{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10650546919976972,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005233683990160674,
      "grad_norm": 1.1370724439620972,
      "learning_rate": 2.910112359550562e-06,
      "loss": 0.8003,
      "step": 10
    },
    {
      "epoch": 0.0010467367980321349,
      "grad_norm": 0.9877656102180481,
      "learning_rate": 3.921348314606742e-06,
      "loss": 0.7587,
      "step": 20
    },
    {
      "epoch": 0.0015701051970482022,
      "grad_norm": 0.8628589510917664,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.7476,
      "step": 30
    },
    {
      "epoch": 0.0020934735960642698,
      "grad_norm": 0.7837583422660828,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.7334,
      "step": 40
    },
    {
      "epoch": 0.002616841995080337,
      "grad_norm": 0.7342932224273682,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.7397,
      "step": 50
    },
    {
      "epoch": 0.0031402103940964044,
      "grad_norm": 0.9271304607391357,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.7296,
      "step": 60
    },
    {
      "epoch": 0.0036635787931124718,
      "grad_norm": 0.8066033720970154,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.6864,
      "step": 70
    },
    {
      "epoch": 0.0041869471921285395,
      "grad_norm": 0.8114457726478577,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.6792,
      "step": 80
    },
    {
      "epoch": 0.004710315591144607,
      "grad_norm": 0.8880093097686768,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.7508,
      "step": 90
    },
    {
      "epoch": 0.005233683990160674,
      "grad_norm": 1.1273611783981323,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.6849,
      "step": 100
    },
    {
      "epoch": 0.0057570523891767415,
      "grad_norm": 0.7791317701339722,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.698,
      "step": 110
    },
    {
      "epoch": 0.006280420788192809,
      "grad_norm": 0.8140974044799805,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.6947,
      "step": 120
    },
    {
      "epoch": 0.006803789187208876,
      "grad_norm": 0.8656443357467651,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.7158,
      "step": 130
    },
    {
      "epoch": 0.0073271575862249435,
      "grad_norm": 0.744526743888855,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.6701,
      "step": 140
    },
    {
      "epoch": 0.00785052598524101,
      "grad_norm": 0.7715036273002625,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.6794,
      "step": 150
    },
    {
      "epoch": 0.008373894384257079,
      "grad_norm": 0.7816882729530334,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.7059,
      "step": 160
    },
    {
      "epoch": 0.008897262783273146,
      "grad_norm": 0.7964625954627991,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.6954,
      "step": 170
    },
    {
      "epoch": 0.009420631182289214,
      "grad_norm": 1.0829215049743652,
      "learning_rate": 2e-05,
      "loss": 0.6888,
      "step": 180
    },
    {
      "epoch": 0.00994399958130528,
      "grad_norm": 0.6891264319419861,
      "learning_rate": 2e-05,
      "loss": 0.6539,
      "step": 190
    },
    {
      "epoch": 0.010467367980321348,
      "grad_norm": 0.7293897867202759,
      "learning_rate": 2e-05,
      "loss": 0.7164,
      "step": 200
    },
    {
      "epoch": 0.010990736379337415,
      "grad_norm": 0.6318921446800232,
      "learning_rate": 2e-05,
      "loss": 0.7084,
      "step": 210
    },
    {
      "epoch": 0.011514104778353483,
      "grad_norm": 0.6405470371246338,
      "learning_rate": 2e-05,
      "loss": 0.6812,
      "step": 220
    },
    {
      "epoch": 0.012037473177369551,
      "grad_norm": 0.6632219552993774,
      "learning_rate": 2e-05,
      "loss": 0.6733,
      "step": 230
    },
    {
      "epoch": 0.012560841576385618,
      "grad_norm": 0.7196585536003113,
      "learning_rate": 2e-05,
      "loss": 0.6835,
      "step": 240
    },
    {
