{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15772748411099055,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007750736319950396,
      "grad_norm": 1.3823052644729614,
      "learning_rate": 2.910112359550562e-06,
      "loss": 0.7897,
      "step": 10
    },
    {
      "epoch": 0.0015501472639900791,
      "grad_norm": 1.15909743309021,
      "learning_rate": 3.921348314606742e-06,
      "loss": 0.7524,
      "step": 20
    },
    {
      "epoch": 0.002325220895985119,
      "grad_norm": 0.9035636186599731,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.7419,
      "step": 30
    },
    {
      "epoch": 0.0031002945279801583,
      "grad_norm": 0.7007580995559692,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.7113,
      "step": 40
    },
    {
      "epoch": 0.0038753681599751977,
      "grad_norm": 0.7174043655395508,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.7164,
      "step": 50
    },
    {
      "epoch": 0.004650441791970238,
      "grad_norm": 0.720160961151123,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.7077,
      "step": 60
    },
    {
      "epoch": 0.005425515423965277,
      "grad_norm": 0.6832423210144043,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.6898,
      "step": 70
    },
    {
      "epoch": 0.0062005890559603165,
      "grad_norm": 0.7489743232727051,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.7083,
      "step": 80
    },
    {
      "epoch": 0.0069756626879553555,
      "grad_norm": 0.7608446478843689,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.6885,
      "step": 90
    },
    {
      "epoch": 0.007750736319950395,
      "grad_norm": 0.7493481636047363,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.6888,
      "step": 100
    },
    {
      "epoch": 0.008525809951945434,
      "grad_norm": 0.7710257172584534,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.6827,
      "step": 110
    },
    {
      "epoch": 0.009300883583940475,
      "grad_norm": 0.797978401184082,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.716,
      "step": 120
    },
    {
      "epoch": 0.010075957215935514,
      "grad_norm": 0.7106821537017822,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.6825,
      "step": 130
    },
    {
      "epoch": 0.010851030847930553,
      "grad_norm": 0.6821442246437073,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.699,
      "step": 140
    },
    {
      "epoch": 0.011626104479925592,
      "grad_norm": 0.7108712792396545,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.6979,
      "step": 150
    },
    {
      "epoch": 0.012401178111920633,
      "grad_norm": 0.7028000354766846,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.6895,
      "step": 160
    },
    {
      "epoch": 0.013176251743915672,
      "grad_norm": 0.721693217754364,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.6835,
      "step": 170
    },
    {
      "epoch": 0.013951325375910711,
      "grad_norm": 0.589385449886322,
      "learning_rate": 2e-05,
      "loss": 0.6868,
      "step": 180
    },
    {
      "epoch": 0.014726399007905752,
      "grad_norm": 1.0280730724334717,
      "learning_rate": 2e-05,
      "loss": 0.7003,
      "step": 190
    },
    {
      "epoch": 0.01550147263990079,
      "grad_norm": 0.6079630255699158,
      "learning_rate": 2e-05,
      "loss": 0.6898,
      "step": 200
    },
    {
      "epoch": 0.01627654627189583,
      "grad_norm": 0.7045310139656067,
      "learning_rate": 2e-05,
      "loss": 0.6917,
      "step": 210
    },
    {
      "epoch": 0.01705161990389087,
      "grad_norm": 0.5710526704788208,
      "learning_rate": 2e-05,
      "loss": 0.6881,
      "step": 220
    },
    {
      "epoch": 0.01782669353588591,
      "grad_norm": 0.5788965225219727,
      "learning_rate": 2e-05,
      "loss": 0.702,
      "step": 230
    },
    {
      "epoch": 0.01860176716788095,
      "grad_norm": 0.6106708645820618,
      "learning_rate": 2e-05,
      "loss": 0.6864,
      "step": 240
    },
    {
      "epoch": 0.019376840799875988,
