{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09528938003371418,
  "eval_steps": 500,
  "global_step": 2035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004682524817381532,
      "grad_norm": 0.7815176248550415,
      "learning_rate": 2.910112359550562e-06,
      "loss": 0.8415,
      "step": 10
    },
    {
      "epoch": 0.0009365049634763064,
      "grad_norm": 0.8108879327774048,
      "learning_rate": 3.921348314606742e-06,
      "loss": 0.8485,
      "step": 20
    },
    {
      "epoch": 0.0014047574452144597,
      "grad_norm": 0.8000619411468506,
      "learning_rate": 4.932584269662922e-06,
      "loss": 0.83,
      "step": 30
    },
    {
      "epoch": 0.0018730099269526129,
      "grad_norm": 0.7511084675788879,
      "learning_rate": 5.943820224719102e-06,
      "loss": 0.8517,
      "step": 40
    },
    {
      "epoch": 0.002341262408690766,
      "grad_norm": 0.7430337071418762,
      "learning_rate": 6.955056179775282e-06,
      "loss": 0.847,
      "step": 50
    },
    {
      "epoch": 0.0028095148904289193,
      "grad_norm": 0.8726410269737244,
      "learning_rate": 7.966292134831462e-06,
      "loss": 0.8172,
      "step": 60
    },
    {
      "epoch": 0.0032777673721670723,
      "grad_norm": 0.8567508459091187,
      "learning_rate": 8.977528089887641e-06,
      "loss": 0.8377,
      "step": 70
    },
    {
      "epoch": 0.0037460198539052258,
      "grad_norm": 0.7639268040657043,
      "learning_rate": 9.988764044943822e-06,
      "loss": 0.8184,
      "step": 80
    },
    {
      "epoch": 0.004214272335643379,
      "grad_norm": 0.9645025134086609,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.8178,
      "step": 90
    },
    {
      "epoch": 0.004682524817381532,
      "grad_norm": 0.801426887512207,
      "learning_rate": 1.2011235955056182e-05,
      "loss": 0.8351,
      "step": 100
    },
    {
      "epoch": 0.005150777299119685,
      "grad_norm": 0.8018251061439514,
      "learning_rate": 1.3022471910112362e-05,
      "loss": 0.8493,
      "step": 110
    },
    {
      "epoch": 0.005619029780857839,
      "grad_norm": 1.6218419075012207,
      "learning_rate": 1.403370786516854e-05,
      "loss": 0.8367,
      "step": 120
    },
    {
      "epoch": 0.006087282262595992,
      "grad_norm": 0.738893449306488,
      "learning_rate": 1.504494382022472e-05,
      "loss": 0.8622,
      "step": 130
    },
    {
      "epoch": 0.006555534744334145,
      "grad_norm": 0.9413527846336365,
      "learning_rate": 1.60561797752809e-05,
      "loss": 0.8024,
      "step": 140
    },
    {
      "epoch": 0.007023787226072298,
      "grad_norm": 0.8190211653709412,
      "learning_rate": 1.706741573033708e-05,
      "loss": 0.8216,
      "step": 150
    },
    {
      "epoch": 0.0074920397078104516,
      "grad_norm": 0.6878272294998169,
      "learning_rate": 1.8078651685393256e-05,
      "loss": 0.8609,
      "step": 160
    },
    {
      "epoch": 0.007960292189548605,
      "grad_norm": 0.7031309008598328,
      "learning_rate": 1.908988764044944e-05,
      "loss": 0.8954,
      "step": 170
    },
    {
      "epoch": 0.008428544671286758,
      "grad_norm": 0.7149655818939209,
      "learning_rate": 2e-05,
      "loss": 0.8378,
      "step": 180
    },
    {
      "epoch": 0.008896797153024912,
      "grad_norm": 0.6629250645637512,
      "learning_rate": 2e-05,
      "loss": 0.8002,
      "step": 190
    },
    {
      "epoch": 0.009365049634763064,
      "grad_norm": 0.6915798783302307,
      "learning_rate": 2e-05,
      "loss": 0.8358,
      "step": 200
    },
    {
      "epoch": 0.009833302116501217,
      "grad_norm": 0.6538642644882202,
      "learning_rate": 2e-05,
      "loss": 0.8535,
      "step": 210
    },
    {
      "epoch": 0.01030155459823937,
      "grad_norm": 0.584514856338501,
      "learning_rate": 2e-05,
      "loss": 0.8362,
      "step": 220
    },
    {
      "epoch": 0.010769807079977524,
      "grad_norm": 1.3603894710540771,
      "learning_rate": 2e-05,
      "loss": 0.8086,
      "step": 230
    },
    {
      "epoch": 0.011238059561715677,
