{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19085225403093123,
  "eval_steps": 500,
  "global_step": 580,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016452780519907865,
      "grad_norm": 1.5217232704162598,
      "learning_rate": 0.00012,
      "loss": 4.5224,
      "step": 5
    },
    {
      "epoch": 0.003290556103981573,
      "grad_norm": 0.574784517288208,
      "learning_rate": 0.0001998022412656559,
      "loss": 3.2397,
      "step": 10
    },
    {
      "epoch": 0.004935834155972359,
      "grad_norm": 0.5069302320480347,
      "learning_rate": 0.0001994726433750824,
      "loss": 2.7151,
      "step": 15
    },
    {
      "epoch": 0.006581112207963146,
      "grad_norm": 0.5865616202354431,
      "learning_rate": 0.00019914304548450891,
      "loss": 2.3507,
      "step": 20
    },
    {
      "epoch": 0.008226390259953932,
      "grad_norm": 0.5909593105316162,
      "learning_rate": 0.0001988134475939354,
      "loss": 2.3338,
      "step": 25
    },
    {
      "epoch": 0.009871668311944718,
      "grad_norm": 0.4913259744644165,
      "learning_rate": 0.0001984838497033619,
      "loss": 2.3544,
      "step": 30
    },
    {
      "epoch": 0.011516946363935505,
      "grad_norm": 0.4331064522266388,
      "learning_rate": 0.00019815425181278842,
      "loss": 2.2672,
      "step": 35
    },
    {
      "epoch": 0.013162224415926292,
      "grad_norm": 0.42509177327156067,
      "learning_rate": 0.0001978246539222149,
      "loss": 2.2764,
      "step": 40
    },
    {
      "epoch": 0.014807502467917079,
      "grad_norm": 0.415414035320282,
      "learning_rate": 0.0001974950560316414,
      "loss": 2.1035,
      "step": 45
    },
    {
      "epoch": 0.016452780519907863,
      "grad_norm": 0.5336166024208069,
      "learning_rate": 0.0001971654581410679,
      "loss": 2.2284,
      "step": 50
    },
    {
      "epoch": 0.01809805857189865,
      "grad_norm": 0.3719511926174164,
      "learning_rate": 0.0001968358602504944,
      "loss": 2.1656,
      "step": 55
    },
    {
      "epoch": 0.019743336623889437,
      "grad_norm": 0.49993693828582764,
      "learning_rate": 0.00019650626235992092,
      "loss": 2.0299,
      "step": 60
    },
    {
      "epoch": 0.021388614675880224,
      "grad_norm": 0.5019952654838562,
      "learning_rate": 0.0001961766644693474,
      "loss": 2.0951,
      "step": 65
    },
    {
      "epoch": 0.02303389272787101,
      "grad_norm": 0.4793168306350708,
      "learning_rate": 0.0001958470665787739,
      "loss": 2.1505,
      "step": 70
    },
    {
      "epoch": 0.024679170779861797,
      "grad_norm": 0.47024038434028625,
      "learning_rate": 0.0001955174686882004,
      "loss": 2.054,
      "step": 75
    },
    {
      "epoch": 0.026324448831852584,
      "grad_norm": 0.5920702815055847,
      "learning_rate": 0.0001951878707976269,
      "loss": 2.1802,
      "step": 80
    },
    {
      "epoch": 0.02796972688384337,
      "grad_norm": 0.4485560655593872,
      "learning_rate": 0.0001948582729070534,
      "loss": 2.1609,
      "step": 85
    },
    {
      "epoch": 0.029615004935834157,
      "grad_norm": 0.41952958703041077,
      "learning_rate": 0.0001945286750164799,
      "loss": 2.0584,
      "step": 90
    },
    {
      "epoch": 0.03126028298782494,
      "grad_norm": 0.40542706847190857,
      "learning_rate": 0.00019419907712590643,
      "loss": 2.22,