      "epoch": 0.013084209975401686,
      "grad_norm": 0.5942214131355286,
      "learning_rate": 2e-05,
      "loss": 0.6613,
      "step": 250
    },
    {
      "epoch": 0.013607578374417752,
      "grad_norm": 0.5716996788978577,
      "learning_rate": 2e-05,
      "loss": 0.6759,
      "step": 260
    },
    {
      "epoch": 0.01413094677343382,
      "grad_norm": 0.5713549256324768,
      "learning_rate": 2e-05,
      "loss": 0.7041,
      "step": 270
    },
    {
      "epoch": 0.014654315172449887,
      "grad_norm": 0.5658433437347412,
      "learning_rate": 2e-05,
      "loss": 0.6866,
      "step": 280
    },
    {
      "epoch": 0.015177683571465955,
      "grad_norm": 0.5381125211715698,
      "learning_rate": 2e-05,
      "loss": 0.7024,
      "step": 290
    },
    {
      "epoch": 0.01570105197048202,
      "grad_norm": 0.5079479217529297,
      "learning_rate": 2e-05,
      "loss": 0.686,
      "step": 300
    },
    {
      "epoch": 0.016224420369498088,
      "grad_norm": 0.5530030727386475,
      "learning_rate": 2e-05,
      "loss": 0.6912,
      "step": 310
    },
    {
      "epoch": 0.016747788768514158,
      "grad_norm": 0.5396811962127686,
      "learning_rate": 2e-05,
      "loss": 0.6751,
      "step": 320
    },
    {
      "epoch": 0.017271157167530225,
      "grad_norm": 0.4894005060195923,
      "learning_rate": 2e-05,
      "loss": 0.6649,
      "step": 330
    },
    {
      "epoch": 0.01779452556654629,
      "grad_norm": 0.5230134129524231,
      "learning_rate": 2e-05,
      "loss": 0.684,
      "step": 340
    },
    {
      "epoch": 0.01831789396556236,
      "grad_norm": 0.5332402586936951,
      "learning_rate": 2e-05,
      "loss": 0.6767,
      "step": 350
    },
    {
      "epoch": 0.018841262364578427,
      "grad_norm": 0.5048417448997498,
      "learning_rate": 2e-05,
      "loss": 0.6922,
      "step": 360
    },
    {
      "epoch": 0.019364630763594494,
      "grad_norm": 0.5345087051391602,
      "learning_rate": 2e-05,
      "loss": 0.6976,
      "step": 370
    },
    {
      "epoch": 0.01988799916261056,
      "grad_norm": 0.511880099773407,
      "learning_rate": 2e-05,
      "loss": 0.6814,
      "step": 380
    },
    {
      "epoch": 0.02041136756162663,
      "grad_norm": 0.46280574798583984,
      "learning_rate": 2e-05,
      "loss": 0.6566,
      "step": 390
    },
    {
      "epoch": 0.020934735960642697,
      "grad_norm": 0.464054137468338,
      "learning_rate": 2e-05,
      "loss": 0.6483,
      "step": 400
    },
    {
      "epoch": 0.021458104359658763,
      "grad_norm": 0.5449008941650391,
      "learning_rate": 2e-05,
      "loss": 0.6841,
      "step": 410
    },
    {
      "epoch": 0.02198147275867483,
      "grad_norm": 0.5352079272270203,
      "learning_rate": 2e-05,
      "loss": 0.6604,
      "step": 420
    },
    {
      "epoch": 0.0225048411576909,
      "grad_norm": 0.5088271498680115,
      "learning_rate": 2e-05,
      "loss": 0.6683,
      "step": 430
    },
    {
      "epoch": 0.023028209556706966,
      "grad_norm": 0.5593430399894714,
      "learning_rate": 2e-05,
      "loss": 0.6795,
      "step": 440
    },
    {
      "epoch": 0.023551577955723033,
      "grad_norm": 0.507481575012207,
      "learning_rate": 2e-05,
      "loss": 0.6654,
      "step": 450
    },
    {
      "epoch": 0.024074946354739103,
      "grad_norm": 0.4815616011619568,
      "learning_rate": 2e-05,
      "loss": 0.6843,
      "step": 460
    },
    {
      "epoch": 0.02459831475375517,
      "grad_norm": 0.5703353881835938,
      "learning_rate": 2e-05,
      "loss": 0.6598,
      "step": 470
    },
    {
      "epoch": 0.025121683152771235,
      "grad_norm": 0.48705339431762695,
      "learning_rate": 2e-05,
      "loss": 0.6614,
      "step": 480
    },
    {
      "epoch": 0.025645051551787302,
      "grad_norm": 0.547533392906189,
      "learning_rate": 2e-05,
      "loss": 0.6585,
      "step": 490
    },
    {
      "epoch": 0.026168419950803372,
      "grad_norm": 0.6569129228591919,
      "learning_rate": 2e-05,
