{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 544,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00919963201471941,
      "grad_norm": 4.493361949920654,
      "learning_rate": 7e-06,
      "loss": 2.5772,
      "step": 5
    },
    {
      "epoch": 0.01839926402943882,
      "grad_norm": 2.119591236114502,
      "learning_rate": 1.575e-05,
      "loss": 2.35,
      "step": 10
    },
    {
      "epoch": 0.027598896044158234,
      "grad_norm": 0.7079921364784241,
      "learning_rate": 2.4499999999999996e-05,
      "loss": 1.9809,
      "step": 15
    },
    {
      "epoch": 0.03679852805887764,
      "grad_norm": 9.288702964782715,
      "learning_rate": 3.3249999999999995e-05,
      "loss": 1.8818,
      "step": 20
    },
    {
      "epoch": 0.045998160073597055,
      "grad_norm": 0.5875306129455566,
      "learning_rate": 4.2e-05,
      "loss": 1.8314,
      "step": 25
    },
    {
      "epoch": 0.05519779208831647,
      "grad_norm": 0.5792304873466492,
      "learning_rate": 5.0749999999999994e-05,
      "loss": 1.6966,
      "step": 30
    },
    {
      "epoch": 0.06439742410303588,
      "grad_norm": 0.5320371985435486,
      "learning_rate": 5.9499999999999996e-05,
      "loss": 1.7159,
      "step": 35
    },
    {
      "epoch": 0.07359705611775529,
      "grad_norm": 0.41402390599250793,
      "learning_rate": 6.824999999999999e-05,
      "loss": 1.6542,
      "step": 40
    },
    {
      "epoch": 0.0827966881324747,
      "grad_norm": 0.46447646617889404,
      "learning_rate": 6.98237885462555e-05,
      "loss": 1.5679,
      "step": 45
    },
    {
      "epoch": 0.09199632014719411,
      "grad_norm": 0.44029220938682556,
      "learning_rate": 6.960352422907488e-05,
      "loss": 1.6419,
      "step": 50
    },
    {
      "epoch": 0.10119595216191353,
      "grad_norm": 0.425231009721756,
      "learning_rate": 6.938325991189428e-05,
      "loss": 1.5516,
      "step": 55
    },
    {
      "epoch": 0.11039558417663294,
      "grad_norm": 0.4705358147621155,
      "learning_rate": 6.916299559471366e-05,
      "loss": 1.572,
      "step": 60
    },
    {
      "epoch": 0.11959521619135234,
      "grad_norm": 0.5355105400085449,
      "learning_rate": 6.894273127753303e-05,
      "loss": 1.5585,
      "step": 65
    },
    {
      "epoch": 0.12879484820607176,
      "grad_norm": 0.4822757840156555,
      "learning_rate": 6.872246696035241e-05,
      "loss": 1.5078,
      "step": 70
    },
    {
      "epoch": 0.13799448022079117,
      "grad_norm": 0.4612935781478882,
      "learning_rate": 6.85022026431718e-05,
      "loss": 1.5677,
      "step": 75
    },
    {
      "epoch": 0.14719411223551057,
      "grad_norm": 0.5228879451751709,
      "learning_rate": 6.828193832599119e-05,
      "loss": 1.5224,
      "step": 80
    },
    {
      "epoch": 0.15639374425023,
      "grad_norm": 0.4631298780441284,
      "learning_rate": 6.806167400881057e-05,
      "loss": 1.4413,
      "step": 85
    },
    {
      "epoch": 0.1655933762649494,
      "grad_norm": 0.5098944306373596,
      "learning_rate": 6.784140969162995e-05,
      "loss": 1.4965,
      "step": 90
    },
    {
      "epoch": 0.17479300827966882,
      "grad_norm": 0.5739426016807556,
      "learning_rate": 6.762114537444933e-05,
      "loss": 1.4526,
      "step": 95
    },
    {
      "epoch": 0.18399264029438822,
      "grad_norm": 0.5409196019172668,
      "learning_rate": 6.740088105726871e-05,
      "loss": 1.4667,
      "step": 100
    },
    {
      "epoch": 0.19319227230910763,
      "grad_norm": 0.6061224341392517,
      "learning_rate": 6.71806167400881e-05,
      "loss": 1.5092,
      "step": 105
    },
    {
      "epoch": 0.20239190432382706,
      "grad_norm": 4.403282642364502,