      "step": 95
    },
    {
      "epoch": 0.03290556103981573,
      "grad_norm": 0.438912570476532,
      "learning_rate": 0.0001938694792353329,
      "loss": 2.1478,
      "step": 100
    },
    {
      "epoch": 0.034550839091806514,
      "grad_norm": 0.46580272912979126,
      "learning_rate": 0.0001935398813447594,
      "loss": 2.1227,
      "step": 105
    },
    {
      "epoch": 0.0361961171437973,
      "grad_norm": 0.5012261271476746,
      "learning_rate": 0.0001932102834541859,
      "loss": 2.1274,
      "step": 110
    },
    {
      "epoch": 0.03784139519578809,
      "grad_norm": 0.5175459384918213,
      "learning_rate": 0.0001928806855636124,
      "loss": 2.0726,
      "step": 115
    },
    {
      "epoch": 0.039486673247778874,
      "grad_norm": 0.5441685318946838,
      "learning_rate": 0.00019255108767303892,
      "loss": 2.1269,
      "step": 120
    },
    {
      "epoch": 0.04113195129976966,
      "grad_norm": 0.4177902042865753,
      "learning_rate": 0.0001922214897824654,
      "loss": 2.164,
      "step": 125
    },
    {
      "epoch": 0.04277722935176045,
      "grad_norm": 0.44649720191955566,
      "learning_rate": 0.0001918918918918919,
      "loss": 2.0883,
      "step": 130
    },
    {
      "epoch": 0.044422507403751234,
      "grad_norm": 0.46839994192123413,
      "learning_rate": 0.0001915622940013184,
      "loss": 2.0448,
      "step": 135
    },
    {
      "epoch": 0.04606778545574202,
      "grad_norm": 0.4343637228012085,
      "learning_rate": 0.0001912326961107449,
      "loss": 2.0282,
      "step": 140
    },
    {
      "epoch": 0.04771306350773281,
      "grad_norm": 0.4241706132888794,
      "learning_rate": 0.00019090309822017141,
      "loss": 2.0895,
      "step": 145
    },
    {
      "epoch": 0.049358341559723594,
      "grad_norm": 0.44053712487220764,
      "learning_rate": 0.0001905735003295979,
      "loss": 2.0925,
      "step": 150
    },
    {
      "epoch": 0.05100361961171438,
      "grad_norm": 0.39026254415512085,
      "learning_rate": 0.0001902439024390244,
      "loss": 2.1519,
      "step": 155
    },
    {
      "epoch": 0.05264889766370517,
      "grad_norm": 0.455168217420578,
      "learning_rate": 0.0001899143045484509,
      "loss": 2.1623,
      "step": 160
    },
    {
      "epoch": 0.054294175715695954,
      "grad_norm": 0.4873504042625427,
      "learning_rate": 0.0001895847066578774,
      "loss": 1.9314,
      "step": 165
    },
    {
      "epoch": 0.05593945376768674,
      "grad_norm": 0.5435200929641724,
      "learning_rate": 0.0001892551087673039,
      "loss": 2.0674,
      "step": 170
    },
    {
      "epoch": 0.05758473181967753,
      "grad_norm": 0.44813185930252075,
      "learning_rate": 0.0001889255108767304,
      "loss": 2.0042,
      "step": 175
    },
    {
      "epoch": 0.059230009871668314,
      "grad_norm": 0.5993271470069885,
      "learning_rate": 0.0001885959129861569,
      "loss": 2.0942,
      "step": 180
    },
    {
      "epoch": 0.0608752879236591,
      "grad_norm": 0.5044869780540466,
      "learning_rate": 0.0001882663150955834,
      "loss": 2.118,
      "step": 185
    },
    {
      "epoch": 0.06252056597564988,
      "grad_norm": 0.4713231325149536,
      "learning_rate": 0.00018793671720500988,
      "loss": 2.1232,
      "step": 190
    },
    {
      "epoch": 0.06416584402764067,
      "grad_norm": 0.5351199507713318,
