{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9987492182614135,
  "eval_steps": 500,
  "global_step": 1598,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012507817385866166,
      "grad_norm": 11.196227689671167,
      "learning_rate": 3.125e-06,
      "loss": 2.214,
      "step": 10
    },
    {
      "epoch": 0.025015634771732333,
      "grad_norm": 8.94526469956846,
      "learning_rate": 6.25e-06,
      "loss": 1.9951,
      "step": 20
    },
    {
      "epoch": 0.0375234521575985,
      "grad_norm": 4.435119438184541,
      "learning_rate": 9.375000000000001e-06,
      "loss": 1.7806,
      "step": 30
    },
    {
      "epoch": 0.050031269543464665,
      "grad_norm": 3.5809779955407897,
      "learning_rate": 1.25e-05,
      "loss": 1.6741,
      "step": 40
    },
    {
      "epoch": 0.06253908692933083,
      "grad_norm": 3.166651040106077,
      "learning_rate": 1.5625e-05,
      "loss": 1.6914,
      "step": 50
    },
    {
      "epoch": 0.075046904315197,
      "grad_norm": 3.9053021248979682,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 1.6361,
      "step": 60
    },
    {
      "epoch": 0.08755472170106317,
      "grad_norm": 3.155446891106998,
      "learning_rate": 2.1875e-05,
      "loss": 1.6324,
      "step": 70
    },
    {
      "epoch": 0.10006253908692933,
      "grad_norm": 3.479387369477938,
      "learning_rate": 2.5e-05,
      "loss": 1.691,
      "step": 80
    },
    {
      "epoch": 0.1125703564727955,
      "grad_norm": 3.1552136407516627,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 1.5845,
      "step": 90
    },
    {
      "epoch": 0.12507817385866166,
      "grad_norm": 2.980287991118556,
      "learning_rate": 3.125e-05,
      "loss": 1.6084,
      "step": 100
    },
    {
      "epoch": 0.13758599124452783,
      "grad_norm": 3.2625386096828253,
      "learning_rate": 3.4375e-05,
      "loss": 1.5345,
      "step": 110
    },
    {
      "epoch": 0.150093808630394,
      "grad_norm": 3.220585292919637,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.5981,
      "step": 120
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 3.3487046432982237,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 1.6322,
      "step": 130
    },
    {
      "epoch": 0.17510944340212634,
      "grad_norm": 3.497338581118587,
      "learning_rate": 4.375e-05,
      "loss": 1.5688,
      "step": 140
    },
    {
      "epoch": 0.18761726078799248,
      "grad_norm": 2.7183936172436955,
      "learning_rate": 4.6875e-05,
      "loss": 1.6114,
      "step": 150
    },
    {
      "epoch": 0.20012507817385866,
      "grad_norm": 3.204681866651314,
      "learning_rate": 5e-05,
      "loss": 1.5904,
      "step": 160
    },
    {
      "epoch": 0.21263289555972484,
      "grad_norm": 2.8734026340283725,
      "learning_rate": 4.999403411726636e-05,
      "loss": 1.5623,
      "step": 170
    },
    {
      "epoch": 0.225140712945591,
      "grad_norm": 2.731883784862566,
      "learning_rate": 4.997613931640598e-05,
      "loss": 1.5458,
      "step": 180
    },
    {
      "epoch": 0.23764853033145716,
      "grad_norm": 3.0795590036212364,
      "learning_rate": 4.9946324138081534e-05,
      "loss": 1.5823,
      "step": 190
    },
    {
      "epoch": 0.2501563477173233,
      "grad_norm": 3.105095822757511,
      "learning_rate": 4.990460281220164e-05,
      "loss": 1.6045,
      "step": 200
    },
    {
      "epoch": 0.2626641651031895,
      "grad_norm": 2.667234411289808,