      "grad_norm": 0.5758199691772461,
      "learning_rate": 2e-05,
      "loss": 0.8336,
      "step": 240
    },
    {
      "epoch": 0.01170631204345383,
      "grad_norm": 0.6881021857261658,
      "learning_rate": 2e-05,
      "loss": 0.8444,
      "step": 250
    },
    {
      "epoch": 0.012174564525191984,
      "grad_norm": 1.9581451416015625,
      "learning_rate": 2e-05,
      "loss": 0.8433,
      "step": 260
    },
    {
      "epoch": 0.012642817006930136,
      "grad_norm": 0.5425940752029419,
      "learning_rate": 2e-05,
      "loss": 0.8213,
      "step": 270
    },
    {
      "epoch": 0.01311106948866829,
      "grad_norm": 0.5425044298171997,
      "learning_rate": 2e-05,
      "loss": 0.8179,
      "step": 280
    },
    {
      "epoch": 0.013579321970406443,
      "grad_norm": 0.657163143157959,
      "learning_rate": 2e-05,
      "loss": 0.8649,
      "step": 290
    },
    {
      "epoch": 0.014047574452144596,
      "grad_norm": 0.569369375705719,
      "learning_rate": 2e-05,
      "loss": 0.8438,
      "step": 300
    },
    {
      "epoch": 0.01451582693388275,
      "grad_norm": 0.554995059967041,
      "learning_rate": 2e-05,
      "loss": 0.8085,
      "step": 310
    },
    {
      "epoch": 0.014984079415620903,
      "grad_norm": 0.5484607219696045,
      "learning_rate": 2e-05,
      "loss": 0.8089,
      "step": 320
    },
    {
      "epoch": 0.015452331897359057,
      "grad_norm": 0.5753210186958313,
      "learning_rate": 2e-05,
      "loss": 0.8142,
      "step": 330
    },
    {
      "epoch": 0.01592058437909721,
      "grad_norm": 0.7434160113334656,
      "learning_rate": 2e-05,
      "loss": 0.8188,
      "step": 340
    },
    {
      "epoch": 0.01638883686083536,
      "grad_norm": 0.574074923992157,
      "learning_rate": 2e-05,
      "loss": 0.8563,
      "step": 350
    },
    {
      "epoch": 0.016857089342573517,
      "grad_norm": 0.5934783816337585,
      "learning_rate": 2e-05,
      "loss": 0.839,
      "step": 360
    },
    {
      "epoch": 0.01732534182431167,
      "grad_norm": 2.1430094242095947,
      "learning_rate": 2e-05,
      "loss": 0.8244,
      "step": 370
    },
    {
      "epoch": 0.017793594306049824,
      "grad_norm": 0.5127322673797607,
      "learning_rate": 2e-05,
      "loss": 0.7979,
      "step": 380
    },
    {
      "epoch": 0.018261846787787975,
      "grad_norm": 0.5187241435050964,
      "learning_rate": 2e-05,
      "loss": 0.8122,
      "step": 390
    },
    {
      "epoch": 0.018730099269526127,
      "grad_norm": 0.5075030326843262,
      "learning_rate": 2e-05,
      "loss": 0.8645,
      "step": 400
    },
    {
      "epoch": 0.019198351751264282,
      "grad_norm": 0.4950161576271057,
      "learning_rate": 2e-05,
      "loss": 0.8418,
      "step": 410
    },
    {
      "epoch": 0.019666604233002434,
      "grad_norm": 0.5396143794059753,
      "learning_rate": 2e-05,
      "loss": 0.8152,
      "step": 420
    },
    {
      "epoch": 0.02013485671474059,
      "grad_norm": 0.5515366196632385,
      "learning_rate": 2e-05,
      "loss": 0.7911,
      "step": 430
    },
    {
      "epoch": 0.02060310919647874,
      "grad_norm": 0.5184299945831299,
      "learning_rate": 2e-05,
      "loss": 0.8403,
      "step": 440
    },
    {
      "epoch": 0.021071361678216896,
      "grad_norm": 0.4794081449508667,
      "learning_rate": 2e-05,
      "loss": 0.8233,
      "step": 450
    },
    {
      "epoch": 0.021539614159955048,
      "grad_norm": 0.7160170674324036,
      "learning_rate": 2e-05,
      "loss": 0.8302,
      "step": 460
    },
    {
      "epoch": 0.0220078666416932,
      "grad_norm": 0.6666805148124695,
      "learning_rate": 2e-05,
      "loss": 0.8202,
      "step": 470
    },
    {
      "epoch": 0.022476119123431355,
      "grad_norm": 0.5356866717338562,
      "learning_rate": 2e-05,
      "loss": 0.8418,
      "step": 480
    },
    {
      "epoch": 0.022944371605169506,
      "grad_norm": 0.4900036156177521,
      "learning_rate": 2e-05,
      "loss": 0.829,
      "step": 490
    },
