{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 547,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009140767824497258,
      "grad_norm": 72.8250732421875,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 3.402,
      "step": 5
    },
    {
      "epoch": 0.018281535648994516,
      "grad_norm": 28.21662139892578,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 2.6895,
      "step": 10
    },
    {
      "epoch": 0.027422303473491772,
      "grad_norm": 12.129012107849121,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.2964,
      "step": 15
    },
    {
      "epoch": 0.03656307129798903,
      "grad_norm": 4.143538475036621,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.386,
      "step": 20
    },
    {
      "epoch": 0.04570383912248629,
      "grad_norm": 9.900189399719238,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.2348,
      "step": 25
    },
    {
      "epoch": 0.054844606946983544,
      "grad_norm": 2.2335424423217773,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.1444,
      "step": 30
    },
    {
      "epoch": 0.06398537477148081,
      "grad_norm": 2.3110196590423584,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 0.1224,
      "step": 35
    },
    {
      "epoch": 0.07312614259597806,
      "grad_norm": 2.3454320430755615,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 0.1052,
      "step": 40
    },
    {
      "epoch": 0.08226691042047532,
      "grad_norm": 2.230443239212036,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.0856,
      "step": 45
    },
    {
      "epoch": 0.09140767824497258,
      "grad_norm": 2.1253552436828613,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.0625,
      "step": 50
    },
    {
      "epoch": 0.10054844606946983,
      "grad_norm": 1.7156140804290771,
      "learning_rate": 2e-05,
      "loss": 0.0384,
      "step": 55
    },
    {
      "epoch": 0.10968921389396709,
      "grad_norm": 1.71486234664917,
      "learning_rate": 1.9994903844605973e-05,
      "loss": 0.0293,
      "step": 60
    },
    {
      "epoch": 0.11882998171846434,
      "grad_norm": 0.5556156039237976,
      "learning_rate": 1.9979620572583846e-05,
      "loss": 0.0122,
      "step": 65
    },
    {
      "epoch": 0.12797074954296161,
      "grad_norm": 0.2656179368495941,
      "learning_rate": 1.995416576111945e-05,
      "loss": 0.0073,
      "step": 70
    },
    {
      "epoch": 0.13711151736745886,
      "grad_norm": 0.21650183200836182,
      "learning_rate": 1.9918565354547738e-05,
      "loss": 0.0045,
      "step": 75
    },
    {
      "epoch": 0.14625228519195613,
      "grad_norm": 0.6048226952552795,
      "learning_rate": 1.9872855637909506e-05,
      "loss": 0.0042,
      "step": 80
    },
    {
      "epoch": 0.15539305301645337,
      "grad_norm": 0.16227181255817413,
      "learning_rate": 1.9817083199968552e-05,
      "loss": 0.0043,
      "step": 85
    },
    {
      "epoch": 0.16453382084095064,
      "grad_norm": 0.6625558137893677,
      "learning_rate": 1.9751304885726967e-05,
      "loss": 0.0047,
      "step": 90
    },
    {
      "epoch": 0.1736745886654479,
      "grad_norm": 0.31208521127700806,
      "learning_rate": 1.9675587738486935e-05,
      "loss": 0.003,
      "step": 95
    },
    {
      "epoch": 0.18281535648994515,
      "grad_norm": 0.21230654418468475,
      "learning_rate": 1.9590008931518133e-05,
      "loss": 0.0023,
      "step": 100
    },
    {
      "epoch": 0.19195612431444242,
      "grad_norm": 0.2529038190841675,
      "learning_rate": 1.9494655689400294e-05,
      "loss": 0.0017,
      "step": 105
    },
    {
      "epoch": 0.20109689213893966,
      "grad_norm": 0.07652478665113449,
      "learning_rate": 1.9389625199121264e-05,
      "loss": 0.0013,
      "step": 110
    },
    {
      "epoch": 0.21023765996343693,
      "grad_norm": 0.07473216205835342,