      "learning_rate": 6.696035242290749e-05,
      "loss": 1.42,
      "step": 110
    },
    {
      "epoch": 0.21159153633854647,
      "grad_norm": 0.5433526635169983,
      "learning_rate": 6.674008810572687e-05,
      "loss": 1.5852,
      "step": 115
    },
    {
      "epoch": 0.22079116835326587,
      "grad_norm": 0.5382786393165588,
      "learning_rate": 6.651982378854625e-05,
      "loss": 1.4788,
      "step": 120
    },
    {
      "epoch": 0.22999080036798528,
      "grad_norm": 0.5642833709716797,
      "learning_rate": 6.629955947136563e-05,
      "loss": 1.4694,
      "step": 125
    },
    {
      "epoch": 0.23919043238270468,
      "grad_norm": 0.5912417769432068,
      "learning_rate": 6.607929515418502e-05,
      "loss": 1.4685,
      "step": 130
    },
    {
      "epoch": 0.24839006439742412,
      "grad_norm": 0.584441602230072,
      "learning_rate": 6.58590308370044e-05,
      "loss": 1.4401,
      "step": 135
    },
    {
      "epoch": 0.2575896964121435,
      "grad_norm": 0.5686805844306946,
      "learning_rate": 6.563876651982378e-05,
      "loss": 1.4622,
      "step": 140
    },
    {
      "epoch": 0.2667893284268629,
      "grad_norm": 0.5634583234786987,
      "learning_rate": 6.541850220264316e-05,
      "loss": 1.4674,
      "step": 145
    },
    {
      "epoch": 0.27598896044158233,
      "grad_norm": 0.5362507700920105,
      "learning_rate": 6.519823788546254e-05,
      "loss": 1.4368,
      "step": 150
    },
    {
      "epoch": 0.28518859245630174,
      "grad_norm": 0.528346836566925,
      "learning_rate": 6.497797356828193e-05,
      "loss": 1.4645,
      "step": 155
    },
    {
      "epoch": 0.29438822447102114,
      "grad_norm": 0.6441851258277893,
      "learning_rate": 6.475770925110131e-05,
      "loss": 1.4359,
      "step": 160
    },
    {
      "epoch": 0.30358785648574055,
      "grad_norm": 0.6480420231819153,
      "learning_rate": 6.45374449339207e-05,
      "loss": 1.5072,
      "step": 165
    },
    {
      "epoch": 0.31278748850046,
      "grad_norm": 0.6448924541473389,
      "learning_rate": 6.431718061674008e-05,
      "loss": 1.3991,
      "step": 170
    },
    {
      "epoch": 0.3219871205151794,
      "grad_norm": 232.7066650390625,
      "learning_rate": 6.409691629955947e-05,
      "loss": 1.4437,
      "step": 175
    },
    {
      "epoch": 0.3311867525298988,
      "grad_norm": 0.6596648097038269,
      "learning_rate": 6.387665198237885e-05,
      "loss": 1.4778,
      "step": 180
    },
    {
      "epoch": 0.3403863845446182,
      "grad_norm": 0.6211815476417542,
      "learning_rate": 6.365638766519823e-05,
      "loss": 1.4235,
      "step": 185
    },
    {
      "epoch": 0.34958601655933763,
      "grad_norm": 0.597537636756897,
      "learning_rate": 6.343612334801761e-05,
      "loss": 1.4416,
      "step": 190
    },
    {
      "epoch": 0.35878564857405704,
      "grad_norm": 0.5805206894874573,
      "learning_rate": 6.321585903083701e-05,
      "loss": 1.4412,
      "step": 195
    },
    {
      "epoch": 0.36798528058877644,
      "grad_norm": 0.6511718034744263,
      "learning_rate": 6.299559471365639e-05,
      "loss": 1.4406,
      "step": 200
    },
    {
      "epoch": 0.37718491260349585,
      "grad_norm": 0.6224706768989563,
      "learning_rate": 6.277533039647577e-05,
      "loss": 1.428,
      "step": 205
    },
    {
      "epoch": 0.38638454461821525,
      "grad_norm": 0.7181910276412964,
      "learning_rate": 6.255506607929515e-05,
      "loss": 1.4363,
      "step": 210
    },
    {
      "epoch": 0.39558417663293466,
      "grad_norm": 0.6790558695793152,
      "learning_rate": 6.233480176211453e-05,
      "loss": 1.4516,
      "step": 215
    },
    {
      "epoch": 0.4047838086476541,
      "grad_norm": 0.9428783655166626,