    {
      "epoch": 0.02341262408690766,
      "grad_norm": 0.47087252140045166,
      "learning_rate": 2e-05,
      "loss": 0.8418,
      "step": 500
    },
    {
      "epoch": 0.023880876568645813,
      "grad_norm": 0.5223408341407776,
      "learning_rate": 2e-05,
      "loss": 0.7874,
      "step": 510
    },
    {
      "epoch": 0.02434912905038397,
      "grad_norm": 0.5723909735679626,
      "learning_rate": 2e-05,
      "loss": 0.8552,
      "step": 520
    },
    {
      "epoch": 0.02481738153212212,
      "grad_norm": 0.4538605213165283,
      "learning_rate": 2e-05,
      "loss": 0.7783,
      "step": 530
    },
    {
      "epoch": 0.025285634013860272,
      "grad_norm": 0.4878973960876465,
      "learning_rate": 2e-05,
      "loss": 0.8085,
      "step": 540
    },
    {
      "epoch": 0.025753886495598427,
      "grad_norm": 0.5102939605712891,
      "learning_rate": 2e-05,
      "loss": 0.799,
      "step": 550
    },
    {
      "epoch": 0.02622213897733658,
      "grad_norm": 0.5069881081581116,
      "learning_rate": 2e-05,
      "loss": 0.8201,
      "step": 560
    },
    {
      "epoch": 0.026690391459074734,
      "grad_norm": 0.45733290910720825,
      "learning_rate": 2e-05,
      "loss": 0.844,
      "step": 570
    },
    {
      "epoch": 0.027158643940812886,
      "grad_norm": 0.4658640921115875,
      "learning_rate": 2e-05,
      "loss": 0.8291,
      "step": 580
    },
    {
      "epoch": 0.02762689642255104,
      "grad_norm": 0.48104459047317505,
      "learning_rate": 2e-05,
      "loss": 0.8432,
      "step": 590
    },
    {
      "epoch": 0.028095148904289192,
      "grad_norm": 0.46297943592071533,
      "learning_rate": 2e-05,
      "loss": 0.8192,
      "step": 600
    },
    {
      "epoch": 0.028563401386027348,
      "grad_norm": 0.450825959444046,
      "learning_rate": 2e-05,
      "loss": 0.7987,
      "step": 610
    },
    {
      "epoch": 0.0290316538677655,
      "grad_norm": 0.4797734022140503,
      "learning_rate": 2e-05,
      "loss": 0.8325,
      "step": 620
    },
    {
      "epoch": 0.02949990634950365,
      "grad_norm": 0.481893390417099,
      "learning_rate": 2e-05,
      "loss": 0.7837,
      "step": 630
    },
    {
      "epoch": 0.029968158831241806,
      "grad_norm": 0.47477421164512634,
      "learning_rate": 2e-05,
      "loss": 0.8278,
      "step": 640
    },
    {
      "epoch": 0.030436411312979958,
      "grad_norm": 0.5964585542678833,
      "learning_rate": 2e-05,
      "loss": 0.7969,
      "step": 650
    },
    {
      "epoch": 0.030904663794718113,
      "grad_norm": 0.46593981981277466,
      "learning_rate": 2e-05,
      "loss": 0.8307,
      "step": 660
    },
    {
      "epoch": 0.03137291627645627,
      "grad_norm": 0.48121365904808044,
      "learning_rate": 2e-05,
      "loss": 0.8174,
      "step": 670
    },
    {
      "epoch": 0.03184116875819442,
      "grad_norm": 0.5038956999778748,
      "learning_rate": 2e-05,
      "loss": 0.8339,
      "step": 680
    },
    {
      "epoch": 0.03230942123993257,
      "grad_norm": 0.5365706086158752,
      "learning_rate": 2e-05,
      "loss": 0.8291,
      "step": 690
    },
    {
      "epoch": 0.03277767372167072,
      "grad_norm": 0.5319100618362427,
      "learning_rate": 2e-05,
      "loss": 0.7953,
      "step": 700
    },
    {
      "epoch": 0.033245926203408875,
      "grad_norm": 0.4542364776134491,
      "learning_rate": 2e-05,
      "loss": 0.8263,
      "step": 710
    },
    {
      "epoch": 0.033714178685147034,
      "grad_norm": 0.47826236486434937,
      "learning_rate": 2e-05,
      "loss": 0.8321,
      "step": 720
    },
    {
      "epoch": 0.034182431166885185,
      "grad_norm": 0.44108861684799194,
      "learning_rate": 2e-05,
      "loss": 0.7989,
      "step": 730
    },
    {
      "epoch": 0.03465068364862334,
      "grad_norm": 0.4653085172176361,
      "learning_rate": 2e-05,
      "loss": 0.7994,
      "step": 740
    },
    {
      "epoch": 0.03511893613036149,
      "grad_norm": 0.5099039077758789,
      "learning_rate": 2e-05,