      "learning_rate": 4.98509952511293e-05,
      "loss": 1.5437,
      "step": 210
    },
    {
      "epoch": 0.27517198248905567,
      "grad_norm": 2.8566556940170322,
      "learning_rate": 4.978552704017835e-05,
      "loss": 1.5735,
      "step": 220
    },
    {
      "epoch": 0.2876797998749218,
      "grad_norm": 3.163297164791991,
      "learning_rate": 4.9708229425402354e-05,
      "loss": 1.4995,
      "step": 230
    },
    {
      "epoch": 0.300187617260788,
      "grad_norm": 2.469748730613264,
      "learning_rate": 4.961913929868172e-05,
      "loss": 1.5849,
      "step": 240
    },
    {
      "epoch": 0.31269543464665417,
      "grad_norm": 2.3807543392076562,
      "learning_rate": 4.9518299180116366e-05,
      "loss": 1.542,
      "step": 250
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 2.6158605188730752,
      "learning_rate": 4.940575719773205e-05,
      "loss": 1.5421,
      "step": 260
    },
    {
      "epoch": 0.33771106941838647,
      "grad_norm": 2.418711564788159,
      "learning_rate": 4.928156706451035e-05,
      "loss": 1.519,
      "step": 270
    },
    {
      "epoch": 0.35021888680425267,
      "grad_norm": 2.5688271193206056,
      "learning_rate": 4.9145788052752975e-05,
      "loss": 1.534,
      "step": 280
    },
    {
      "epoch": 0.3627267041901188,
      "grad_norm": 2.749288049559472,
      "learning_rate": 4.899848496579287e-05,
      "loss": 1.5005,
      "step": 290
    },
    {
      "epoch": 0.37523452157598497,
      "grad_norm": 2.535758124519615,
      "learning_rate": 4.883972810706548e-05,
      "loss": 1.4939,
      "step": 300
    },
    {
      "epoch": 0.3877423389618512,
      "grad_norm": 2.7195432729416833,
      "learning_rate": 4.866959324655501e-05,
      "loss": 1.5848,
      "step": 310
    },
    {
      "epoch": 0.4002501563477173,
      "grad_norm": 2.573563516367268,
      "learning_rate": 4.8488161584631574e-05,
      "loss": 1.5405,
      "step": 320
    },
    {
      "epoch": 0.41275797373358347,
      "grad_norm": 2.3636405411668773,
      "learning_rate": 4.829551971329672e-05,
      "loss": 1.4888,
      "step": 330
    },
    {
      "epoch": 0.4252657911194497,
      "grad_norm": 2.662627405108673,
      "learning_rate": 4.809175957485558e-05,
      "loss": 1.5268,
      "step": 340
    },
    {
      "epoch": 0.4377736085053158,
      "grad_norm": 2.9176522067958586,
      "learning_rate": 4.7876978418035455e-05,
      "loss": 1.5558,
      "step": 350
    },
    {
      "epoch": 0.450281425891182,
      "grad_norm": 2.6802852707789944,
      "learning_rate": 4.7651278751571984e-05,
      "loss": 1.4693,
      "step": 360
    },
    {
      "epoch": 0.4627892432770482,
      "grad_norm": 2.3192718381618747,
      "learning_rate": 4.7414768295284594e-05,
      "loss": 1.4593,
      "step": 370
    },
    {
      "epoch": 0.47529706066291433,
      "grad_norm": 1.9806583859678688,
      "learning_rate": 4.716755992866509e-05,
      "loss": 1.4264,
      "step": 380
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 2.3557329695543774,
      "learning_rate": 4.6909771637003556e-05,
      "loss": 1.4341,
      "step": 390
    },
    {
      "epoch": 0.5003126954346466,
      "grad_norm": 2.461600528378801,
      "learning_rate": 4.664152645507744e-05,
      "loss": 1.4021,
      "step": 400
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 2.1270176374651935,
      "learning_rate": 4.636295240843068e-05,
      "loss": 1.3945,
      "step": 410
    },
    {