      "grad_norm": 0.561893105506897,
      "learning_rate": 2e-05,
      "loss": 0.6921,
      "step": 250
    },
    {
      "epoch": 0.02015191443187103,
      "grad_norm": 0.5690069794654846,
      "learning_rate": 2e-05,
      "loss": 0.6752,
      "step": 260
    },
    {
      "epoch": 0.020926988063866066,
      "grad_norm": 0.4941854774951935,
      "learning_rate": 2e-05,
      "loss": 0.6717,
      "step": 270
    },
    {
      "epoch": 0.021702061695861107,
      "grad_norm": 0.5330811738967896,
      "learning_rate": 2e-05,
      "loss": 0.68,
      "step": 280
    },
    {
      "epoch": 0.022477135327856147,
      "grad_norm": 0.5373284220695496,
      "learning_rate": 2e-05,
      "loss": 0.6864,
      "step": 290
    },
    {
      "epoch": 0.023252208959851185,
      "grad_norm": 0.4778149724006653,
      "learning_rate": 2e-05,
      "loss": 0.6953,
      "step": 300
    },
    {
      "epoch": 0.024027282591846225,
      "grad_norm": 0.509177565574646,
      "learning_rate": 2e-05,
      "loss": 0.6774,
      "step": 310
    },
    {
      "epoch": 0.024802356223841266,
      "grad_norm": 0.48862743377685547,
      "learning_rate": 2e-05,
      "loss": 0.6819,
      "step": 320
    },
    {
      "epoch": 0.025577429855836303,
      "grad_norm": 0.5163516402244568,
      "learning_rate": 2e-05,
      "loss": 0.688,
      "step": 330
    },
    {
      "epoch": 0.026352503487831344,
      "grad_norm": 0.48807498812675476,
      "learning_rate": 2e-05,
      "loss": 0.6817,
      "step": 340
    },
    {
      "epoch": 0.027127577119826385,
      "grad_norm": 0.5226020216941833,
      "learning_rate": 2e-05,
      "loss": 0.6873,
      "step": 350
    },
    {
      "epoch": 0.027902650751821422,
      "grad_norm": 0.48832374811172485,
      "learning_rate": 2e-05,
      "loss": 0.6793,
      "step": 360
    },
    {
      "epoch": 0.028677724383816463,
      "grad_norm": 0.5948355793952942,
      "learning_rate": 2e-05,
      "loss": 0.7136,
      "step": 370
    },
    {
      "epoch": 0.029452798015811504,
      "grad_norm": 0.47444790601730347,
      "learning_rate": 2e-05,
      "loss": 0.6893,
      "step": 380
    },
    {
      "epoch": 0.03022787164780654,
      "grad_norm": 0.46937182545661926,
      "learning_rate": 2e-05,
      "loss": 0.6799,
      "step": 390
    },
    {
      "epoch": 0.03100294527980158,
      "grad_norm": 0.4924728572368622,
      "learning_rate": 2e-05,
      "loss": 0.6882,
      "step": 400
    },
    {
      "epoch": 0.03177801891179662,
      "grad_norm": 0.46873292326927185,
      "learning_rate": 2e-05,
      "loss": 0.6784,
      "step": 410
    },
    {
      "epoch": 0.03255309254379166,
      "grad_norm": 0.5081288814544678,
      "learning_rate": 2e-05,
      "loss": 0.6673,
      "step": 420
    },
    {
      "epoch": 0.0333281661757867,
      "grad_norm": 0.48152658343315125,
      "learning_rate": 2e-05,
      "loss": 0.6891,
      "step": 430
    },
    {
      "epoch": 0.03410323980778174,
      "grad_norm": 0.5463388562202454,
      "learning_rate": 2e-05,
      "loss": 0.6737,
      "step": 440
    },
    {
      "epoch": 0.03487831343977678,
      "grad_norm": 0.493053674697876,
      "learning_rate": 2e-05,
      "loss": 0.6837,
      "step": 450
    },
    {
      "epoch": 0.03565338707177182,
      "grad_norm": 0.4562004506587982,
      "learning_rate": 2e-05,
      "loss": 0.6805,
      "step": 460
    },
    {
      "epoch": 0.03642846070376686,
      "grad_norm": 0.45049288868904114,
      "learning_rate": 2e-05,
      "loss": 0.6853,
      "step": 470
    },
    {
      "epoch": 0.0372035343357619,
      "grad_norm": 0.44892555475234985,
      "learning_rate": 2e-05,
      "loss": 0.6939,
      "step": 480
    },
    {
      "epoch": 0.037978607967756935,
      "grad_norm": 0.45876285433769226,
      "learning_rate": 2e-05,
      "loss": 0.6752,
      "step": 490
    },
    {
      "epoch": 0.038753681599751975,
      "grad_norm": 0.4538588523864746,
      "learning_rate": 2e-05,
      "loss": 0.6822,
