10789814415192059,
      "grad_norm": 1.7820697092202835,
      "learning_rate": 2e-05,
      "loss": 0.8312843322753907,
      "step": 2000
    },
    {
      "epoch": 0.10843763487268018,
      "grad_norm": 4.015953726833389,
      "learning_rate": 2e-05,
      "loss": 0.8443691253662109,
      "step": 2010
    },
    {
      "epoch": 0.10897712559343979,
      "grad_norm": 1.999195946930485,
      "learning_rate": 2e-05,
      "loss": 0.8289900779724121,
      "step": 2020
    },
    {
      "epoch": 0.1095166163141994,
      "grad_norm": 1.8651265962731969,
      "learning_rate": 2e-05,
      "loss": 0.840304946899414,
      "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
}