      "epoch": 0.525328330206379,
      "grad_norm": 2.3665847282413575,
      "learning_rate": 4.607418245227089e-05,
      "loss": 1.4461,
      "step": 420
    },
    {
      "epoch": 0.5378361475922452,
      "grad_norm": 2.4752815650228093,
      "learning_rate": 4.577535440801368e-05,
      "loss": 1.4968,
      "step": 430
    },
    {
      "epoch": 0.5503439649781113,
      "grad_norm": 2.442249949806804,
      "learning_rate": 4.546661089750462e-05,
      "loss": 1.4575,
      "step": 440
    },
    {
      "epoch": 0.5628517823639775,
      "grad_norm": 2.7248721839556795,
      "learning_rate": 4.5148099274950005e-05,
      "loss": 1.4477,
      "step": 450
    },
    {
      "epoch": 0.5753595997498436,
      "grad_norm": 2.318960929300146,
      "learning_rate": 4.481997155658898e-05,
      "loss": 1.5055,
      "step": 460
    },
    {
      "epoch": 0.5878674171357098,
      "grad_norm": 2.388316725594586,
      "learning_rate": 4.4482384348140695e-05,
      "loss": 1.497,
      "step": 470
    },
    {
      "epoch": 0.600375234521576,
      "grad_norm": 2.3580062020206825,
      "learning_rate": 4.413549877006099e-05,
      "loss": 1.4085,
      "step": 480
    },
    {
      "epoch": 0.6128830519074422,
      "grad_norm": 2.30371005036015,
      "learning_rate": 4.3779480380644337e-05,
      "loss": 1.4317,
      "step": 490
    },
    {
      "epoch": 0.6253908692933083,
      "grad_norm": 2.277490335597429,
      "learning_rate": 4.34144990970077e-05,
      "loss": 1.3452,
      "step": 500
    },
    {
      "epoch": 0.6253908692933083,
      "eval_loss": 1.5973767042160034,
      "eval_runtime": 52.0268,
      "eval_samples_per_second": 109.271,
      "eval_steps_per_second": 13.666,
      "step": 500
    },
    {
      "epoch": 0.6378986866791745,
      "grad_norm": 2.3070851884604475,
      "learning_rate": 4.304072911399415e-05,
      "loss": 1.4545,
      "step": 510
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 2.3084992239900246,
      "learning_rate": 4.2658348821034724e-05,
      "loss": 1.4045,
      "step": 520
    },
    {
      "epoch": 0.6629143214509068,
      "grad_norm": 2.4525306744373374,
      "learning_rate": 4.226754071700841e-05,
      "loss": 1.3536,
      "step": 530
    },
    {
      "epoch": 0.6754221388367729,
      "grad_norm": 2.6009908546977956,
      "learning_rate": 4.1868491323140816e-05,
      "loss": 1.3148,
      "step": 540
    },
    {
      "epoch": 0.6879299562226392,
      "grad_norm": 2.021929537122587,
      "learning_rate": 4.146139109398303e-05,
      "loss": 1.3477,
      "step": 550
    },
    {
      "epoch": 0.7004377736085053,
      "grad_norm": 2.5221876399286094,
      "learning_rate": 4.1046434326513305e-05,
      "loss": 1.5216,
      "step": 560
    },
    {
      "epoch": 0.7129455909943715,
      "grad_norm": 2.16247339066387,
      "learning_rate": 4.062381906740477e-05,
      "loss": 1.293,
      "step": 570
    },
    {
      "epoch": 0.7254534083802376,
      "grad_norm": 2.4082164854514474,
      "learning_rate": 4.019374701850362e-05,
      "loss": 1.357,
      "step": 580
    },
    {
      "epoch": 0.7379612257661038,
      "grad_norm": 2.147993492009433,
      "learning_rate": 3.975642344056271e-05,
      "loss": 1.307,
      "step": 590
    },
    {
      "epoch": 0.7504690431519699,
      "grad_norm": 2.327347035494655,
      "learning_rate": 3.931205705527664e-05,
      "loss": 1.3439,
      "step": 600
    },
    {
      "epoch": 0.7629768605378362,