      "loss": 0.6716,
      "step": 500
    },
    {
      "epoch": 0.02669178834981944,
      "grad_norm": 0.5733374357223511,
      "learning_rate": 2e-05,
      "loss": 0.6465,
      "step": 510
    },
    {
      "epoch": 0.027215156748835505,
      "grad_norm": 0.4885842502117157,
      "learning_rate": 2e-05,
      "loss": 0.682,
      "step": 520
    },
    {
      "epoch": 0.02773852514785157,
      "grad_norm": 0.42785435914993286,
      "learning_rate": 2e-05,
      "loss": 0.6594,
      "step": 530
    },
    {
      "epoch": 0.02826189354686764,
      "grad_norm": 0.4955022931098938,
      "learning_rate": 2e-05,
      "loss": 0.6674,
      "step": 540
    },
    {
      "epoch": 0.028785261945883708,
      "grad_norm": 0.48021453619003296,
      "learning_rate": 2e-05,
      "loss": 0.6796,
      "step": 550
    },
    {
      "epoch": 0.029308630344899774,
      "grad_norm": 0.4767313301563263,
      "learning_rate": 2e-05,
      "loss": 0.6865,
      "step": 560
    },
    {
      "epoch": 0.029831998743915844,
      "grad_norm": 0.5284311771392822,
      "learning_rate": 2e-05,
      "loss": 0.6489,
      "step": 570
    },
    {
      "epoch": 0.03035536714293191,
      "grad_norm": 0.4461924731731415,
      "learning_rate": 2e-05,
      "loss": 0.686,
      "step": 580
    },
    {
      "epoch": 0.030878735541947977,
      "grad_norm": 0.45115983486175537,
      "learning_rate": 2e-05,
      "loss": 0.6539,
      "step": 590
    },
    {
      "epoch": 0.03140210394096404,
      "grad_norm": 0.5064119100570679,
      "learning_rate": 2e-05,
      "loss": 0.6946,
      "step": 600
    },
    {
      "epoch": 0.03192547233998011,
      "grad_norm": 0.5319550037384033,
      "learning_rate": 2e-05,
      "loss": 0.645,
      "step": 610
    },
    {
      "epoch": 0.032448840738996176,
      "grad_norm": 0.4419703781604767,
      "learning_rate": 2e-05,
      "loss": 0.7003,
      "step": 620
    },
    {
      "epoch": 0.03297220913801225,
      "grad_norm": 0.42887452244758606,
      "learning_rate": 2e-05,
      "loss": 0.6783,
      "step": 630
    },
    {
      "epoch": 0.033495577537028316,
      "grad_norm": 0.46661144495010376,
      "learning_rate": 2e-05,
      "loss": 0.6686,
      "step": 640
    },
    {
      "epoch": 0.03401894593604438,
      "grad_norm": 0.5283986330032349,
      "learning_rate": 2e-05,
      "loss": 0.6679,
      "step": 650
    },
    {
      "epoch": 0.03454231433506045,
      "grad_norm": 0.5113454461097717,
      "learning_rate": 2e-05,
      "loss": 0.6506,
      "step": 660
    },
    {
      "epoch": 0.035065682734076516,
      "grad_norm": 0.4744948148727417,
      "learning_rate": 2e-05,
      "loss": 0.6724,
      "step": 670
    },
    {
      "epoch": 0.03558905113309258,
      "grad_norm": 0.49696066975593567,
      "learning_rate": 2e-05,
      "loss": 0.6652,
      "step": 680
    },
    {
      "epoch": 0.03611241953210865,
      "grad_norm": 0.7813011407852173,
      "learning_rate": 2e-05,
      "loss": 0.6621,
      "step": 690
    },
    {
      "epoch": 0.03663578793112472,
      "grad_norm": 0.49424248933792114,
      "learning_rate": 2e-05,
      "loss": 0.6727,
      "step": 700
    },
    {
      "epoch": 0.03715915633014079,
      "grad_norm": 0.4447154104709625,
      "learning_rate": 2e-05,
      "loss": 0.6659,
      "step": 710
    },
    {
      "epoch": 0.037682524729156855,
      "grad_norm": 0.44892066717147827,
      "learning_rate": 2e-05,
      "loss": 0.6554,
      "step": 720
    },
    {
      "epoch": 0.03820589312817292,
      "grad_norm": 0.49734535813331604,
      "learning_rate": 2e-05,
      "loss": 0.6779,
      "step": 730
    },
    {
      "epoch": 0.03872926152718899,
      "grad_norm": 0.5591990947723389,
      "learning_rate": 2e-05,
      "loss": 0.6927,
      "step": 740
    },
    {
      "epoch": 0.039252629926205054,
      "grad_norm": 0.45224255323410034,
      "learning_rate": 2e-05,
      "loss": 0.6398,
      "step": 750
    },
    {
      "epoch": 0.03977599832522112,