      "learning_rate": 1.927502451102095e-05,
      "loss": 0.0008,
      "step": 115
    },
    {
      "epoch": 0.21937842778793418,
      "grad_norm": 0.10759185999631882,
      "learning_rate": 1.9150970429682316e-05,
      "loss": 0.0009,
      "step": 120
    },
    {
      "epoch": 0.22851919561243145,
      "grad_norm": 0.2672303020954132,
      "learning_rate": 1.9017589394880515e-05,
      "loss": 0.0005,
      "step": 125
    },
    {
      "epoch": 0.2376599634369287,
      "grad_norm": 1.33341383934021,
      "learning_rate": 1.8875017352711547e-05,
      "loss": 0.0019,
      "step": 130
    },
    {
      "epoch": 0.24680073126142596,
      "grad_norm": 0.5362780690193176,
      "learning_rate": 1.8723399617031754e-05,
      "loss": 0.0017,
      "step": 135
    },
    {
      "epoch": 0.25594149908592323,
      "grad_norm": 0.3548431694507599,
      "learning_rate": 1.8562890721349434e-05,
      "loss": 0.0015,
      "step": 140
    },
    {
      "epoch": 0.26508226691042047,
      "grad_norm": 0.18760216236114502,
      "learning_rate": 1.8393654261319504e-05,
      "loss": 0.0009,
      "step": 145
    },
    {
      "epoch": 0.2742230347349177,
      "grad_norm": 0.2579905688762665,
      "learning_rate": 1.821586272800168e-05,
      "loss": 0.0007,
      "step": 150
    },
    {
      "epoch": 0.283363802559415,
      "grad_norm": 0.2245369404554367,
      "learning_rate": 1.8029697332052277e-05,
      "loss": 0.0009,
      "step": 155
    },
    {
      "epoch": 0.29250457038391225,
      "grad_norm": 0.8462201952934265,
      "learning_rate": 1.7835347819028642e-05,
      "loss": 0.0026,
      "step": 160
    },
    {
      "epoch": 0.3016453382084095,
      "grad_norm": 0.37047141790390015,
      "learning_rate": 1.76330122759946e-05,
      "loss": 0.0011,
      "step": 165
    },
    {
      "epoch": 0.31078610603290674,
      "grad_norm": 0.6407871246337891,
      "learning_rate": 1.7422896929623957e-05,
      "loss": 0.0011,
      "step": 170
    },
    {
      "epoch": 0.31992687385740404,
      "grad_norm": 0.4370276927947998,
      "learning_rate": 1.720521593600787e-05,
      "loss": 0.0032,
      "step": 175
    },
    {
      "epoch": 0.3290676416819013,
      "grad_norm": 0.35974910855293274,
      "learning_rate": 1.6980191162380298e-05,
      "loss": 0.0039,
      "step": 180
    },
    {
      "epoch": 0.3382084095063985,
      "grad_norm": 0.1552378237247467,
      "learning_rate": 1.674805196098402e-05,
      "loss": 0.002,
      "step": 185
    },
    {
      "epoch": 0.3473491773308958,
      "grad_norm": 0.3591105341911316,
      "learning_rate": 1.6509034935307716e-05,
      "loss": 0.0019,
      "step": 190
    },
    {
      "epoch": 0.35648994515539306,
      "grad_norm": 0.04844851791858673,
      "learning_rate": 1.6263383698932307e-05,
      "loss": 0.0011,
      "step": 195
    },
    {
      "epoch": 0.3656307129798903,
      "grad_norm": 0.1252487599849701,
      "learning_rate": 1.6011348627232463e-05,
      "loss": 0.0014,
      "step": 200
    },
    {
      "epoch": 0.37477148080438755,
      "grad_norm": 0.11114215105772018,
      "learning_rate": 1.5753186602186207e-05,
      "loss": 0.0008,
      "step": 205
    },
    {
      "epoch": 0.38391224862888484,
      "grad_norm": 0.023969072848558426,
      "learning_rate": 1.5489160750552833e-05,
      "loss": 0.0004,
      "step": 210
    },
    {
      "epoch": 0.3930530164533821,
      "grad_norm": 0.061600591987371445,
      "learning_rate": 1.5219540175685938e-05,
      "loss": 0.0003,
      "step": 215
    },
    {
      "epoch": 0.40219378427787933,
      "grad_norm": 0.0951351672410965,
      "learning_rate": 1.4944599683254903e-05,
      "loss": 0.0002,
      "step": 220
    },
    {
      "epoch": 0.4113345521023766,
      "grad_norm": 0.08145473152399063,
      "learning_rate": 1.4664619501154445e-05,