      "step": 500
    },
    {
      "epoch": 0.039528755231747016,
      "grad_norm": 0.46754956245422363,
      "learning_rate": 2e-05,
      "loss": 0.6762,
      "step": 510
    },
    {
      "epoch": 0.04030382886374206,
      "grad_norm": 0.5183224081993103,
      "learning_rate": 2e-05,
      "loss": 0.6857,
      "step": 520
    },
    {
      "epoch": 0.0410789024957371,
      "grad_norm": 0.4643199145793915,
      "learning_rate": 2e-05,
      "loss": 0.6758,
      "step": 530
    },
    {
      "epoch": 0.04185397612773213,
      "grad_norm": 0.45650675892829895,
      "learning_rate": 2e-05,
      "loss": 0.6851,
      "step": 540
    },
    {
      "epoch": 0.04262904975972717,
      "grad_norm": 0.42580446600914,
      "learning_rate": 2e-05,
      "loss": 0.6841,
      "step": 550
    },
    {
      "epoch": 0.04340412339172221,
      "grad_norm": 0.4507347047328949,
      "learning_rate": 2e-05,
      "loss": 0.6803,
      "step": 560
    },
    {
      "epoch": 0.044179197023717254,
      "grad_norm": 0.447135329246521,
      "learning_rate": 2e-05,
      "loss": 0.6877,
      "step": 570
    },
    {
      "epoch": 0.044954270655712295,
      "grad_norm": 0.4340040981769562,
      "learning_rate": 2e-05,
      "loss": 0.6622,
      "step": 580
    },
    {
      "epoch": 0.045729344287707335,
      "grad_norm": 0.4411773383617401,
      "learning_rate": 2e-05,
      "loss": 0.6895,
      "step": 590
    },
    {
      "epoch": 0.04650441791970237,
      "grad_norm": 0.4499826729297638,
      "learning_rate": 2e-05,
      "loss": 0.6898,
      "step": 600
    },
    {
      "epoch": 0.04727949155169741,
      "grad_norm": 0.4610482156276703,
      "learning_rate": 2e-05,
      "loss": 0.6906,
      "step": 610
    },
    {
      "epoch": 0.04805456518369245,
      "grad_norm": 0.4646986126899719,
      "learning_rate": 2e-05,
      "loss": 0.6891,
      "step": 620
    },
    {
      "epoch": 0.04882963881568749,
      "grad_norm": 0.4380117654800415,
      "learning_rate": 2e-05,
      "loss": 0.6651,
      "step": 630
    },
    {
      "epoch": 0.04960471244768253,
      "grad_norm": 0.7984209656715393,
      "learning_rate": 2e-05,
      "loss": 0.675,
      "step": 640
    },
    {
      "epoch": 0.050379786079677566,
      "grad_norm": 0.45534566044807434,
      "learning_rate": 2e-05,
      "loss": 0.6737,
      "step": 650
    },
    {
      "epoch": 0.05115485971167261,
      "grad_norm": 0.43884512782096863,
      "learning_rate": 2e-05,
      "loss": 0.6748,
      "step": 660
    },
    {
      "epoch": 0.05192993334366765,
      "grad_norm": 0.45912545919418335,
      "learning_rate": 2e-05,
      "loss": 0.672,
      "step": 670
    },
    {
      "epoch": 0.05270500697566269,
      "grad_norm": 0.43527087569236755,
      "learning_rate": 2e-05,
      "loss": 0.6772,
      "step": 680
    },
    {
      "epoch": 0.05348008060765773,
      "grad_norm": 0.41790688037872314,
      "learning_rate": 2e-05,
      "loss": 0.6748,
      "step": 690
    },
    {
      "epoch": 0.05425515423965277,
      "grad_norm": 0.4713754951953888,
      "learning_rate": 2e-05,
      "loss": 0.6759,
      "step": 700
    },
    {
      "epoch": 0.055030227871647804,
      "grad_norm": 0.44159114360809326,
      "learning_rate": 2e-05,
      "loss": 0.6666,
      "step": 710
    },
    {
      "epoch": 0.055805301503642844,
      "grad_norm": 0.4281693696975708,
      "learning_rate": 2e-05,
      "loss": 0.6879,
      "step": 720
    },
    {
      "epoch": 0.056580375135637885,
      "grad_norm": 0.42915165424346924,
      "learning_rate": 2e-05,
      "loss": 0.6745,
      "step": 730
    },
    {
      "epoch": 0.057355448767632926,
      "grad_norm": 0.4454156160354614,
      "learning_rate": 2e-05,
      "loss": 0.6714,
      "step": 740
    },
    {
      "epoch": 0.05813052239962797,
      "grad_norm": 0.5239861607551575,
      "learning_rate": 2e-05,
      "loss": 0.6823,
      "step": 750
    },
    {
      "epoch": 0.05890559603162301,
      "grad_norm": 0.44252240657806396,