      "grad_norm": 0.41793182492256165,
      "learning_rate": 2e-05,
      "loss": 0.6668,
      "step": 760
    },
    {
      "epoch": 0.04029936672423719,
      "grad_norm": 0.43993815779685974,
      "learning_rate": 2e-05,
      "loss": 0.6456,
      "step": 770
    },
    {
      "epoch": 0.04082273512325326,
      "grad_norm": 0.44372230768203735,
      "learning_rate": 2e-05,
      "loss": 0.6669,
      "step": 780
    },
    {
      "epoch": 0.04134610352226933,
      "grad_norm": 0.4827944040298462,
      "learning_rate": 2e-05,
      "loss": 0.657,
      "step": 790
    },
    {
      "epoch": 0.041869471921285394,
      "grad_norm": 0.4187488257884979,
      "learning_rate": 2e-05,
      "loss": 0.6456,
      "step": 800
    },
    {
      "epoch": 0.04239284032030146,
      "grad_norm": 0.47213008999824524,
      "learning_rate": 2e-05,
      "loss": 0.6555,
      "step": 810
    },
    {
      "epoch": 0.042916208719317527,
      "grad_norm": 0.43557852506637573,
      "learning_rate": 2e-05,
      "loss": 0.6545,
      "step": 820
    },
    {
      "epoch": 0.04343957711833359,
      "grad_norm": 0.45871806144714355,
      "learning_rate": 2e-05,
      "loss": 0.6538,
      "step": 830
    },
    {
      "epoch": 0.04396294551734966,
      "grad_norm": 0.46028947830200195,
      "learning_rate": 2e-05,
      "loss": 0.6356,
      "step": 840
    },
    {
      "epoch": 0.04448631391636573,
      "grad_norm": 0.548116147518158,
      "learning_rate": 2e-05,
      "loss": 0.6872,
      "step": 850
    },
    {
      "epoch": 0.0450096823153818,
      "grad_norm": 0.49427151679992676,
      "learning_rate": 2e-05,
      "loss": 0.6372,
      "step": 860
    },
    {
      "epoch": 0.045533050714397866,
      "grad_norm": 0.46103739738464355,
      "learning_rate": 2e-05,
      "loss": 0.6991,
      "step": 870
    },
    {
      "epoch": 0.04605641911341393,
      "grad_norm": 0.4400480091571808,
      "learning_rate": 2e-05,
      "loss": 0.667,
      "step": 880
    },
    {
      "epoch": 0.04657978751243,
      "grad_norm": 0.45002153515815735,
      "learning_rate": 2e-05,
      "loss": 0.6582,
      "step": 890
    },
    {
      "epoch": 0.047103155911446065,
      "grad_norm": 0.44472604990005493,
      "learning_rate": 2e-05,
      "loss": 0.6706,
      "step": 900
    },
    {
      "epoch": 0.04762652431046213,
      "grad_norm": 0.4121211767196655,
      "learning_rate": 2e-05,
      "loss": 0.6602,
      "step": 910
    },
    {
      "epoch": 0.048149892709478205,
      "grad_norm": 0.5010108351707458,
      "learning_rate": 2e-05,
      "loss": 0.6761,
      "step": 920
    },
    {
      "epoch": 0.04867326110849427,
      "grad_norm": 0.45920342206954956,
      "learning_rate": 2e-05,
      "loss": 0.6671,
      "step": 930
    },
    {
      "epoch": 0.04919662950751034,
      "grad_norm": 0.5177173018455505,
      "learning_rate": 2e-05,
      "loss": 0.652,
      "step": 940
    },
    {
      "epoch": 0.049719997906526404,
      "grad_norm": 0.49086499214172363,
      "learning_rate": 2e-05,
      "loss": 0.6795,
      "step": 950
    },
    {
      "epoch": 0.05024336630554247,
      "grad_norm": 0.582841157913208,
      "learning_rate": 2e-05,
      "loss": 0.6376,
      "step": 960
    },
    {
      "epoch": 0.05076673470455854,
      "grad_norm": 0.4690440595149994,
      "learning_rate": 2e-05,
      "loss": 0.6465,
      "step": 970
    },
    {
      "epoch": 0.051290103103574604,
      "grad_norm": 0.45363402366638184,
      "learning_rate": 2e-05,
      "loss": 0.6511,
      "step": 980
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 0.43920376896858215,
      "learning_rate": 2e-05,
      "loss": 0.6943,
      "step": 990
    },
    {
      "epoch": 0.052336839901606744,
      "grad_norm": 0.421144038438797,
      "learning_rate": 2e-05,
      "loss": 0.6434,
      "step": 1000
    },
    {
      "epoch": 0.05286020830062281,
      "grad_norm": 0.45188188552856445,
      "learning_rate": 2e-05,
      "loss": 0.6467,
      "step": 1010