      "loss": 0.0002,
      "step": 225
    },
    {
      "epoch": 0.42047531992687387,
      "grad_norm": 0.01746625453233719,
      "learning_rate": 1.4379884993887605e-05,
      "loss": 0.0002,
      "step": 230
    },
    {
      "epoch": 0.4296160877513711,
      "grad_norm": 0.02120082452893257,
      "learning_rate": 1.4090686371713403e-05,
      "loss": 0.0004,
      "step": 235
    },
    {
      "epoch": 0.43875685557586835,
      "grad_norm": 0.019948139786720276,
      "learning_rate": 1.3797318394855496e-05,
      "loss": 0.0002,
      "step": 240
    },
    {
      "epoch": 0.44789762340036565,
      "grad_norm": 0.305644690990448,
      "learning_rate": 1.3500080073073436e-05,
      "loss": 0.0006,
      "step": 245
    },
    {
      "epoch": 0.4570383912248629,
      "grad_norm": 0.5187322497367859,
      "learning_rate": 1.319927436090259e-05,
      "loss": 0.0006,
      "step": 250
    },
    {
      "epoch": 0.46617915904936014,
      "grad_norm": 0.30897632241249084,
      "learning_rate": 1.2895207848873488e-05,
      "loss": 0.0007,
      "step": 255
    },
    {
      "epoch": 0.4753199268738574,
      "grad_norm": 0.07400551438331604,
      "learning_rate": 1.2588190451025209e-05,
      "loss": 0.0005,
      "step": 260
    },
    {
      "epoch": 0.4844606946983547,
      "grad_norm": 0.08495013415813446,
      "learning_rate": 1.2278535089031377e-05,
      "loss": 0.0005,
      "step": 265
    },
    {
      "epoch": 0.4936014625228519,
      "grad_norm": 0.18518061935901642,
      "learning_rate": 1.1966557373260654e-05,
      "loss": 0.0004,
      "step": 270
    },
    {
      "epoch": 0.5027422303473492,
      "grad_norm": 0.16111266613006592,
      "learning_rate": 1.165257528109685e-05,
      "loss": 0.0003,
      "step": 275
    },
    {
      "epoch": 0.5118829981718465,
      "grad_norm": 0.07125530391931534,
      "learning_rate": 1.1336908832846485e-05,
      "loss": 0.0002,
      "step": 280
    },
    {
      "epoch": 0.5210237659963437,
      "grad_norm": 0.027559850364923477,
      "learning_rate": 1.1019879765564155e-05,
      "loss": 0.0002,
      "step": 285
    },
    {
      "epoch": 0.5301645338208409,
      "grad_norm": 0.03874915465712547,
      "learning_rate": 1.0701811205128115e-05,
      "loss": 0.0004,
      "step": 290
    },
    {
      "epoch": 0.5393053016453382,
      "grad_norm": 0.07408824563026428,
      "learning_rate": 1.0383027336900356e-05,
      "loss": 0.0005,
      "step": 295
    },
    {
      "epoch": 0.5484460694698354,
      "grad_norm": 0.19742679595947266,
      "learning_rate": 1.0063853075306792e-05,
      "loss": 0.0004,
      "step": 300
    },
    {
      "epoch": 0.5575868372943327,
      "grad_norm": 0.030554568395018578,
      "learning_rate": 9.744613732674401e-06,
      "loss": 0.0002,
      "step": 305
    },
    {
      "epoch": 0.56672760511883,
      "grad_norm": 0.1797352284193039,
      "learning_rate": 9.425634687662768e-06,
      "loss": 0.0003,
      "step": 310
    },
    {
      "epoch": 0.5758683729433273,
      "grad_norm": 0.08481526374816895,
      "learning_rate": 9.107241053628058e-06,
      "loss": 0.0001,
      "step": 315
    },
    {
      "epoch": 0.5850091407678245,
      "grad_norm": 0.08169592916965485,
      "learning_rate": 8.789757347257373e-06,
      "loss": 0.0002,
      "step": 320
    },
    {
      "epoch": 0.5941499085923218,
      "grad_norm": 0.073927141726017,
      "learning_rate": 8.473507157811254e-06,
      "loss": 0.0003,
      "step": 325
    },
    {
      "epoch": 0.603290676416819,
      "grad_norm": 0.00965256430208683,
      "learning_rate": 8.158812817311474e-06,
      "loss": 0.0002,
      "step": 330
    },
    {
      "epoch": 0.6124314442413162,
      "grad_norm": 0.022856874391436577,
      "learning_rate": 7.845995072010188e-06,
      "loss": 0.0002,