      "learning_rate": 0.0001876071193144364,
      "loss": 2.0956,
      "step": 195
    },
    {
      "epoch": 0.06581112207963145,
      "grad_norm": 0.380096971988678,
      "learning_rate": 0.0001872775214238629,
      "loss": 2.0466,
      "step": 200
    },
    {
      "epoch": 0.06745640013162224,
      "grad_norm": 0.4392818510532379,
      "learning_rate": 0.0001869479235332894,
      "loss": 2.0503,
      "step": 205
    },
    {
      "epoch": 0.06910167818361303,
      "grad_norm": 0.49540552496910095,
      "learning_rate": 0.00018661832564271588,
      "loss": 2.0771,
      "step": 210
    },
    {
      "epoch": 0.07074695623560381,
      "grad_norm": 0.5129232406616211,
      "learning_rate": 0.00018628872775214238,
      "loss": 1.9724,
      "step": 215
    },
    {
      "epoch": 0.0723922342875946,
      "grad_norm": 0.4697638750076294,
      "learning_rate": 0.0001859591298615689,
      "loss": 2.03,
      "step": 220
    },
    {
      "epoch": 0.07403751233958539,
      "grad_norm": 0.4250948131084442,
      "learning_rate": 0.0001856295319709954,
      "loss": 2.0235,
      "step": 225
    },
    {
      "epoch": 0.07568279039157617,
      "grad_norm": 0.5197622776031494,
      "learning_rate": 0.0001852999340804219,
      "loss": 1.991,
      "step": 230
    },
    {
      "epoch": 0.07732806844356696,
      "grad_norm": 0.45986393094062805,
      "learning_rate": 0.0001849703361898484,
      "loss": 2.0191,
      "step": 235
    },
    {
      "epoch": 0.07897334649555775,
      "grad_norm": 0.5618834495544434,
      "learning_rate": 0.00018464073829927487,
      "loss": 1.9859,
      "step": 240
    },
    {
      "epoch": 0.08061862454754853,
      "grad_norm": 0.5400542616844177,
      "learning_rate": 0.0001843111404087014,
      "loss": 1.9633,
      "step": 245
    },
    {
      "epoch": 0.08226390259953932,
      "grad_norm": 0.5259667038917542,
      "learning_rate": 0.0001839815425181279,
      "loss": 1.8768,
      "step": 250
    },
    {
      "epoch": 0.08390918065153011,
      "grad_norm": 0.5015618801116943,
      "learning_rate": 0.0001836519446275544,
      "loss": 2.0329,
      "step": 255
    },
    {
      "epoch": 0.0855544587035209,
      "grad_norm": 0.4835856854915619,
      "learning_rate": 0.0001833223467369809,
      "loss": 1.9815,
      "step": 260
    },
    {
      "epoch": 0.08719973675551168,
      "grad_norm": 0.4211411774158478,
      "learning_rate": 0.0001829927488464074,
      "loss": 1.9899,
      "step": 265
    },
    {
      "epoch": 0.08884501480750247,
      "grad_norm": 0.4507792294025421,
      "learning_rate": 0.0001826631509558339,
      "loss": 1.9865,
      "step": 270
    },
    {
      "epoch": 0.09049029285949325,
      "grad_norm": 0.5402964353561401,
      "learning_rate": 0.00018233355306526038,
      "loss": 1.902,
      "step": 275
    },
    {
      "epoch": 0.09213557091148404,
      "grad_norm": 0.4574088454246521,
      "learning_rate": 0.0001820039551746869,
      "loss": 1.9727,
      "step": 280
    },
    {
      "epoch": 0.09378084896347483,
      "grad_norm": 0.4615534842014313,
      "learning_rate": 0.0001816743572841134,
      "loss": 2.0582,
      "step": 285
    },
    {
      "epoch": 0.09542612701546561,
      "grad_norm": 0.5126486420631409,
      "learning_rate": 0.0001813447593935399,
      "loss": 2.0274,
      "step": 290
    },
    {
      "epoch": 0.0970714050674564,