      "loss": 0.7591,
      "step": 750
    },
    {
      "epoch": 0.03558718861209965,
      "grad_norm": 0.48215553164482117,
      "learning_rate": 2e-05,
      "loss": 0.7921,
      "step": 760
    },
    {
      "epoch": 0.0360554410938378,
      "grad_norm": 0.46062806248664856,
      "learning_rate": 2e-05,
      "loss": 0.8244,
      "step": 770
    },
    {
      "epoch": 0.03652369357557595,
      "grad_norm": 0.5108964443206787,
      "learning_rate": 2e-05,
      "loss": 0.8667,
      "step": 780
    },
    {
      "epoch": 0.0369919460573141,
      "grad_norm": 0.47737154364585876,
      "learning_rate": 2e-05,
      "loss": 0.8246,
      "step": 790
    },
    {
      "epoch": 0.037460198539052254,
      "grad_norm": 0.5114936828613281,
      "learning_rate": 2e-05,
      "loss": 0.8188,
      "step": 800
    },
    {
      "epoch": 0.03792845102079041,
      "grad_norm": 0.47046583890914917,
      "learning_rate": 2e-05,
      "loss": 0.8393,
      "step": 810
    },
    {
      "epoch": 0.038396703502528565,
      "grad_norm": 0.4314744472503662,
      "learning_rate": 2e-05,
      "loss": 0.7953,
      "step": 820
    },
    {
      "epoch": 0.038864955984266716,
      "grad_norm": 0.4930090308189392,
      "learning_rate": 2e-05,
      "loss": 0.8048,
      "step": 830
    },
    {
      "epoch": 0.03933320846600487,
      "grad_norm": 0.4331071078777313,
      "learning_rate": 2e-05,
      "loss": 0.8389,
      "step": 840
    },
    {
      "epoch": 0.03980146094774302,
      "grad_norm": 0.4713480472564697,
      "learning_rate": 2e-05,
      "loss": 0.8165,
      "step": 850
    },
    {
      "epoch": 0.04026971342948118,
      "grad_norm": 0.4679141938686371,
      "learning_rate": 2e-05,
      "loss": 0.8198,
      "step": 860
    },
    {
      "epoch": 0.04073796591121933,
      "grad_norm": 0.7808457612991333,
      "learning_rate": 2e-05,
      "loss": 0.8528,
      "step": 870
    },
    {
      "epoch": 0.04120621839295748,
      "grad_norm": 0.44788986444473267,
      "learning_rate": 2e-05,
      "loss": 0.8225,
      "step": 880
    },
    {
      "epoch": 0.041674470874695634,
      "grad_norm": 0.480165034532547,
      "learning_rate": 2e-05,
      "loss": 0.8185,
      "step": 890
    },
    {
      "epoch": 0.04214272335643379,
      "grad_norm": 0.46314555406570435,
      "learning_rate": 2e-05,
      "loss": 0.8116,
      "step": 900
    },
    {
      "epoch": 0.042610975838171944,
      "grad_norm": 0.6263248920440674,
      "learning_rate": 2e-05,
      "loss": 0.8418,
      "step": 910
    },
    {
      "epoch": 0.043079228319910096,
      "grad_norm": 0.4619986414909363,
      "learning_rate": 2e-05,
      "loss": 0.8378,
      "step": 920
    },
    {
      "epoch": 0.04354748080164825,
      "grad_norm": 0.4389607906341553,
      "learning_rate": 2e-05,
      "loss": 0.8153,
      "step": 930
    },
    {
      "epoch": 0.0440157332833864,
      "grad_norm": 0.5322599411010742,
      "learning_rate": 2e-05,
      "loss": 0.8049,
      "step": 940
    },
    {
      "epoch": 0.04448398576512456,
      "grad_norm": 0.4362427890300751,
      "learning_rate": 2e-05,
      "loss": 0.7895,
      "step": 950
    },
    {
      "epoch": 0.04495223824686271,
      "grad_norm": 0.560736358165741,
      "learning_rate": 2e-05,
      "loss": 0.7834,
      "step": 960
    },
    {
      "epoch": 0.04542049072860086,
      "grad_norm": 0.49655383825302124,
      "learning_rate": 2e-05,
      "loss": 0.8419,
      "step": 970
    },
    {
      "epoch": 0.04588874321033901,
      "grad_norm": 0.447719931602478,
      "learning_rate": 2e-05,
      "loss": 0.8268,
      "step": 980
    },
    {
      "epoch": 0.04635699569207717,
      "grad_norm": 0.472380131483078,
      "learning_rate": 2e-05,
      "loss": 0.797,
      "step": 990
    },
    {
      "epoch": 0.04682524817381532,
      "grad_norm": 0.4404251277446747,
      "learning_rate": 2e-05,
      "loss": 0.8216,
      "step": 1000
    },
    {
      "epoch": 0.047293500655553475,
      "grad_norm": 0.8469703793525696,