      "step": 335
    },
    {
      "epoch": 0.6215722120658135,
      "grad_norm": 0.06963472068309784,
      "learning_rate": 7.535372755475411e-06,
      "loss": 0.0002,
      "step": 340
    },
    {
      "epoch": 0.6307129798903108,
      "grad_norm": 0.024691695347428322,
      "learning_rate": 7.22726246362592e-06,
      "loss": 0.0002,
      "step": 345
    },
    {
      "epoch": 0.6398537477148081,
      "grad_norm": 0.012590546160936356,
      "learning_rate": 6.921978232046878e-06,
      "loss": 0.0002,
      "step": 350
    },
    {
      "epoch": 0.6489945155393053,
      "grad_norm": 0.05468595027923584,
      "learning_rate": 6.619831215914974e-06,
      "loss": 0.0002,
      "step": 355
    },
    {
      "epoch": 0.6581352833638026,
      "grad_norm": 0.07750693708658218,
      "learning_rate": 6.321129372859418e-06,
      "loss": 0.0002,
      "step": 360
    },
    {
      "epoch": 0.6672760511882998,
      "grad_norm": 0.027170751243829727,
      "learning_rate": 6.026177149081949e-06,
      "loss": 0.0002,
      "step": 365
    },
    {
      "epoch": 0.676416819012797,
      "grad_norm": 0.013442575931549072,
      "learning_rate": 5.7352751690558025e-06,
      "loss": 0.0002,
      "step": 370
    },
    {
      "epoch": 0.6855575868372943,
      "grad_norm": 0.06503641605377197,
      "learning_rate": 5.448719929119916e-06,
      "loss": 0.0002,
      "step": 375
    },
    {
      "epoch": 0.6946983546617916,
      "grad_norm": 0.1688007265329361,
      "learning_rate": 5.166803495280614e-06,
      "loss": 0.0002,
      "step": 380
    },
    {
      "epoch": 0.7038391224862889,
      "grad_norm": 0.16672426462173462,
      "learning_rate": 4.889813205528895e-06,
      "loss": 0.0002,
      "step": 385
    },
    {
      "epoch": 0.7129798903107861,
      "grad_norm": 0.0711933895945549,
      "learning_rate": 4.61803137697661e-06,
      "loss": 0.0002,
      "step": 390
    },
    {
      "epoch": 0.7221206581352834,
      "grad_norm": 0.017142411321401596,
      "learning_rate": 4.351735018110066e-06,
      "loss": 0.0001,
      "step": 395
    },
    {
      "epoch": 0.7312614259597806,
      "grad_norm": 0.06323219835758209,
      "learning_rate": 4.091195546454398e-06,
      "loss": 0.0002,
      "step": 400
    },
    {
      "epoch": 0.7404021937842779,
      "grad_norm": 0.15650759637355804,
      "learning_rate": 3.8366785119363624e-06,
      "loss": 0.0002,
      "step": 405
    },
    {
      "epoch": 0.7495429616087751,
      "grad_norm": 0.10531863570213318,
      "learning_rate": 3.5884433262276376e-06,
      "loss": 0.0001,
      "step": 410
    },
    {
      "epoch": 0.7586837294332724,
      "grad_norm": 0.009012032300233841,
      "learning_rate": 3.3467429983443477e-06,
      "loss": 0.0003,
      "step": 415
    },
    {
      "epoch": 0.7678244972577697,
      "grad_norm": 0.021396493539214134,
      "learning_rate": 3.111823876772426e-06,
      "loss": 0.0001,
      "step": 420
    },
    {
      "epoch": 0.7769652650822669,
      "grad_norm": 0.03978023678064346,
      "learning_rate": 2.883925398381585e-06,
      "loss": 0.0001,
      "step": 425
    },
    {
      "epoch": 0.7861060329067642,
      "grad_norm": 0.02052459307014942,
      "learning_rate": 2.663279844383815e-06,
      "loss": 0.0001,
      "step": 430
    },
    {
      "epoch": 0.7952468007312614,
      "grad_norm": 0.009402839466929436,
      "learning_rate": 2.4501121035851494e-06,
      "loss": 0.0001,
      "step": 435
    },
    {
      "epoch": 0.8043875685557587,
      "grad_norm": 0.02130948193371296,
      "learning_rate": 2.244639443172013e-06,
      "loss": 0.0001,
      "step": 440
    },
    {
      "epoch": 0.8135283363802559,
      "grad_norm": 0.056616611778736115,
      "learning_rate": 2.047071287265735e-06,
      "loss": 0.0001,
      "step": 445
    },
    {