    },
    {
      "epoch": 0.05338357669963888,
      "grad_norm": 0.4339853823184967,
      "learning_rate": 2e-05,
      "loss": 0.6596,
      "step": 1020
    },
    {
      "epoch": 0.05390694509865494,
      "grad_norm": 0.4234607517719269,
      "learning_rate": 2e-05,
      "loss": 0.674,
      "step": 1030
    },
    {
      "epoch": 0.05443031349767101,
      "grad_norm": 0.46552717685699463,
      "learning_rate": 2e-05,
      "loss": 0.6649,
      "step": 1040
    },
    {
      "epoch": 0.054953681896687076,
      "grad_norm": 0.4405843913555145,
      "learning_rate": 2e-05,
      "loss": 0.6577,
      "step": 1050
    },
    {
      "epoch": 0.05547705029570314,
      "grad_norm": 0.5044958591461182,
      "learning_rate": 2e-05,
      "loss": 0.6152,
      "step": 1060
    },
    {
      "epoch": 0.056000418694719216,
      "grad_norm": 0.43265852332115173,
      "learning_rate": 2e-05,
      "loss": 0.6317,
      "step": 1070
    },
    {
      "epoch": 0.05652378709373528,
      "grad_norm": 0.41526952385902405,
      "learning_rate": 2e-05,
      "loss": 0.6501,
      "step": 1080
    },
    {
      "epoch": 0.05704715549275135,
      "grad_norm": 0.43947693705558777,
      "learning_rate": 2e-05,
      "loss": 0.6542,
      "step": 1090
    },
    {
      "epoch": 0.057570523891767415,
      "grad_norm": 0.4375130534172058,
      "learning_rate": 2e-05,
      "loss": 0.671,
      "step": 1100
    },
    {
      "epoch": 0.05809389229078348,
      "grad_norm": 0.4554004371166229,
      "learning_rate": 2e-05,
      "loss": 0.6507,
      "step": 1110
    },
    {
      "epoch": 0.05861726068979955,
      "grad_norm": 0.5064834356307983,
      "learning_rate": 2e-05,
      "loss": 0.6467,
      "step": 1120
    },
    {
      "epoch": 0.059140629088815615,
      "grad_norm": 0.446809321641922,
      "learning_rate": 2e-05,
      "loss": 0.6751,
      "step": 1130
    },
    {
      "epoch": 0.05966399748783169,
      "grad_norm": 0.4745899736881256,
      "learning_rate": 2e-05,
      "loss": 0.6564,
      "step": 1140
    },
    {
      "epoch": 0.060187365886847755,
      "grad_norm": 0.5119066834449768,
      "learning_rate": 2e-05,
      "loss": 0.6618,
      "step": 1150
    },
    {
      "epoch": 0.06071073428586382,
      "grad_norm": 0.41898113489151,
      "learning_rate": 2e-05,
      "loss": 0.6622,
      "step": 1160
    },
    {
      "epoch": 0.06123410268487989,
      "grad_norm": 0.6409226059913635,
      "learning_rate": 2e-05,
      "loss": 0.6708,
      "step": 1170
    },
    {
      "epoch": 0.061757471083895954,
      "grad_norm": 0.439377099275589,
      "learning_rate": 2e-05,
      "loss": 0.6473,
      "step": 1180
    },
    {
      "epoch": 0.06228083948291202,
      "grad_norm": 0.4160749316215515,
      "learning_rate": 2e-05,
      "loss": 0.6798,
      "step": 1190
    },
    {
      "epoch": 0.06280420788192809,
      "grad_norm": 0.5204553604125977,
      "learning_rate": 2e-05,
      "loss": 0.6866,
      "step": 1200
    },
    {
      "epoch": 0.06332757628094415,
      "grad_norm": 0.48897305130958557,
      "learning_rate": 2e-05,
      "loss": 0.6618,
      "step": 1210
    },
    {
      "epoch": 0.06385094467996022,
      "grad_norm": 0.45014750957489014,
      "learning_rate": 2e-05,
      "loss": 0.6647,
      "step": 1220
    },
    {
      "epoch": 0.06437431307897629,
      "grad_norm": 0.4595189690589905,
      "learning_rate": 2e-05,
      "loss": 0.6625,
      "step": 1230
    },
    {
      "epoch": 0.06489768147799235,
      "grad_norm": 0.49671754240989685,
      "learning_rate": 2e-05,
      "loss": 0.663,
      "step": 1240
    },
    {
      "epoch": 0.06542104987700843,
      "grad_norm": 0.44070637226104736,
      "learning_rate": 2e-05,
      "loss": 0.6613,
      "step": 1250
    },
    {
      "epoch": 0.0659444182760245,
      "grad_norm": 0.45897576212882996,
      "learning_rate": 2e-05,
      "loss": 0.6516,
      "step": 1260
    },
    {
      "epoch": 0.06646778667504057,
      "grad_norm": 0.4450547695159912,