      "learning_rate": 6.211453744493392e-05,
      "loss": 1.4527,
      "step": 220
    },
    {
      "epoch": 0.4139834406623735,
      "grad_norm": 0.7599747180938721,
      "learning_rate": 6.18942731277533e-05,
      "loss": 1.4756,
      "step": 225
    },
    {
      "epoch": 0.42318307267709293,
      "grad_norm": 0.5899630784988403,
      "learning_rate": 6.167400881057268e-05,
      "loss": 1.4126,
      "step": 230
    },
    {
      "epoch": 0.43238270469181234,
      "grad_norm": 0.7069624066352844,
      "learning_rate": 6.145374449339206e-05,
      "loss": 1.3768,
      "step": 235
    },
    {
      "epoch": 0.44158233670653174,
      "grad_norm": 1.1761517524719238,
      "learning_rate": 6.123348017621144e-05,
      "loss": 1.3948,
      "step": 240
    },
    {
      "epoch": 0.45078196872125115,
      "grad_norm": 0.8364585041999817,
      "learning_rate": 6.101321585903083e-05,
      "loss": 1.4601,
      "step": 245
    },
    {
      "epoch": 0.45998160073597055,
      "grad_norm": 0.7272374033927917,
      "learning_rate": 6.0792951541850214e-05,
      "loss": 1.4054,
      "step": 250
    },
    {
      "epoch": 0.46918123275068996,
      "grad_norm": 0.722029983997345,
      "learning_rate": 6.0572687224669595e-05,
      "loss": 1.4382,
      "step": 255
    },
    {
      "epoch": 0.47838086476540936,
      "grad_norm": 0.7180947065353394,
      "learning_rate": 6.0352422907488984e-05,
      "loss": 1.414,
      "step": 260
    },
    {
      "epoch": 0.48758049678012877,
      "grad_norm": 0.8569415211677551,
      "learning_rate": 6.0132158590308366e-05,
      "loss": 1.3801,
      "step": 265
    },
    {
      "epoch": 0.49678012879484823,
      "grad_norm": 0.6971564292907715,
      "learning_rate": 5.991189427312775e-05,
      "loss": 1.4264,
      "step": 270
    },
    {
      "epoch": 0.5059797608095676,
      "grad_norm": 1.1400465965270996,
      "learning_rate": 5.9691629955947136e-05,
      "loss": 1.4571,
      "step": 275
    },
    {
      "epoch": 0.515179392824287,
      "grad_norm": 0.6640013456344604,
      "learning_rate": 5.947136563876652e-05,
      "loss": 1.4494,
      "step": 280
    },
    {
      "epoch": 0.5243790248390064,
      "grad_norm": 0.612842857837677,
      "learning_rate": 5.92511013215859e-05,
      "loss": 1.3979,
      "step": 285
    },
    {
      "epoch": 0.5335786568537259,
      "grad_norm": 6.370260715484619,
      "learning_rate": 5.903083700440528e-05,
      "loss": 1.4008,
      "step": 290
    },
    {
      "epoch": 0.5427782888684453,
      "grad_norm": 0.6938475966453552,
      "learning_rate": 5.881057268722466e-05,
      "loss": 1.3901,
      "step": 295
    },
    {
      "epoch": 0.5519779208831647,
      "grad_norm": 0.7252101302146912,
      "learning_rate": 5.8590308370044045e-05,
      "loss": 1.4129,
      "step": 300
    },
    {
      "epoch": 0.5611775528978841,
      "grad_norm": 0.7261694669723511,
      "learning_rate": 5.837004405286343e-05,
      "loss": 1.4504,
      "step": 305
    },
    {
      "epoch": 0.5703771849126035,
      "grad_norm": 1.128242015838623,
      "learning_rate": 5.8149779735682815e-05,
      "loss": 1.4392,
      "step": 310
    },
    {
      "epoch": 0.5795768169273229,
      "grad_norm": 0.7343323230743408,
      "learning_rate": 5.79295154185022e-05,
      "loss": 1.4001,
      "step": 315
    },
    {
      "epoch": 0.5887764489420423,
      "grad_norm": 0.6398953795433044,
      "learning_rate": 5.770925110132158e-05,
      "loss": 1.4533,
      "step": 320
    },
    {
      "epoch": 0.5979760809567617,
      "grad_norm": 0.9343668222427368,
      "learning_rate": 5.748898678414096e-05,
      "loss": 1.4464,
      "step": 325
    },
    {
      "epoch": 0.6071757129714811,