      "grad_norm": 0.6757667660713196,
      "learning_rate": 0.00018101516150296638,
      "loss": 1.879,
      "step": 295
    },
    {
      "epoch": 0.09871668311944719,
      "grad_norm": 0.49488508701324463,
      "learning_rate": 0.00018068556361239288,
      "loss": 1.9348,
      "step": 300
    },
    {
      "epoch": 0.10036196117143797,
      "grad_norm": 0.5860428810119629,
      "learning_rate": 0.0001803559657218194,
      "loss": 1.9276,
      "step": 305
    },
    {
      "epoch": 0.10200723922342876,
      "grad_norm": 0.5148414373397827,
      "learning_rate": 0.0001800263678312459,
      "loss": 2.0563,
      "step": 310
    },
    {
      "epoch": 0.10365251727541955,
      "grad_norm": 0.5046892762184143,
      "learning_rate": 0.00017969676994067238,
      "loss": 2.0009,
      "step": 315
    },
    {
      "epoch": 0.10529779532741033,
      "grad_norm": 0.4465779960155487,
      "learning_rate": 0.0001793671720500989,
      "loss": 1.9842,
      "step": 320
    },
    {
      "epoch": 0.10694307337940112,
      "grad_norm": 0.4488319158554077,
      "learning_rate": 0.00017903757415952537,
      "loss": 1.9881,
      "step": 325
    },
    {
      "epoch": 0.10858835143139191,
      "grad_norm": 0.46680882573127747,
      "learning_rate": 0.0001787079762689519,
      "loss": 2.0471,
      "step": 330
    },
    {
      "epoch": 0.1102336294833827,
      "grad_norm": 0.5483986139297485,
      "learning_rate": 0.00017837837837837839,
      "loss": 2.0581,
      "step": 335
    },
    {
      "epoch": 0.11187890753537348,
      "grad_norm": 0.4938408434391022,
      "learning_rate": 0.00017804878048780488,
      "loss": 1.9712,
      "step": 340
    },
    {
      "epoch": 0.11352418558736427,
      "grad_norm": 0.4176371991634369,
      "learning_rate": 0.0001777191825972314,
      "loss": 1.9019,
      "step": 345
    },
    {
      "epoch": 0.11516946363935505,
      "grad_norm": 0.45936137437820435,
      "learning_rate": 0.0001773895847066579,
      "loss": 1.8773,
      "step": 350
    },
    {
      "epoch": 0.11681474169134584,
      "grad_norm": 0.5166374444961548,
      "learning_rate": 0.0001770599868160844,
      "loss": 2.0059,
      "step": 355
    },
    {
      "epoch": 0.11846001974333663,
      "grad_norm": 0.5485665202140808,
      "learning_rate": 0.00017673038892551088,
      "loss": 1.9634,
      "step": 360
    },
    {
      "epoch": 0.12010529779532741,
      "grad_norm": 0.44683098793029785,
      "learning_rate": 0.00017640079103493737,
      "loss": 1.9239,
      "step": 365
    },
    {
      "epoch": 0.1217505758473182,
      "grad_norm": 0.4426558315753937,
      "learning_rate": 0.0001760711931443639,
      "loss": 1.9467,
      "step": 370
    },
    {
      "epoch": 0.12339585389930899,
      "grad_norm": 0.45059794187545776,
      "learning_rate": 0.0001757415952537904,
      "loss": 1.9099,
      "step": 375
    },
    {
      "epoch": 0.12504113195129976,
      "grad_norm": 0.47326767444610596,
      "learning_rate": 0.00017541199736321688,
      "loss": 1.9521,
      "step": 380
    },
    {
      "epoch": 0.12668641000329056,
      "grad_norm": 0.4886496961116791,
      "learning_rate": 0.00017508239947264337,
      "loss": 1.9336,
      "step": 385
    },
    {
      "epoch": 0.12833168805528133,
      "grad_norm": 0.4394533336162567,
      "learning_rate": 0.00017475280158206987,