      "learning_rate": 2e-05,
      "loss": 0.641,
      "step": 1270
    },
    {
      "epoch": 0.06699115507405663,
      "grad_norm": 0.4288750886917114,
      "learning_rate": 2e-05,
      "loss": 0.6656,
      "step": 1280
    },
    {
      "epoch": 0.0675145234730727,
      "grad_norm": 0.47525206208229065,
      "learning_rate": 2e-05,
      "loss": 0.6915,
      "step": 1290
    },
    {
      "epoch": 0.06803789187208877,
      "grad_norm": 0.41285258531570435,
      "learning_rate": 2e-05,
      "loss": 0.6401,
      "step": 1300
    },
    {
      "epoch": 0.06856126027110483,
      "grad_norm": 0.46445295214653015,
      "learning_rate": 2e-05,
      "loss": 0.6692,
      "step": 1310
    },
    {
      "epoch": 0.0690846286701209,
      "grad_norm": 0.44153061509132385,
      "learning_rate": 2e-05,
      "loss": 0.6291,
      "step": 1320
    },
    {
      "epoch": 0.06960799706913696,
      "grad_norm": 0.7016943693161011,
      "learning_rate": 2e-05,
      "loss": 0.6405,
      "step": 1330
    },
    {
      "epoch": 0.07013136546815303,
      "grad_norm": 0.498710572719574,
      "learning_rate": 2e-05,
      "loss": 0.6433,
      "step": 1340
    },
    {
      "epoch": 0.0706547338671691,
      "grad_norm": 0.4415338337421417,
      "learning_rate": 2e-05,
      "loss": 0.673,
      "step": 1350
    },
    {
      "epoch": 0.07117810226618516,
      "grad_norm": 0.5377183556556702,
      "learning_rate": 2e-05,
      "loss": 0.6556,
      "step": 1360
    },
    {
      "epoch": 0.07170147066520123,
      "grad_norm": 0.40461525321006775,
      "learning_rate": 2e-05,
      "loss": 0.6384,
      "step": 1370
    },
    {
      "epoch": 0.0722248390642173,
      "grad_norm": 0.4240797758102417,
      "learning_rate": 2e-05,
      "loss": 0.6467,
      "step": 1380
    },
    {
      "epoch": 0.07274820746323336,
      "grad_norm": 0.4052056074142456,
      "learning_rate": 2e-05,
      "loss": 0.6448,
      "step": 1390
    },
    {
      "epoch": 0.07327157586224944,
      "grad_norm": 0.41825127601623535,
      "learning_rate": 2e-05,
      "loss": 0.6465,
      "step": 1400
    },
    {
      "epoch": 0.07379494426126551,
      "grad_norm": 0.41024652123451233,
      "learning_rate": 2e-05,
      "loss": 0.6428,
      "step": 1410
    },
    {
      "epoch": 0.07431831266028158,
      "grad_norm": 0.38469892740249634,
      "learning_rate": 2e-05,
      "loss": 0.6652,
      "step": 1420
    },
    {
      "epoch": 0.07484168105929764,
      "grad_norm": 0.4639175236225128,
      "learning_rate": 2e-05,
      "loss": 0.6503,
      "step": 1430
    },
    {
      "epoch": 0.07536504945831371,
      "grad_norm": 0.4508153200149536,
      "learning_rate": 2e-05,
      "loss": 0.6464,
      "step": 1440
    },
    {
      "epoch": 0.07588841785732978,
      "grad_norm": 0.5173973441123962,
      "learning_rate": 2e-05,
      "loss": 0.6475,
      "step": 1450
    },
    {
      "epoch": 0.07641178625634584,
      "grad_norm": 0.47181883454322815,
      "learning_rate": 2e-05,
      "loss": 0.6662,
      "step": 1460
    },
    {
      "epoch": 0.07693515465536191,
      "grad_norm": 0.43690988421440125,
      "learning_rate": 2e-05,
      "loss": 0.6459,
      "step": 1470
    },
    {
      "epoch": 0.07745852305437798,
      "grad_norm": 0.40047961473464966,
      "learning_rate": 2e-05,
      "loss": 0.6808,
      "step": 1480
    },
    {
      "epoch": 0.07798189145339404,
      "grad_norm": 0.3962308466434479,
      "learning_rate": 2e-05,
      "loss": 0.6249,
      "step": 1490
    },
    {
      "epoch": 0.07850525985241011,
      "grad_norm": 0.5075916051864624,
      "learning_rate": 2e-05,
      "loss": 0.6562,
      "step": 1500
    },
    {
      "epoch": 0.07902862825142618,
      "grad_norm": 0.44439756870269775,
      "learning_rate": 2e-05,
      "loss": 0.6744,
      "step": 1510
    },
    {
      "epoch": 0.07955199665044224,
      "grad_norm": 0.4172062575817108,
      "learning_rate": 2e-05,
      "loss": 0.6328,
      "step": 1520