      "learning_rate": 2e-05,
      "loss": 0.6731,
      "step": 760
    },
    {
      "epoch": 0.05968066966361804,
      "grad_norm": 0.5074107646942139,
      "learning_rate": 2e-05,
      "loss": 0.684,
      "step": 770
    },
    {
      "epoch": 0.06045574329561308,
      "grad_norm": 0.4552975296974182,
      "learning_rate": 2e-05,
      "loss": 0.6836,
      "step": 780
    },
    {
      "epoch": 0.06123081692760812,
      "grad_norm": 0.42174383997917175,
      "learning_rate": 2e-05,
      "loss": 0.6717,
      "step": 790
    },
    {
      "epoch": 0.06200589055960316,
      "grad_norm": 0.44547125697135925,
      "learning_rate": 2e-05,
      "loss": 0.6775,
      "step": 800
    },
    {
      "epoch": 0.0627809641915982,
      "grad_norm": 0.44405683875083923,
      "learning_rate": 2e-05,
      "loss": 0.689,
      "step": 810
    },
    {
      "epoch": 0.06355603782359324,
      "grad_norm": 0.42822331190109253,
      "learning_rate": 2e-05,
      "loss": 0.6822,
      "step": 820
    },
    {
      "epoch": 0.06433111145558829,
      "grad_norm": 0.402357280254364,
      "learning_rate": 2e-05,
      "loss": 0.6716,
      "step": 830
    },
    {
      "epoch": 0.06510618508758333,
      "grad_norm": 0.43392375111579895,
      "learning_rate": 2e-05,
      "loss": 0.6689,
      "step": 840
    },
    {
      "epoch": 0.06588125871957835,
      "grad_norm": 0.4689558744430542,
      "learning_rate": 2e-05,
      "loss": 0.6846,
      "step": 850
    },
    {
      "epoch": 0.0666563323515734,
      "grad_norm": 0.4157777428627014,
      "learning_rate": 2e-05,
      "loss": 0.6812,
      "step": 860
    },
    {
      "epoch": 0.06743140598356843,
      "grad_norm": 0.5666890740394592,
      "learning_rate": 2e-05,
      "loss": 0.6693,
      "step": 870
    },
    {
      "epoch": 0.06820647961556348,
      "grad_norm": 0.40637901425361633,
      "learning_rate": 2e-05,
      "loss": 0.6894,
      "step": 880
    },
    {
      "epoch": 0.06898155324755852,
      "grad_norm": 0.42309945821762085,
      "learning_rate": 2e-05,
      "loss": 0.6705,
      "step": 890
    },
    {
      "epoch": 0.06975662687955356,
      "grad_norm": 0.429792195558548,
      "learning_rate": 2e-05,
      "loss": 0.6767,
      "step": 900
    },
    {
      "epoch": 0.0705317005115486,
      "grad_norm": 0.440060555934906,
      "learning_rate": 2e-05,
      "loss": 0.6687,
      "step": 910
    },
    {
      "epoch": 0.07130677414354364,
      "grad_norm": 0.4015533924102783,
      "learning_rate": 2e-05,
      "loss": 0.6719,
      "step": 920
    },
    {
      "epoch": 0.07208184777553868,
      "grad_norm": 0.43568137288093567,
      "learning_rate": 2e-05,
      "loss": 0.663,
      "step": 930
    },
    {
      "epoch": 0.07285692140753372,
      "grad_norm": 0.4287867844104767,
      "learning_rate": 2e-05,
      "loss": 0.677,
      "step": 940
    },
    {
      "epoch": 0.07363199503952876,
      "grad_norm": 0.43465718626976013,
      "learning_rate": 2e-05,
      "loss": 0.6782,
      "step": 950
    },
    {
      "epoch": 0.0744070686715238,
      "grad_norm": 0.4249207675457001,
      "learning_rate": 2e-05,
      "loss": 0.6627,
      "step": 960
    },
    {
      "epoch": 0.07518214230351883,
      "grad_norm": 0.42393025755882263,
      "learning_rate": 2e-05,
      "loss": 0.6832,
      "step": 970
    },
    {
      "epoch": 0.07595721593551387,
      "grad_norm": 0.442570298910141,
      "learning_rate": 2e-05,
      "loss": 0.6864,
      "step": 980
    },
    {
      "epoch": 0.07673228956750891,
      "grad_norm": 0.5258124470710754,
      "learning_rate": 2e-05,
      "loss": 0.6925,
      "step": 990
    },
    {
      "epoch": 0.07750736319950395,
      "grad_norm": 0.43202176690101624,
      "learning_rate": 2e-05,
      "loss": 0.6737,
      "step": 1000
    },
    {
      "epoch": 0.07828243683149899,
      "grad_norm": 0.39281439781188965,
      "learning_rate": 2e-05,
      "loss": 0.6673,
      "step": 1010
    },
    {
      "epoch": 0.07905751046349403,