      "loss": 1.8583,
      "step": 390
    },
    {
      "epoch": 0.12997696610727213,
      "grad_norm": 0.5217518210411072,
      "learning_rate": 0.0001744232036914964,
      "loss": 1.9916,
      "step": 395
    },
    {
      "epoch": 0.1316222441592629,
      "grad_norm": 0.44888633489608765,
      "learning_rate": 0.00017409360580092288,
      "loss": 2.0022,
      "step": 400
    },
    {
      "epoch": 0.1332675222112537,
      "grad_norm": 0.5385366678237915,
      "learning_rate": 0.0001737640079103494,
      "loss": 1.9492,
      "step": 405
    },
    {
      "epoch": 0.13491280026324448,
      "grad_norm": 0.4314708113670349,
      "learning_rate": 0.00017343441001977587,
      "loss": 2.0088,
      "step": 410
    },
    {
      "epoch": 0.13655807831523528,
      "grad_norm": 0.4006335735321045,
      "learning_rate": 0.00017310481212920236,
      "loss": 1.9524,
      "step": 415
    },
    {
      "epoch": 0.13820335636722605,
      "grad_norm": 0.5291544198989868,
      "learning_rate": 0.00017277521423862888,
      "loss": 1.8593,
      "step": 420
    },
    {
      "epoch": 0.13984863441921686,
      "grad_norm": 0.47129592299461365,
      "learning_rate": 0.00017244561634805538,
      "loss": 1.9542,
      "step": 425
    },
    {
      "epoch": 0.14149391247120763,
      "grad_norm": 0.449595183134079,
      "learning_rate": 0.0001721160184574819,
      "loss": 1.9294,
      "step": 430
    },
    {
      "epoch": 0.14313919052319843,
      "grad_norm": 0.4410437047481537,
      "learning_rate": 0.0001717864205669084,
      "loss": 1.9209,
      "step": 435
    },
    {
      "epoch": 0.1447844685751892,
      "grad_norm": 0.5655415654182434,
      "learning_rate": 0.00017145682267633488,
      "loss": 1.9486,
      "step": 440
    },
    {
      "epoch": 0.14642974662718,
      "grad_norm": 0.5219452381134033,
      "learning_rate": 0.00017112722478576138,
      "loss": 1.8922,
      "step": 445
    },
    {
      "epoch": 0.14807502467917077,
      "grad_norm": 0.49918806552886963,
      "learning_rate": 0.00017079762689518787,
      "loss": 1.92,
      "step": 450
    },
    {
      "epoch": 0.14972030273116158,
      "grad_norm": 0.4410875141620636,
      "learning_rate": 0.0001704680290046144,
      "loss": 1.9363,
      "step": 455
    },
    {
      "epoch": 0.15136558078315235,
      "grad_norm": 0.4709133207798004,
      "learning_rate": 0.00017013843111404089,
      "loss": 1.8803,
      "step": 460
    },
    {
      "epoch": 0.15301085883514315,
      "grad_norm": 0.447390079498291,
      "learning_rate": 0.00016980883322346738,
      "loss": 2.0388,
      "step": 465
    },
    {
      "epoch": 0.15465613688713392,
      "grad_norm": 0.4439023435115814,
      "learning_rate": 0.00016947923533289387,
      "loss": 1.9112,
      "step": 470
    },
    {
      "epoch": 0.15630141493912472,
      "grad_norm": 0.5134996175765991,
      "learning_rate": 0.00016914963744232037,
      "loss": 1.9556,
      "step": 475
    },
    {
      "epoch": 0.1579466929911155,
      "grad_norm": 0.5412283539772034,
      "learning_rate": 0.0001688200395517469,
      "loss": 1.899,
      "step": 480
    },
    {
      "epoch": 0.1595919710431063,
      "grad_norm": 0.46328097581863403,
      "learning_rate": 0.00016849044166117338,
      "loss": 1.8476,
      "step": 485
    },
    {
      "epoch": 0.16123724909509707,
      "grad_norm": 0.43716996908187866,