      "grad_norm": 0.7744137644767761,
      "learning_rate": 5.726872246696035e-05,
      "loss": 1.3802,
      "step": 330
    },
    {
      "epoch": 0.6163753449862005,
      "grad_norm": 0.7824112772941589,
      "learning_rate": 5.704845814977973e-05,
      "loss": 1.3885,
      "step": 335
    },
    {
      "epoch": 0.62557497700092,
      "grad_norm": 0.7310079336166382,
      "learning_rate": 5.682819383259911e-05,
      "loss": 1.3351,
      "step": 340
    },
    {
      "epoch": 0.6347746090156394,
      "grad_norm": 0.6795840859413147,
      "learning_rate": 5.66079295154185e-05,
      "loss": 1.4371,
      "step": 345
    },
    {
      "epoch": 0.6439742410303588,
      "grad_norm": 0.7529902458190918,
      "learning_rate": 5.638766519823788e-05,
      "loss": 1.4985,
      "step": 350
    },
    {
      "epoch": 0.6531738730450782,
      "grad_norm": 0.7649794220924377,
      "learning_rate": 5.6167400881057265e-05,
      "loss": 1.4007,
      "step": 355
    },
    {
      "epoch": 0.6623735050597976,
      "grad_norm": 0.8272032141685486,
      "learning_rate": 5.594713656387665e-05,
      "loss": 1.4233,
      "step": 360
    },
    {
      "epoch": 0.671573137074517,
      "grad_norm": 0.7489705085754395,
      "learning_rate": 5.5726872246696035e-05,
      "loss": 1.3739,
      "step": 365
    },
    {
      "epoch": 0.6807727690892365,
      "grad_norm": 0.8254089951515198,
      "learning_rate": 5.550660792951541e-05,
      "loss": 1.5,
      "step": 370
    },
    {
      "epoch": 0.6899724011039559,
      "grad_norm": 0.7875320911407471,
      "learning_rate": 5.528634361233479e-05,
      "loss": 1.3998,
      "step": 375
    },
    {
      "epoch": 0.6991720331186753,
      "grad_norm": 0.7118289470672607,
      "learning_rate": 5.506607929515418e-05,
      "loss": 1.4549,
      "step": 380
    },
    {
      "epoch": 0.7083716651333947,
      "grad_norm": 0.7725639343261719,
      "learning_rate": 5.484581497797356e-05,
      "loss": 1.3842,
      "step": 385
    },
    {
      "epoch": 0.7175712971481141,
      "grad_norm": 1.2431738376617432,
      "learning_rate": 5.4625550660792944e-05,
      "loss": 1.4364,
      "step": 390
    },
    {
      "epoch": 0.7267709291628335,
      "grad_norm": 0.9481919407844543,
      "learning_rate": 5.4405286343612326e-05,
      "loss": 1.3786,
      "step": 395
    },
    {
      "epoch": 0.7359705611775529,
      "grad_norm": 0.7844451069831848,
      "learning_rate": 5.4185022026431715e-05,
      "loss": 1.3388,
      "step": 400
    },
    {
      "epoch": 0.7451701931922723,
      "grad_norm": 0.8081017136573792,
      "learning_rate": 5.3964757709251096e-05,
      "loss": 1.4376,
      "step": 405
    },
    {
      "epoch": 0.7543698252069917,
      "grad_norm": 13030255.0,
      "learning_rate": 5.374449339207048e-05,
      "loss": 1.439,
      "step": 410
    },
    {
      "epoch": 0.7635694572217111,
      "grad_norm": 0.7132210731506348,
      "learning_rate": 5.352422907488987e-05,
      "loss": 1.392,
      "step": 415
    },
    {
      "epoch": 0.7727690892364305,
      "grad_norm": 0.8951236009597778,
      "learning_rate": 5.330396475770925e-05,
      "loss": 1.3945,
      "step": 420
    },
    {
      "epoch": 0.7819687212511499,
      "grad_norm": 0.7916706800460815,
      "learning_rate": 5.308370044052863e-05,
      "loss": 1.3567,
      "step": 425
    },
    {
      "epoch": 0.7911683532658693,
      "grad_norm": 0.8253033757209778,
      "learning_rate": 5.286343612334801e-05,
      "loss": 1.3707,
      "step": 430
    },
    {
      "epoch": 0.8003679852805887,
      "grad_norm": 0.8816981911659241,
      "learning_rate": 5.26431718061674e-05,
      "loss": 1.3911,
      "step": 435
    },
    {