    },
    {
      "epoch": 0.08007536504945831,
      "grad_norm": 0.9272112250328064,
      "learning_rate": 2e-05,
      "loss": 0.6554,
      "step": 1530
    },
    {
      "epoch": 0.08059873344847437,
      "grad_norm": 0.44365498423576355,
      "learning_rate": 2e-05,
      "loss": 0.6567,
      "step": 1540
    },
    {
      "epoch": 0.08112210184749045,
      "grad_norm": 0.5808505415916443,
      "learning_rate": 2e-05,
      "loss": 0.6671,
      "step": 1550
    },
    {
      "epoch": 0.08164547024650652,
      "grad_norm": 0.4238007068634033,
      "learning_rate": 2e-05,
      "loss": 0.6655,
      "step": 1560
    },
    {
      "epoch": 0.08216883864552259,
      "grad_norm": 0.4158059358596802,
      "learning_rate": 2e-05,
      "loss": 0.6502,
      "step": 1570
    },
    {
      "epoch": 0.08269220704453865,
      "grad_norm": 0.4266833961009979,
      "learning_rate": 2e-05,
      "loss": 0.6389,
      "step": 1580
    },
    {
      "epoch": 0.08321557544355472,
      "grad_norm": 0.4183817505836487,
      "learning_rate": 2e-05,
      "loss": 0.6297,
      "step": 1590
    },
    {
      "epoch": 0.08373894384257079,
      "grad_norm": 0.4242572784423828,
      "learning_rate": 2e-05,
      "loss": 0.6575,
      "step": 1600
    },
    {
      "epoch": 0.08426231224158685,
      "grad_norm": 0.42805418372154236,
      "learning_rate": 2e-05,
      "loss": 0.6316,
      "step": 1610
    },
    {
      "epoch": 0.08478568064060292,
      "grad_norm": 0.441866010427475,
      "learning_rate": 2e-05,
      "loss": 0.6702,
      "step": 1620
    },
    {
      "epoch": 0.08530904903961899,
      "grad_norm": 0.4371151626110077,
      "learning_rate": 2e-05,
      "loss": 0.6623,
      "step": 1630
    },
    {
      "epoch": 0.08583241743863505,
      "grad_norm": 0.43131211400032043,
      "learning_rate": 2e-05,
      "loss": 0.6448,
      "step": 1640
    },
    {
      "epoch": 0.08635578583765112,
      "grad_norm": 0.4316512644290924,
      "learning_rate": 2e-05,
      "loss": 0.6374,
      "step": 1650
    },
    {
      "epoch": 0.08687915423666719,
      "grad_norm": 0.48419904708862305,
      "learning_rate": 2e-05,
      "loss": 0.6224,
      "step": 1660
    },
    {
      "epoch": 0.08740252263568325,
      "grad_norm": 0.3933804929256439,
      "learning_rate": 2e-05,
      "loss": 0.6522,
      "step": 1670
    },
    {
      "epoch": 0.08792589103469932,
      "grad_norm": 0.4437639117240906,
      "learning_rate": 2e-05,
      "loss": 0.6237,
      "step": 1680
    },
    {
      "epoch": 0.08844925943371539,
      "grad_norm": 0.4899040460586548,
      "learning_rate": 2e-05,
      "loss": 0.6321,
      "step": 1690
    },
    {
      "epoch": 0.08897262783273147,
      "grad_norm": 0.4382249712944031,
      "learning_rate": 2e-05,
      "loss": 0.6469,
      "step": 1700
    },
    {
      "epoch": 0.08949599623174753,
      "grad_norm": 0.4095931053161621,
      "learning_rate": 2e-05,
      "loss": 0.6588,
      "step": 1710
    },
    {
      "epoch": 0.0900193646307636,
      "grad_norm": 0.43513184785842896,
      "learning_rate": 2e-05,
      "loss": 0.6569,
      "step": 1720
    },
    {
      "epoch": 0.09054273302977967,
      "grad_norm": 0.46793821454048157,
      "learning_rate": 2e-05,
      "loss": 0.6322,
      "step": 1730
    },
    {
      "epoch": 0.09106610142879573,
      "grad_norm": 0.430164098739624,
      "learning_rate": 2e-05,
      "loss": 0.6224,
      "step": 1740
    },
    {
      "epoch": 0.0915894698278118,
      "grad_norm": 0.3761891722679138,
      "learning_rate": 2e-05,
      "loss": 0.606,
      "step": 1750
    },
    {
      "epoch": 0.09211283822682786,
      "grad_norm": 0.373146116733551,
      "learning_rate": 2e-05,
      "loss": 0.6329,
      "step": 1760
    },
    {
      "epoch": 0.09263620662584393,
      "grad_norm": 0.42644017934799194,
      "learning_rate": 2e-05,
      "loss": 0.6466,
      "step": 1770
    },
    {
      "epoch": 0.09315957502486,
      "grad_norm": 0.40171223878860474,