      "grad_norm": 0.7493364214897156,
      "learning_rate": 2e-05,
      "loss": 0.6652,
      "step": 1020
    },
    {
      "epoch": 0.07983258409548907,
      "grad_norm": 0.4130217730998993,
      "learning_rate": 2e-05,
      "loss": 0.6437,
      "step": 1030
    },
    {
      "epoch": 0.08060765772748411,
      "grad_norm": 0.4456067681312561,
      "learning_rate": 2e-05,
      "loss": 0.6876,
      "step": 1040
    },
    {
      "epoch": 0.08138273135947915,
      "grad_norm": 0.50323885679245,
      "learning_rate": 2e-05,
      "loss": 0.6567,
      "step": 1050
    },
    {
      "epoch": 0.0821578049914742,
      "grad_norm": 0.44397807121276855,
      "learning_rate": 2e-05,
      "loss": 0.66,
      "step": 1060
    },
    {
      "epoch": 0.08293287862346924,
      "grad_norm": 0.4491206407546997,
      "learning_rate": 2e-05,
      "loss": 0.6703,
      "step": 1070
    },
    {
      "epoch": 0.08370795225546426,
      "grad_norm": 0.41675621271133423,
      "learning_rate": 2e-05,
      "loss": 0.675,
      "step": 1080
    },
    {
      "epoch": 0.0844830258874593,
      "grad_norm": 0.4307570457458496,
      "learning_rate": 2e-05,
      "loss": 0.6551,
      "step": 1090
    },
    {
      "epoch": 0.08525809951945434,
      "grad_norm": 0.4013335406780243,
      "learning_rate": 2e-05,
      "loss": 0.6557,
      "step": 1100
    },
    {
      "epoch": 0.08603317315144939,
      "grad_norm": 0.42541980743408203,
      "learning_rate": 2e-05,
      "loss": 0.6669,
      "step": 1110
    },
    {
      "epoch": 0.08680824678344443,
      "grad_norm": 0.4157240390777588,
      "learning_rate": 2e-05,
      "loss": 0.7118,
      "step": 1120
    },
    {
      "epoch": 0.08758332041543947,
      "grad_norm": 0.3873870074748993,
      "learning_rate": 2e-05,
      "loss": 0.6654,
      "step": 1130
    },
    {
      "epoch": 0.08835839404743451,
      "grad_norm": 0.4169309735298157,
      "learning_rate": 2e-05,
      "loss": 0.6718,
      "step": 1140
    },
    {
      "epoch": 0.08913346767942955,
      "grad_norm": 0.4192080497741699,
      "learning_rate": 2e-05,
      "loss": 0.6891,
      "step": 1150
    },
    {
      "epoch": 0.08990854131142459,
      "grad_norm": 0.3823591470718384,
      "learning_rate": 2e-05,
      "loss": 0.676,
      "step": 1160
    },
    {
      "epoch": 0.09068361494341963,
      "grad_norm": 0.4174516797065735,
      "learning_rate": 2e-05,
      "loss": 0.6688,
      "step": 1170
    },
    {
      "epoch": 0.09145868857541467,
      "grad_norm": 0.42104941606521606,
      "learning_rate": 2e-05,
      "loss": 0.6878,
      "step": 1180
    },
    {
      "epoch": 0.0922337622074097,
      "grad_norm": 0.42700275778770447,
      "learning_rate": 2e-05,
      "loss": 0.6584,
      "step": 1190
    },
    {
      "epoch": 0.09300883583940474,
      "grad_norm": 0.4459708034992218,
      "learning_rate": 2e-05,
      "loss": 0.6735,
      "step": 1200
    },
    {
      "epoch": 0.09378390947139978,
      "grad_norm": 0.4184398353099823,
      "learning_rate": 2e-05,
      "loss": 0.6737,
      "step": 1210
    },
    {
      "epoch": 0.09455898310339482,
      "grad_norm": 0.40880343317985535,
      "learning_rate": 2e-05,
      "loss": 0.6604,
      "step": 1220
    },
    {
      "epoch": 0.09533405673538986,
      "grad_norm": 0.422642320394516,
      "learning_rate": 2e-05,
      "loss": 0.6478,
      "step": 1230
    },
    {
      "epoch": 0.0961091303673849,
      "grad_norm": 0.40179723501205444,
      "learning_rate": 2e-05,
      "loss": 0.6808,
      "step": 1240
    },
    {
      "epoch": 0.09688420399937994,
      "grad_norm": 0.44401225447654724,
      "learning_rate": 2e-05,
      "loss": 0.6782,
      "step": 1250
    },
    {
      "epoch": 0.09765927763137498,
      "grad_norm": 0.4101133346557617,
      "learning_rate": 2e-05,
      "loss": 0.6558,
      "step": 1260
    },
    {
      "epoch": 0.09843435126337002,
      "grad_norm": 0.3988134562969208,
      "learning_rate": 2e-05,
      "loss": 0.6706,