      "epoch": 0.8095676172953082,
      "grad_norm": 0.7913665175437927,
      "learning_rate": 5.242290748898678e-05,
      "loss": 1.3613,
      "step": 440
    },
    {
      "epoch": 0.8187672493100276,
      "grad_norm": 0.7874677777290344,
      "learning_rate": 5.2202643171806164e-05,
      "loss": 1.4487,
      "step": 445
    },
    {
      "epoch": 0.827966881324747,
      "grad_norm": 0.7003588080406189,
      "learning_rate": 5.1982378854625546e-05,
      "loss": 1.3712,
      "step": 450
    },
    {
      "epoch": 0.8371665133394665,
      "grad_norm": 0.7311933040618896,
      "learning_rate": 5.176211453744493e-05,
      "loss": 1.3422,
      "step": 455
    },
    {
      "epoch": 0.8463661453541859,
      "grad_norm": 0.823244571685791,
      "learning_rate": 5.154185022026431e-05,
      "loss": 1.3605,
      "step": 460
    },
    {
      "epoch": 0.8555657773689053,
      "grad_norm": 0.8285578489303589,
      "learning_rate": 5.132158590308369e-05,
      "loss": 1.418,
      "step": 465
    },
    {
      "epoch": 0.8647654093836247,
      "grad_norm": 0.8007466197013855,
      "learning_rate": 5.110132158590308e-05,
      "loss": 1.3539,
      "step": 470
    },
    {
      "epoch": 0.8739650413983441,
      "grad_norm": 0.7975384593009949,
      "learning_rate": 5.088105726872246e-05,
      "loss": 1.3959,
      "step": 475
    },
    {
      "epoch": 0.8831646734130635,
      "grad_norm": 0.931978702545166,
      "learning_rate": 5.0660792951541843e-05,
      "loss": 1.3734,
      "step": 480
    },
    {
      "epoch": 0.8923643054277829,
      "grad_norm": 0.9099324345588684,
      "learning_rate": 5.044052863436123e-05,
      "loss": 1.3722,
      "step": 485
    },
    {
      "epoch": 0.9015639374425023,
      "grad_norm": 0.7978657484054565,
      "learning_rate": 5.0220264317180614e-05,
      "loss": 1.3741,
      "step": 490
    },
    {
      "epoch": 0.9107635694572217,
      "grad_norm": 0.8722144365310669,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 1.3869,
      "step": 495
    },
    {
      "epoch": 0.9199632014719411,
      "grad_norm": 1309.4061279296875,
      "learning_rate": 4.977973568281938e-05,
      "loss": 1.4329,
      "step": 500
    },
    {
      "epoch": 0.9291628334866605,
      "grad_norm": 0.807162880897522,
      "learning_rate": 4.9559471365638766e-05,
      "loss": 1.3755,
      "step": 505
    },
    {
      "epoch": 0.9383624655013799,
      "grad_norm": 0.9719377160072327,
      "learning_rate": 4.933920704845815e-05,
      "loss": 1.4036,
      "step": 510
    },
    {
      "epoch": 0.9475620975160993,
      "grad_norm": 3.86576247215271,
      "learning_rate": 4.911894273127753e-05,
      "loss": 1.3866,
      "step": 515
    },
    {
      "epoch": 0.9567617295308187,
      "grad_norm": 0.8033193945884705,
      "learning_rate": 4.889867841409692e-05,
      "loss": 1.3861,
      "step": 520
    },
    {
      "epoch": 0.9659613615455381,
      "grad_norm": 0.8535065650939941,
      "learning_rate": 4.867841409691629e-05,
      "loss": 1.2592,
      "step": 525
    },
    {
      "epoch": 0.9751609935602575,
      "grad_norm": 0.8155761957168579,
      "learning_rate": 4.8458149779735675e-05,
      "loss": 1.3123,
      "step": 530
    },
    {
      "epoch": 0.984360625574977,
      "grad_norm": 155.9907989501953,
      "learning_rate": 4.823788546255506e-05,
      "loss": 1.3567,
      "step": 535
    },
    {
      "epoch": 0.9935602575896965,
      "grad_norm": 2.225149631500244,
      "learning_rate": 4.8017621145374445e-05,
      "loss": 1.3736,
      "step": 540
    }
  ],
  "logging_steps": 5,
  "max_steps": 1629,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.125792658549078e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}