      "learning_rate": 2e-05,
      "loss": 0.8061,
      "step": 1010
    },
    {
      "epoch": 0.047761753137291627,
      "grad_norm": 0.49690261483192444,
      "learning_rate": 2e-05,
      "loss": 0.8739,
      "step": 1020
    },
    {
      "epoch": 0.04823000561902978,
      "grad_norm": 0.4546132981777191,
      "learning_rate": 2e-05,
      "loss": 0.8611,
      "step": 1030
    },
    {
      "epoch": 0.04869825810076794,
      "grad_norm": 0.9852249026298523,
      "learning_rate": 2e-05,
      "loss": 0.8151,
      "step": 1040
    },
    {
      "epoch": 0.04916651058250609,
      "grad_norm": 0.4317361116409302,
      "learning_rate": 2e-05,
      "loss": 0.8253,
      "step": 1050
    },
    {
      "epoch": 0.04963476306424424,
      "grad_norm": 0.48968589305877686,
      "learning_rate": 2e-05,
      "loss": 0.8241,
      "step": 1060
    },
    {
      "epoch": 0.05010301554598239,
      "grad_norm": 0.5702976584434509,
      "learning_rate": 2e-05,
      "loss": 0.788,
      "step": 1070
    },
    {
      "epoch": 0.050571268027720544,
      "grad_norm": 0.4381064474582672,
      "learning_rate": 2e-05,
      "loss": 0.7815,
      "step": 1080
    },
    {
      "epoch": 0.0510395205094587,
      "grad_norm": 0.48637041449546814,
      "learning_rate": 2e-05,
      "loss": 0.8424,
      "step": 1090
    },
    {
      "epoch": 0.051507772991196854,
      "grad_norm": 0.4259801506996155,
      "learning_rate": 2e-05,
      "loss": 0.817,
      "step": 1100
    },
    {
      "epoch": 0.051976025472935006,
      "grad_norm": 0.4507712423801422,
      "learning_rate": 2e-05,
      "loss": 0.856,
      "step": 1110
    },
    {
      "epoch": 0.05244427795467316,
      "grad_norm": 0.4860295057296753,
      "learning_rate": 2e-05,
      "loss": 0.8139,
      "step": 1120
    },
    {
      "epoch": 0.052912530436411316,
      "grad_norm": 0.5244073271751404,
      "learning_rate": 2e-05,
      "loss": 0.8165,
      "step": 1130
    },
    {
      "epoch": 0.05338078291814947,
      "grad_norm": 0.4211806654930115,
      "learning_rate": 2e-05,
      "loss": 0.7845,
      "step": 1140
    },
    {
      "epoch": 0.05384903539988762,
      "grad_norm": 0.4540943205356598,
      "learning_rate": 2e-05,
      "loss": 0.7812,
      "step": 1150
    },
    {
      "epoch": 0.05431728788162577,
      "grad_norm": 0.4845108985900879,
      "learning_rate": 2e-05,
      "loss": 0.8138,
      "step": 1160
    },
    {
      "epoch": 0.05478554036336392,
      "grad_norm": 0.46812689304351807,
      "learning_rate": 2e-05,
      "loss": 0.8065,
      "step": 1170
    },
    {
      "epoch": 0.05525379284510208,
      "grad_norm": 0.42959365248680115,
      "learning_rate": 2e-05,
      "loss": 0.8089,
      "step": 1180
    },
    {
      "epoch": 0.05572204532684023,
      "grad_norm": 0.7998138070106506,
      "learning_rate": 2e-05,
      "loss": 0.8137,
      "step": 1190
    },
    {
      "epoch": 0.056190297808578385,
      "grad_norm": 0.46024176478385925,
      "learning_rate": 2e-05,
      "loss": 0.8341,
      "step": 1200
    },
    {
      "epoch": 0.05665855029031654,
      "grad_norm": 0.4920409023761749,
      "learning_rate": 2e-05,
      "loss": 0.8328,
      "step": 1210
    },
    {
      "epoch": 0.057126802772054695,
      "grad_norm": 0.44345328211784363,
      "learning_rate": 2e-05,
      "loss": 0.8242,
      "step": 1220
    },
    {
      "epoch": 0.05759505525379285,
      "grad_norm": 0.4638558030128479,
      "learning_rate": 2e-05,
      "loss": 0.8111,
      "step": 1230
    },
    {
      "epoch": 0.058063307735531,
      "grad_norm": 0.6508961319923401,
      "learning_rate": 2e-05,
      "loss": 0.809,
      "step": 1240
    },
    {
      "epoch": 0.05853156021726915,
      "grad_norm": 0.4465144872665405,
      "learning_rate": 2e-05,
      "loss": 0.8195,
      "step": 1250
    },
    {
      "epoch": 0.0589998126990073,
      "grad_norm": 0.4405592978000641,
      "learning_rate": 2e-05,
      "loss": 0.8352,
      "step": 1260
    },
    {
      "epoch": 0.05946806518074546,