      "step": 1270
    },
    {
      "epoch": 0.09920942489536506,
      "grad_norm": 0.43161827325820923,
      "learning_rate": 2e-05,
      "loss": 0.6577,
      "step": 1280
    },
    {
      "epoch": 0.0999844985273601,
      "grad_norm": 0.4305391311645508,
      "learning_rate": 2e-05,
      "loss": 0.6735,
      "step": 1290
    },
    {
      "epoch": 0.10075957215935513,
      "grad_norm": 0.5483478307723999,
      "learning_rate": 2e-05,
      "loss": 0.6824,
      "step": 1300
    },
    {
      "epoch": 0.10153464579135017,
      "grad_norm": 0.43918097019195557,
      "learning_rate": 2e-05,
      "loss": 0.6843,
      "step": 1310
    },
    {
      "epoch": 0.10230971942334521,
      "grad_norm": 0.4245496392250061,
      "learning_rate": 2e-05,
      "loss": 0.6784,
      "step": 1320
    },
    {
      "epoch": 0.10308479305534025,
      "grad_norm": 0.42245975136756897,
      "learning_rate": 2e-05,
      "loss": 0.6602,
      "step": 1330
    },
    {
      "epoch": 0.1038598666873353,
      "grad_norm": 0.42837628722190857,
      "learning_rate": 2e-05,
      "loss": 0.6665,
      "step": 1340
    },
    {
      "epoch": 0.10463494031933034,
      "grad_norm": 0.4032275080680847,
      "learning_rate": 2e-05,
      "loss": 0.6619,
      "step": 1350
    },
    {
      "epoch": 0.10541001395132538,
      "grad_norm": 0.41980066895484924,
      "learning_rate": 2e-05,
      "loss": 0.6516,
      "step": 1360
    },
    {
      "epoch": 0.10618508758332042,
      "grad_norm": 0.4778800308704376,
      "learning_rate": 2e-05,
      "loss": 0.6634,
      "step": 1370
    },
    {
      "epoch": 0.10696016121531546,
      "grad_norm": 0.4086174964904785,
      "learning_rate": 2e-05,
      "loss": 0.6706,
      "step": 1380
    },
    {
      "epoch": 0.1077352348473105,
      "grad_norm": 0.39581477642059326,
      "learning_rate": 2e-05,
      "loss": 0.6601,
      "step": 1390
    },
    {
      "epoch": 0.10851030847930554,
      "grad_norm": 0.4274316132068634,
      "learning_rate": 2e-05,
      "loss": 0.6553,
      "step": 1400
    },
    {
      "epoch": 0.10928538211130058,
      "grad_norm": 1.0265446901321411,
      "learning_rate": 2e-05,
      "loss": 0.648,
      "step": 1410
    },
    {
      "epoch": 0.11006045574329561,
      "grad_norm": 0.3895666003227234,
      "learning_rate": 2e-05,
      "loss": 0.6377,
      "step": 1420
    },
    {
      "epoch": 0.11083552937529065,
      "grad_norm": 0.40829238295555115,
      "learning_rate": 2e-05,
      "loss": 0.659,
      "step": 1430
    },
    {
      "epoch": 0.11161060300728569,
      "grad_norm": 0.417646199464798,
      "learning_rate": 2e-05,
      "loss": 0.6935,
      "step": 1440
    },
    {
      "epoch": 0.11238567663928073,
      "grad_norm": 0.4010778069496155,
      "learning_rate": 2e-05,
      "loss": 0.6758,
      "step": 1450
    },
    {
      "epoch": 0.11316075027127577,
      "grad_norm": 0.4173222780227661,
      "learning_rate": 2e-05,
      "loss": 0.6724,
      "step": 1460
    },
    {
      "epoch": 0.11393582390327081,
      "grad_norm": 0.4018092155456543,
      "learning_rate": 2e-05,
      "loss": 0.6701,
      "step": 1470
    },
    {
      "epoch": 0.11471089753526585,
      "grad_norm": 0.43614667654037476,
      "learning_rate": 2e-05,
      "loss": 0.6796,
      "step": 1480
    },
    {
      "epoch": 0.11548597116726089,
      "grad_norm": 0.41816315054893494,
      "learning_rate": 2e-05,
      "loss": 0.6773,
      "step": 1490
    },
    {
      "epoch": 0.11626104479925593,
      "grad_norm": 0.39446917176246643,
      "learning_rate": 2e-05,
      "loss": 0.6608,
      "step": 1500
    },
    {
      "epoch": 0.11703611843125097,
      "grad_norm": 0.447988897562027,
      "learning_rate": 2e-05,
      "loss": 0.6654,
      "step": 1510
    },
    {
      "epoch": 0.11781119206324601,
      "grad_norm": 0.41491132974624634,
      "learning_rate": 2e-05,
      "loss": 0.6858,
      "step": 1520
    },
    {
      "epoch": 0.11858626569524104,
      "grad_norm": 0.406842976808548,