      "epoch": 0.8226691042047533,
      "grad_norm": 0.05803929269313812,
      "learning_rate": 1.857609003471007e-06,
      "loss": 0.0002,
      "step": 450
    },
    {
      "epoch": 0.8318098720292505,
      "grad_norm": 0.005538036115467548,
      "learning_rate": 1.6764456976357279e-06,
      "loss": 0.0001,
      "step": 455
    },
    {
      "epoch": 0.8409506398537477,
      "grad_norm": 0.0059971073642373085,
      "learning_rate": 1.503766017031547e-06,
      "loss": 0.0001,
      "step": 460
    },
    {
      "epoch": 0.850091407678245,
      "grad_norm": 0.0059807188808918,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.0001,
      "step": 465
    },
    {
      "epoch": 0.8592321755027422,
      "grad_norm": 0.005512280389666557,
      "learning_rate": 1.1845527073454045e-06,
      "loss": 0.0001,
      "step": 470
    },
    {
      "epoch": 0.8683729433272395,
      "grad_norm": 0.021586749702692032,
      "learning_rate": 1.0383444303894453e-06,
      "loss": 0.0001,
      "step": 475
    },
    {
      "epoch": 0.8775137111517367,
      "grad_norm": 0.01218556147068739,
      "learning_rate": 9.012701513075839e-07,
      "loss": 0.0001,
      "step": 480
    },
    {
      "epoch": 0.886654478976234,
      "grad_norm": 0.005609170068055391,
      "learning_rate": 7.734695804651693e-07,
      "loss": 0.0001,
      "step": 485
    },
    {
      "epoch": 0.8957952468007313,
      "grad_norm": 0.02664189226925373,
      "learning_rate": 6.550729761758901e-07,
      "loss": 0.0001,
      "step": 490
    },
    {
      "epoch": 0.9049360146252285,
      "grad_norm": 0.016554079949855804,
      "learning_rate": 5.462010119384665e-07,
      "loss": 0.0001,
      "step": 495
    },
    {
      "epoch": 0.9140767824497258,
      "grad_norm": 0.005938609596341848,
      "learning_rate": 4.4696465344245874e-07,
      "loss": 0.0001,
      "step": 500
    },
    {
      "epoch": 0.923217550274223,
      "grad_norm": 0.01982252486050129,
      "learning_rate": 3.574650454685902e-07,
      "loss": 0.0001,
      "step": 505
    },
    {
      "epoch": 0.9323583180987203,
      "grad_norm": 0.02185707353055477,
      "learning_rate": 2.777934087988532e-07,
      "loss": 0.0001,
      "step": 510
    },
    {
      "epoch": 0.9414990859232175,
      "grad_norm": 0.007851045578718185,
      "learning_rate": 2.0803094724143879e-07,
      "loss": 0.0001,
      "step": 515
    },
    {
      "epoch": 0.9506398537477148,
      "grad_norm": 0.018694985657930374,
      "learning_rate": 1.482487648653008e-07,
      "loss": 0.0001,
      "step": 520
    },
    {
      "epoch": 0.9597806215722121,
      "grad_norm": 0.02687523327767849,
      "learning_rate": 9.85077935286749e-08,
      "loss": 0.0002,
      "step": 525
    },
    {
      "epoch": 0.9689213893967094,
      "grad_norm": 0.007271461188793182,
      "learning_rate": 5.8858730775438465e-08,
      "loss": 0.0001,
      "step": 530
    },
    {
      "epoch": 0.9780621572212066,
      "grad_norm": 0.022476373240351677,
      "learning_rate": 2.9341988162595593e-08,
      "loss": 0.0004,
      "step": 535
    },
    {
      "epoch": 0.9872029250457038,
      "grad_norm": 0.009166369214653969,
      "learning_rate": 9.987650071561217e-09,
      "loss": 0.0001,
      "step": 540
    },
    {
      "epoch": 0.9963436928702011,
      "grad_norm": 0.00787508673965931,
      "learning_rate": 8.154430452267381e-10,
      "loss": 0.0001,
      "step": 545
    },
    {
      "epoch": 1.0,
      "step": 547,
      "total_flos": 2.567967004866642e+17,
      "train_loss": 0.07939198961997766,
      "train_runtime": 7762.1038,
      "train_samples_per_second": 9.018,
      "train_steps_per_second": 0.07
    }
  ],
  "logging_steps": 5,
  "max_steps": 547,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.567967004866642e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}