      "grad_norm": 0.43743807077407837,
      "learning_rate": 2e-05,
      "loss": 0.8149,
      "step": 1270
    },
    {
      "epoch": 0.05993631766248361,
      "grad_norm": 0.5173885226249695,
      "learning_rate": 2e-05,
      "loss": 0.8421,
      "step": 1280
    },
    {
      "epoch": 0.060404570144221764,
      "grad_norm": 0.41101977229118347,
      "learning_rate": 2e-05,
      "loss": 0.8493,
      "step": 1290
    },
    {
      "epoch": 0.060872822625959916,
      "grad_norm": 0.41480135917663574,
      "learning_rate": 2e-05,
      "loss": 0.7971,
      "step": 1300
    },
    {
      "epoch": 0.06134107510769807,
      "grad_norm": 0.5274170637130737,
      "learning_rate": 2e-05,
      "loss": 0.8106,
      "step": 1310
    },
    {
      "epoch": 0.061809327589436226,
      "grad_norm": 0.4326211214065552,
      "learning_rate": 2e-05,
      "loss": 0.7927,
      "step": 1320
    },
    {
      "epoch": 0.06227758007117438,
      "grad_norm": 0.4117155373096466,
      "learning_rate": 2e-05,
      "loss": 0.7877,
      "step": 1330
    },
    {
      "epoch": 0.06274583255291254,
      "grad_norm": 0.4453534483909607,
      "learning_rate": 2e-05,
      "loss": 0.8417,
      "step": 1340
    },
    {
      "epoch": 0.06321408503465069,
      "grad_norm": 0.6158928871154785,
      "learning_rate": 2e-05,
      "loss": 0.7797,
      "step": 1350
    },
    {
      "epoch": 0.06368233751638884,
      "grad_norm": 0.43932247161865234,
      "learning_rate": 2e-05,
      "loss": 0.8042,
      "step": 1360
    },
    {
      "epoch": 0.06415058999812699,
      "grad_norm": 0.5323647856712341,
      "learning_rate": 2e-05,
      "loss": 0.798,
      "step": 1370
    },
    {
      "epoch": 0.06461884247986514,
      "grad_norm": 0.4197414517402649,
      "learning_rate": 2e-05,
      "loss": 0.8223,
      "step": 1380
    },
    {
      "epoch": 0.0650870949616033,
      "grad_norm": 0.48507630825042725,
      "learning_rate": 2e-05,
      "loss": 0.8105,
      "step": 1390
    },
    {
      "epoch": 0.06555534744334145,
      "grad_norm": 0.47112739086151123,
      "learning_rate": 2e-05,
      "loss": 0.8249,
      "step": 1400
    },
    {
      "epoch": 0.0660235999250796,
      "grad_norm": 0.48371198773384094,
      "learning_rate": 2e-05,
      "loss": 0.8105,
      "step": 1410
    },
    {
      "epoch": 0.06649185240681775,
      "grad_norm": 0.43702569603919983,
      "learning_rate": 2e-05,
      "loss": 0.7906,
      "step": 1420
    },
    {
      "epoch": 0.06696010488855592,
      "grad_norm": 0.44430628418922424,
      "learning_rate": 2e-05,
      "loss": 0.8313,
      "step": 1430
    },
    {
      "epoch": 0.06742835737029407,
      "grad_norm": 0.4579251706600189,
      "learning_rate": 2e-05,
      "loss": 0.8415,
      "step": 1440
    },
    {
      "epoch": 0.06789660985203222,
      "grad_norm": 0.48323583602905273,
      "learning_rate": 2e-05,
      "loss": 0.8341,
      "step": 1450
    },
    {
      "epoch": 0.06836486233377037,
      "grad_norm": 0.427022248506546,
      "learning_rate": 2e-05,
      "loss": 0.8007,
      "step": 1460
    },
    {
      "epoch": 0.06883311481550852,
      "grad_norm": 0.4505695104598999,
      "learning_rate": 2e-05,
      "loss": 0.8095,
      "step": 1470
    },
    {
      "epoch": 0.06930136729724667,
      "grad_norm": 0.45807015895843506,
      "learning_rate": 2e-05,
      "loss": 0.7785,
      "step": 1480
    },
    {
      "epoch": 0.06976961977898483,
      "grad_norm": 0.5102551579475403,
      "learning_rate": 2e-05,
      "loss": 0.806,
      "step": 1490
    },
    {
      "epoch": 0.07023787226072298,
      "grad_norm": 0.42989158630371094,
      "learning_rate": 2e-05,
      "loss": 0.8295,
      "step": 1500
    },
    {
      "epoch": 0.07070612474246113,
      "grad_norm": 0.5128605961799622,
      "learning_rate": 2e-05,
      "loss": 0.8218,
      "step": 1510
    },
    {
      "epoch": 0.0711743772241993,
      "grad_norm": 0.4889835715293884,
      "learning_rate": 2e-05,
      "loss": 0.7938,