      "learning_rate": 2e-05,
      "loss": 0.6686,
      "step": 1530
    },
    {
      "epoch": 0.11936133932723608,
      "grad_norm": 0.6441549062728882,
      "learning_rate": 2e-05,
      "loss": 0.6552,
      "step": 1540
    },
    {
      "epoch": 0.12013641295923112,
      "grad_norm": 0.4140605628490448,
      "learning_rate": 2e-05,
      "loss": 0.6547,
      "step": 1550
    },
    {
      "epoch": 0.12091148659122616,
      "grad_norm": 0.41722798347473145,
      "learning_rate": 2e-05,
      "loss": 0.6582,
      "step": 1560
    },
    {
      "epoch": 0.1216865602232212,
      "grad_norm": 0.43592479825019836,
      "learning_rate": 2e-05,
      "loss": 0.6687,
      "step": 1570
    },
    {
      "epoch": 0.12246163385521625,
      "grad_norm": 0.4203198552131653,
      "learning_rate": 2e-05,
      "loss": 0.6691,
      "step": 1580
    },
    {
      "epoch": 0.12323670748721129,
      "grad_norm": 0.4950765371322632,
      "learning_rate": 2e-05,
      "loss": 0.6769,
      "step": 1590
    },
    {
      "epoch": 0.12401178111920633,
      "grad_norm": 0.4129418432712555,
      "learning_rate": 2e-05,
      "loss": 0.6696,
      "step": 1600
    },
    {
      "epoch": 0.12478685475120137,
      "grad_norm": 0.4015454053878784,
      "learning_rate": 2e-05,
      "loss": 0.6594,
      "step": 1610
    },
    {
      "epoch": 0.1255619283831964,
      "grad_norm": 0.40145838260650635,
      "learning_rate": 2e-05,
      "loss": 0.6548,
      "step": 1620
    },
    {
      "epoch": 0.12633700201519144,
      "grad_norm": 0.40511614084243774,
      "learning_rate": 2e-05,
      "loss": 0.6583,
      "step": 1630
    },
    {
      "epoch": 0.1271120756471865,
      "grad_norm": 0.4618526101112366,
      "learning_rate": 2e-05,
      "loss": 0.6596,
      "step": 1640
    },
    {
      "epoch": 0.12788714927918152,
      "grad_norm": 0.4379795789718628,
      "learning_rate": 2e-05,
      "loss": 0.6816,
      "step": 1650
    },
    {
      "epoch": 0.12866222291117657,
      "grad_norm": 0.5952076315879822,
      "learning_rate": 2e-05,
      "loss": 0.6773,
      "step": 1660
    },
    {
      "epoch": 0.1294372965431716,
      "grad_norm": 0.39318859577178955,
      "learning_rate": 2e-05,
      "loss": 0.6531,
      "step": 1670
    },
    {
      "epoch": 0.13021237017516665,
      "grad_norm": 0.4082723557949066,
      "learning_rate": 2e-05,
      "loss": 0.6623,
      "step": 1680
    },
    {
      "epoch": 0.13098744380716168,
      "grad_norm": 0.4530302584171295,
      "learning_rate": 2e-05,
      "loss": 0.6684,
      "step": 1690
    },
    {
      "epoch": 0.1317625174391567,
      "grad_norm": 0.43130335211753845,
      "learning_rate": 2e-05,
      "loss": 0.6514,
      "step": 1700
    },
    {
      "epoch": 0.13253759107115176,
      "grad_norm": 0.4232826828956604,
      "learning_rate": 2e-05,
      "loss": 0.6621,
      "step": 1710
    },
    {
      "epoch": 0.1333126647031468,
      "grad_norm": 0.4304817318916321,
      "learning_rate": 2e-05,
      "loss": 0.6542,
      "step": 1720
    },
    {
      "epoch": 0.13408773833514184,
      "grad_norm": 0.40232929587364197,
      "learning_rate": 2e-05,
      "loss": 0.6736,
      "step": 1730
    },
    {
      "epoch": 0.13486281196713687,
      "grad_norm": 0.39328262209892273,
      "learning_rate": 2e-05,
      "loss": 0.6634,
      "step": 1740
    },
    {
      "epoch": 0.13563788559913192,
      "grad_norm": 0.384797602891922,
      "learning_rate": 2e-05,
      "loss": 0.6591,
      "step": 1750
    },
    {
      "epoch": 0.13641295923112695,
      "grad_norm": 0.39744696021080017,
      "learning_rate": 2e-05,
      "loss": 0.6552,
      "step": 1760
    },
    {
      "epoch": 0.137188032863122,
      "grad_norm": 0.8520597219467163,
      "learning_rate": 2e-05,
      "loss": 0.6649,
      "step": 1770
    },
    {
      "epoch": 0.13796310649511703,
      "grad_norm": 0.402743399143219,
      "learning_rate": 2e-05,
      "loss": 0.6639,
      "step": 1780
    },
    {