      "learning_rate": 0.00016816084377059987,
      "loss": 1.9059,
      "step": 490
    },
    {
      "epoch": 0.16288252714708787,
      "grad_norm": 0.4769724905490875,
      "learning_rate": 0.00016783124588002637,
      "loss": 1.9186,
      "step": 495
    },
    {
      "epoch": 0.16452780519907864,
      "grad_norm": 0.5047943592071533,
      "learning_rate": 0.00016750164798945286,
      "loss": 1.9161,
      "step": 500
    },
    {
      "epoch": 0.16617308325106944,
      "grad_norm": 0.4556055963039398,
      "learning_rate": 0.00016717205009887938,
      "loss": 1.8834,
      "step": 505
    },
    {
      "epoch": 0.16781836130306022,
      "grad_norm": 0.4692705571651459,
      "learning_rate": 0.00016684245220830588,
      "loss": 1.9091,
      "step": 510
    },
    {
      "epoch": 0.16946363935505102,
      "grad_norm": 0.43482905626296997,
      "learning_rate": 0.00016651285431773237,
      "loss": 1.9405,
      "step": 515
    },
    {
      "epoch": 0.1711089174070418,
      "grad_norm": 0.5708907246589661,
      "learning_rate": 0.0001661832564271589,
      "loss": 1.9027,
      "step": 520
    },
    {
      "epoch": 0.1727541954590326,
      "grad_norm": 0.49181491136550903,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.8526,
      "step": 525
    },
    {
      "epoch": 0.17439947351102336,
      "grad_norm": 0.5000940561294556,
      "learning_rate": 0.00016552406064601188,
      "loss": 1.8588,
      "step": 530
    },
    {
      "epoch": 0.17604475156301416,
      "grad_norm": 0.45289117097854614,
      "learning_rate": 0.00016519446275543837,
      "loss": 2.0358,
      "step": 535
    },
    {
      "epoch": 0.17769002961500494,
      "grad_norm": 0.5227617621421814,
      "learning_rate": 0.00016486486486486486,
      "loss": 1.8512,
      "step": 540
    },
    {
      "epoch": 0.17933530766699574,
      "grad_norm": 0.512492299079895,
      "learning_rate": 0.00016453526697429138,
      "loss": 1.9014,
      "step": 545
    },
    {
      "epoch": 0.1809805857189865,
      "grad_norm": 0.4832890033721924,
      "learning_rate": 0.00016420566908371785,
      "loss": 1.9765,
      "step": 550
    },
    {
      "epoch": 0.18262586377097728,
      "grad_norm": 0.4797350764274597,
      "learning_rate": 0.00016387607119314437,
      "loss": 1.8907,
      "step": 555
    },
    {
      "epoch": 0.18427114182296808,
      "grad_norm": 0.48889973759651184,
      "learning_rate": 0.00016354647330257086,
      "loss": 1.9369,
      "step": 560
    },
    {
      "epoch": 0.18591641987495885,
      "grad_norm": 0.44188860058784485,
      "learning_rate": 0.00016321687541199739,
      "loss": 1.8547,
      "step": 565
    },
    {
      "epoch": 0.18756169792694966,
      "grad_norm": 0.5300605893135071,
      "learning_rate": 0.00016288727752142388,
      "loss": 1.8603,
      "step": 570
    },
    {
      "epoch": 0.18920697597894043,
      "grad_norm": 0.5411728620529175,
      "learning_rate": 0.00016255767963085037,
      "loss": 1.8067,
      "step": 575
    },
    {
      "epoch": 0.19085225403093123,
      "grad_norm": 0.5871673226356506,
      "learning_rate": 0.00016222808174027687,
      "loss": 1.8875,
      "step": 580
    }
  ],
  "logging_steps": 5,
  "max_steps": 3039,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1842159022647296e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}