      "step": 1520
    },
    {
      "epoch": 0.07164262970593745,
      "grad_norm": 0.4175378680229187,
      "learning_rate": 2e-05,
      "loss": 0.8033,
      "step": 1530
    },
    {
      "epoch": 0.0721108821876756,
      "grad_norm": 0.4378540813922882,
      "learning_rate": 2e-05,
      "loss": 0.8042,
      "step": 1540
    },
    {
      "epoch": 0.07257913466941375,
      "grad_norm": 0.4375297427177429,
      "learning_rate": 2e-05,
      "loss": 0.8218,
      "step": 1550
    },
    {
      "epoch": 0.0730473871511519,
      "grad_norm": 0.49845996499061584,
      "learning_rate": 2e-05,
      "loss": 0.8044,
      "step": 1560
    },
    {
      "epoch": 0.07351563963289005,
      "grad_norm": 0.46285390853881836,
      "learning_rate": 2e-05,
      "loss": 0.7989,
      "step": 1570
    },
    {
      "epoch": 0.0739838921146282,
      "grad_norm": 0.46297210454940796,
      "learning_rate": 2e-05,
      "loss": 0.8065,
      "step": 1580
    },
    {
      "epoch": 0.07445214459636636,
      "grad_norm": 0.5150440335273743,
      "learning_rate": 2e-05,
      "loss": 0.8284,
      "step": 1590
    },
    {
      "epoch": 0.07492039707810451,
      "grad_norm": 0.47179800271987915,
      "learning_rate": 2e-05,
      "loss": 0.8059,
      "step": 1600
    },
    {
      "epoch": 0.07538864955984266,
      "grad_norm": 0.4652591347694397,
      "learning_rate": 2e-05,
      "loss": 0.8229,
      "step": 1610
    },
    {
      "epoch": 0.07585690204158083,
      "grad_norm": 0.4540858864784241,
      "learning_rate": 2e-05,
      "loss": 0.7697,
      "step": 1620
    },
    {
      "epoch": 0.07632515452331898,
      "grad_norm": 0.4078024923801422,
      "learning_rate": 2e-05,
      "loss": 0.8106,
      "step": 1630
    },
    {
      "epoch": 0.07679340700505713,
      "grad_norm": 0.44727492332458496,
      "learning_rate": 2e-05,
      "loss": 0.8216,
      "step": 1640
    },
    {
      "epoch": 0.07726165948679528,
      "grad_norm": 0.46308594942092896,
      "learning_rate": 2e-05,
      "loss": 0.8184,
      "step": 1650
    },
    {
      "epoch": 0.07772991196853343,
      "grad_norm": 0.4770665764808655,
      "learning_rate": 2e-05,
      "loss": 0.7977,
      "step": 1660
    },
    {
      "epoch": 0.07819816445027158,
      "grad_norm": 0.4776230752468109,
      "learning_rate": 2e-05,
      "loss": 0.7921,
      "step": 1670
    },
    {
      "epoch": 0.07866641693200974,
      "grad_norm": 0.5174942016601562,
      "learning_rate": 2e-05,
      "loss": 0.8066,
      "step": 1680
    },
    {
      "epoch": 0.07913466941374789,
      "grad_norm": 0.43850815296173096,
      "learning_rate": 2e-05,
      "loss": 0.8068,
      "step": 1690
    },
    {
      "epoch": 0.07960292189548604,
      "grad_norm": 1.0964583158493042,
      "learning_rate": 2e-05,
      "loss": 0.7769,
      "step": 1700
    },
    {
      "epoch": 0.0800711743772242,
      "grad_norm": 0.4482307434082031,
      "learning_rate": 2e-05,
      "loss": 0.7822,
      "step": 1710
    },
    {
      "epoch": 0.08053942685896236,
      "grad_norm": 0.5412369966506958,
      "learning_rate": 2e-05,
      "loss": 0.7915,
      "step": 1720
    },
    {
      "epoch": 0.08100767934070051,
      "grad_norm": 0.4515257179737091,
      "learning_rate": 2e-05,
      "loss": 0.8215,
      "step": 1730
    },
    {
      "epoch": 0.08147593182243866,
      "grad_norm": 0.4404001533985138,
      "learning_rate": 2e-05,
      "loss": 0.8162,
      "step": 1740
    },
    {
      "epoch": 0.08194418430417681,
      "grad_norm": 0.4400689899921417,
      "learning_rate": 2e-05,
      "loss": 0.7876,
      "step": 1750
    },
    {
      "epoch": 0.08241243678591496,
      "grad_norm": 0.4302707314491272,
      "learning_rate": 2e-05,
      "loss": 0.8352,
      "step": 1760
    },
    {
      "epoch": 0.08288068926765312,
      "grad_norm": 0.4659354090690613,
      "learning_rate": 2e-05,
      "loss": 0.7758,
      "step": 1770
    },
    {
      "epoch": 0.08334894174939127,
      "grad_norm": 0.4827459752559662,