      "epoch": 0.1387381801271121,
      "grad_norm": 0.40198618173599243,
      "learning_rate": 2e-05,
      "loss": 0.6653,
      "step": 1790
    },
    {
      "epoch": 0.13951325375910711,
      "grad_norm": 0.41853809356689453,
      "learning_rate": 2e-05,
      "loss": 0.6823,
      "step": 1800
    },
    {
      "epoch": 0.14028832739110214,
      "grad_norm": 1.1882494688034058,
      "learning_rate": 2e-05,
      "loss": 0.6481,
      "step": 1810
    },
    {
      "epoch": 0.1410634010230972,
      "grad_norm": 0.5747016668319702,
      "learning_rate": 2e-05,
      "loss": 0.662,
      "step": 1820
    },
    {
      "epoch": 0.14183847465509222,
      "grad_norm": 0.41559216380119324,
      "learning_rate": 2e-05,
      "loss": 0.669,
      "step": 1830
    },
    {
      "epoch": 0.14261354828708728,
      "grad_norm": 0.3821167051792145,
      "learning_rate": 2e-05,
      "loss": 0.6656,
      "step": 1840
    },
    {
      "epoch": 0.1433886219190823,
      "grad_norm": 0.4053109884262085,
      "learning_rate": 2e-05,
      "loss": 0.658,
      "step": 1850
    },
    {
      "epoch": 0.14416369555107736,
      "grad_norm": 0.8168757557868958,
      "learning_rate": 2e-05,
      "loss": 0.67,
      "step": 1860
    },
    {
      "epoch": 0.14493876918307239,
      "grad_norm": 0.42168760299682617,
      "learning_rate": 2e-05,
      "loss": 0.6597,
      "step": 1870
    },
    {
      "epoch": 0.14571384281506744,
      "grad_norm": 0.42126354575157166,
      "learning_rate": 2e-05,
      "loss": 0.6661,
      "step": 1880
    },
    {
      "epoch": 0.14648891644706247,
      "grad_norm": 0.4499135911464691,
      "learning_rate": 2e-05,
      "loss": 0.6592,
      "step": 1890
    },
    {
      "epoch": 0.14726399007905752,
      "grad_norm": 0.42486631870269775,
      "learning_rate": 2e-05,
      "loss": 0.6424,
      "step": 1900
    },
    {
      "epoch": 0.14803906371105255,
      "grad_norm": 0.3847733736038208,
      "learning_rate": 2e-05,
      "loss": 0.6635,
      "step": 1910
    },
    {
      "epoch": 0.1488141373430476,
      "grad_norm": 0.4100988507270813,
      "learning_rate": 2e-05,
      "loss": 0.6558,
      "step": 1920
    },
    {
      "epoch": 0.14958921097504263,
      "grad_norm": 0.4142761826515198,
      "learning_rate": 2e-05,
      "loss": 0.6635,
      "step": 1930
    },
    {
      "epoch": 0.15036428460703766,
      "grad_norm": 0.40710175037384033,
      "learning_rate": 2e-05,
      "loss": 0.6742,
      "step": 1940
    },
    {
      "epoch": 0.1511393582390327,
      "grad_norm": 0.4328700602054596,
      "learning_rate": 2e-05,
      "loss": 0.6715,
      "step": 1950
    },
    {
      "epoch": 0.15191443187102774,
      "grad_norm": 0.605353593826294,
      "learning_rate": 2e-05,
      "loss": 0.6495,
      "step": 1960
    },
    {
      "epoch": 0.1526895055030228,
      "grad_norm": 0.5102190971374512,
      "learning_rate": 2e-05,
      "loss": 0.6644,
      "step": 1970
    },
    {
      "epoch": 0.15346457913501782,
      "grad_norm": 0.45153525471687317,
      "learning_rate": 2e-05,
      "loss": 0.6451,
      "step": 1980
    },
    {
      "epoch": 0.15423965276701287,
      "grad_norm": 0.4187360107898712,
      "learning_rate": 2e-05,
      "loss": 0.6549,
      "step": 1990
    },
    {
      "epoch": 0.1550147263990079,
      "grad_norm": 0.41170287132263184,
      "learning_rate": 2e-05,
      "loss": 0.6661,
      "step": 2000
    },
    {
      "epoch": 0.15578980003100296,
      "grad_norm": 0.3859499990940094,
      "learning_rate": 2e-05,
      "loss": 0.6571,
      "step": 2010
    },
    {
      "epoch": 0.15656487366299798,
      "grad_norm": 0.38852736353874207,
      "learning_rate": 2e-05,
      "loss": 0.6679,
      "step": 2020
    },
    {
      "epoch": 0.15733994729499304,
      "grad_norm": 0.4105587601661682,
      "learning_rate": 2e-05,
      "loss": 0.6436,
      "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": 9.084295122442519e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}