      "learning_rate": 2e-05,
      "loss": 0.6567,
      "step": 1780
    },
    {
      "epoch": 0.09368294342387606,
      "grad_norm": 0.5002732872962952,
      "learning_rate": 2e-05,
      "loss": 0.6645,
      "step": 1790
    },
    {
      "epoch": 0.09420631182289213,
      "grad_norm": 0.45148345828056335,
      "learning_rate": 2e-05,
      "loss": 0.6735,
      "step": 1800
    },
    {
      "epoch": 0.0947296802219082,
      "grad_norm": 0.4408950209617615,
      "learning_rate": 2e-05,
      "loss": 0.64,
      "step": 1810
    },
    {
      "epoch": 0.09525304862092426,
      "grad_norm": 0.41224032640457153,
      "learning_rate": 2e-05,
      "loss": 0.6483,
      "step": 1820
    },
    {
      "epoch": 0.09577641701994033,
      "grad_norm": 0.3857000768184662,
      "learning_rate": 2e-05,
      "loss": 0.6591,
      "step": 1830
    },
    {
      "epoch": 0.09629978541895641,
      "grad_norm": 0.5142344832420349,
      "learning_rate": 2e-05,
      "loss": 0.6613,
      "step": 1840
    },
    {
      "epoch": 0.09682315381797248,
      "grad_norm": 0.43707653880119324,
      "learning_rate": 2e-05,
      "loss": 0.6463,
      "step": 1850
    },
    {
      "epoch": 0.09734652221698854,
      "grad_norm": 0.5951546430587769,
      "learning_rate": 2e-05,
      "loss": 0.6634,
      "step": 1860
    },
    {
      "epoch": 0.09786989061600461,
      "grad_norm": 0.451498419046402,
      "learning_rate": 2e-05,
      "loss": 0.6228,
      "step": 1870
    },
    {
      "epoch": 0.09839325901502068,
      "grad_norm": 0.43872302770614624,
      "learning_rate": 2e-05,
      "loss": 0.6417,
      "step": 1880
    },
    {
      "epoch": 0.09891662741403674,
      "grad_norm": 0.3905869722366333,
      "learning_rate": 2e-05,
      "loss": 0.6195,
      "step": 1890
    },
    {
      "epoch": 0.09943999581305281,
      "grad_norm": 0.46226704120635986,
      "learning_rate": 2e-05,
      "loss": 0.652,
      "step": 1900
    },
    {
      "epoch": 0.09996336421206888,
      "grad_norm": 0.4350249469280243,
      "learning_rate": 2e-05,
      "loss": 0.6814,
      "step": 1910
    },
    {
      "epoch": 0.10048673261108494,
      "grad_norm": 0.547003448009491,
      "learning_rate": 2e-05,
      "loss": 0.6376,
      "step": 1920
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 0.40520697832107544,
      "learning_rate": 2e-05,
      "loss": 0.6281,
      "step": 1930
    },
    {
      "epoch": 0.10153346940911707,
      "grad_norm": 0.3886966109275818,
      "learning_rate": 2e-05,
      "loss": 0.6349,
      "step": 1940
    },
    {
      "epoch": 0.10205683780813314,
      "grad_norm": 0.4416722059249878,
      "learning_rate": 2e-05,
      "loss": 0.6626,
      "step": 1950
    },
    {
      "epoch": 0.10258020620714921,
      "grad_norm": 0.4272310137748718,
      "learning_rate": 2e-05,
      "loss": 0.627,
      "step": 1960
    },
    {
      "epoch": 0.10310357460616527,
      "grad_norm": 0.4342178404331207,
      "learning_rate": 2e-05,
      "loss": 0.6616,
      "step": 1970
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 0.4413588047027588,
      "learning_rate": 2e-05,
      "loss": 0.6602,
      "step": 1980
    },
    {
      "epoch": 0.10415031140419742,
      "grad_norm": 0.39807382225990295,
      "learning_rate": 2e-05,
      "loss": 0.6184,
      "step": 1990
    },
    {
      "epoch": 0.10467367980321349,
      "grad_norm": 0.39922189712524414,
      "learning_rate": 2e-05,
      "loss": 0.6348,
      "step": 2000
    },
    {
      "epoch": 0.10519704820222955,
      "grad_norm": 0.4405508041381836,
      "learning_rate": 2e-05,
      "loss": 0.6527,
      "step": 2010
    },
    {
      "epoch": 0.10572041660124562,
      "grad_norm": 0.4154644310474396,
      "learning_rate": 2e-05,
      "loss": 0.6383,
      "step": 2020
    },
    {
      "epoch": 0.10624378500026169,
      "grad_norm": 0.4121659994125366,
      "learning_rate": 2e-05,
      "loss": 0.6337,
      "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
}