      "learning_rate": 2e-05,
      "loss": 0.7892,
      "step": 1780
    },
    {
      "epoch": 0.08381719423112942,
      "grad_norm": 1.0690308809280396,
      "learning_rate": 2e-05,
      "loss": 0.8228,
      "step": 1790
    },
    {
      "epoch": 0.08428544671286758,
      "grad_norm": 0.4485591650009155,
      "learning_rate": 2e-05,
      "loss": 0.7583,
      "step": 1800
    },
    {
      "epoch": 0.08475369919460574,
      "grad_norm": 0.44925209879875183,
      "learning_rate": 2e-05,
      "loss": 0.7587,
      "step": 1810
    },
    {
      "epoch": 0.08522195167634389,
      "grad_norm": 0.4562433063983917,
      "learning_rate": 2e-05,
      "loss": 0.7677,
      "step": 1820
    },
    {
      "epoch": 0.08569020415808204,
      "grad_norm": 0.45940324664115906,
      "learning_rate": 2e-05,
      "loss": 0.7985,
      "step": 1830
    },
    {
      "epoch": 0.08615845663982019,
      "grad_norm": 0.4248304069042206,
      "learning_rate": 2e-05,
      "loss": 0.7445,
      "step": 1840
    },
    {
      "epoch": 0.08662670912155834,
      "grad_norm": 0.48499906063079834,
      "learning_rate": 2e-05,
      "loss": 0.8037,
      "step": 1850
    },
    {
      "epoch": 0.0870949616032965,
      "grad_norm": 0.43459802865982056,
      "learning_rate": 2e-05,
      "loss": 0.7893,
      "step": 1860
    },
    {
      "epoch": 0.08756321408503465,
      "grad_norm": 0.521557629108429,
      "learning_rate": 2e-05,
      "loss": 0.79,
      "step": 1870
    },
    {
      "epoch": 0.0880314665667728,
      "grad_norm": 0.424723744392395,
      "learning_rate": 2e-05,
      "loss": 0.7598,
      "step": 1880
    },
    {
      "epoch": 0.08849971904851096,
      "grad_norm": 0.4430510401725769,
      "learning_rate": 2e-05,
      "loss": 0.8156,
      "step": 1890
    },
    {
      "epoch": 0.08896797153024912,
      "grad_norm": 0.43703287839889526,
      "learning_rate": 2e-05,
      "loss": 0.8031,
      "step": 1900
    },
    {
      "epoch": 0.08943622401198727,
      "grad_norm": 0.46375030279159546,
      "learning_rate": 2e-05,
      "loss": 0.7903,
      "step": 1910
    },
    {
      "epoch": 0.08990447649372542,
      "grad_norm": 0.46522295475006104,
      "learning_rate": 2e-05,
      "loss": 0.7418,
      "step": 1920
    },
    {
      "epoch": 0.09037272897546357,
      "grad_norm": 0.40295276045799255,
      "learning_rate": 2e-05,
      "loss": 0.781,
      "step": 1930
    },
    {
      "epoch": 0.09084098145720172,
      "grad_norm": 0.42140400409698486,
      "learning_rate": 2e-05,
      "loss": 0.7899,
      "step": 1940
    },
    {
      "epoch": 0.09130923393893987,
      "grad_norm": 0.6773248314857483,
      "learning_rate": 2e-05,
      "loss": 0.8514,
      "step": 1950
    },
    {
      "epoch": 0.09177748642067803,
      "grad_norm": 0.46820682287216187,
      "learning_rate": 2e-05,
      "loss": 0.8016,
      "step": 1960
    },
    {
      "epoch": 0.09224573890241618,
      "grad_norm": 0.4235709011554718,
      "learning_rate": 2e-05,
      "loss": 0.7933,
      "step": 1970
    },
    {
      "epoch": 0.09271399138415434,
      "grad_norm": 0.43302154541015625,
      "learning_rate": 2e-05,
      "loss": 0.7481,
      "step": 1980
    },
    {
      "epoch": 0.0931822438658925,
      "grad_norm": 0.4129074215888977,
      "learning_rate": 2e-05,
      "loss": 0.7644,
      "step": 1990
    },
    {
      "epoch": 0.09365049634763065,
      "grad_norm": 0.47755202651023865,
      "learning_rate": 2e-05,
      "loss": 0.7979,
      "step": 2000
    },
    {
      "epoch": 0.0941187488293688,
      "grad_norm": 0.4275096356868744,
      "learning_rate": 2e-05,
      "loss": 0.7869,
      "step": 2010
    },
    {
      "epoch": 0.09458700131110695,
      "grad_norm": 0.41398802399635315,
      "learning_rate": 2e-05,
      "loss": 0.7833,
      "step": 2020
    },
    {
      "epoch": 0.0950552537928451,
      "grad_norm": 0.4200058877468109,
      "learning_rate": 2e-05,
      "loss": 0.791,
      "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
}