      "grad_norm": 2.3709636186020537,
      "learning_rate": 3.886085994566506e-05,
      "loss": 1.3583,
      "step": 610
    },
    {
      "epoch": 0.7754846779237023,
      "grad_norm": 2.479454672693421,
      "learning_rate": 3.840304745485162e-05,
      "loss": 1.3027,
      "step": 620
    },
    {
      "epoch": 0.7879924953095685,
      "grad_norm": 3.0231086471463398,
      "learning_rate": 3.7938838083287056e-05,
      "loss": 1.2713,
      "step": 630
    },
    {
      "epoch": 0.8005003126954346,
      "grad_norm": 2.4618474144423885,
      "learning_rate": 3.746845338446533e-05,
      "loss": 1.2691,
      "step": 640
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 2.683364877303722,
      "learning_rate": 3.6992117859182674e-05,
      "loss": 1.3601,
      "step": 650
    },
    {
      "epoch": 0.8255159474671669,
      "grad_norm": 2.2275611309820915,
      "learning_rate": 3.651005884838995e-05,
      "loss": 1.3015,
      "step": 660
    },
    {
      "epoch": 0.8380237648530331,
      "grad_norm": 2.103409392935606,
      "learning_rate": 3.6022506424689485e-05,
      "loss": 1.2854,
      "step": 670
    },
    {
      "epoch": 0.8505315822388994,
      "grad_norm": 2.0900193989619416,
      "learning_rate": 3.552969328252817e-05,
      "loss": 1.2873,
      "step": 680
    },
    {
      "epoch": 0.8630393996247655,
      "grad_norm": 2.4106505955260005,
      "learning_rate": 3.5031854627139284e-05,
      "loss": 1.2996,
      "step": 690
    },
    {
      "epoch": 0.8755472170106317,
      "grad_norm": 2.4059236606171717,
      "learning_rate": 3.452922806228587e-05,
      "loss": 1.3185,
      "step": 700
    },
    {
      "epoch": 0.8880550343964978,
      "grad_norm": 2.5241974809557175,
      "learning_rate": 3.402205347685953e-05,
      "loss": 1.2231,
      "step": 710
    },
    {
      "epoch": 0.900562851782364,
      "grad_norm": 2.055185555826128,
      "learning_rate": 3.351057293038841e-05,
      "loss": 1.3374,
      "step": 720
    },
    {
      "epoch": 0.9130706691682301,
      "grad_norm": 2.2760930492977054,
      "learning_rate": 3.2995030537509396e-05,
      "loss": 1.3444,
      "step": 730
    },
    {
      "epoch": 0.9255784865540964,
      "grad_norm": 2.2552997614472914,
      "learning_rate": 3.247567235145929e-05,
      "loss": 1.2456,
      "step": 740
    },
    {
      "epoch": 0.9380863039399625,
      "grad_norm": 2.433944058150599,
      "learning_rate": 3.195274624664086e-05,
      "loss": 1.1923,
      "step": 750
    },
    {
      "epoch": 0.9505941213258287,
      "grad_norm": 2.1846841795842202,
      "learning_rate": 3.14265018003197e-05,
      "loss": 1.2513,
      "step": 760
    },
    {
      "epoch": 0.9631019387116948,
      "grad_norm": 2.4960158537732773,
      "learning_rate": 3.089719017350828e-05,
      "loss": 1.2928,
      "step": 770
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 2.2820418756697665,
      "learning_rate": 3.03650639910942e-05,
      "loss": 1.2285,
      "step": 780
    },
    {
      "epoch": 0.9881175734834271,
      "grad_norm": 2.2304674808935503,
      "learning_rate": 2.983037722126978e-05,
      "loss": 1.2109,
      "step": 790
    },
    {
      "epoch": 1.0006253908692933,
      "grad_norm": 2.4884834373076257,
      "learning_rate": 2.929338505432045e-05,
      "loss": 1.2071,
      "step": 800
    },
    {
      "epoch": 1.0131332082551594,
      "grad_norm": 2.2652235105915866,
      "learning_rate": 2.8754343780829968e-05,
      "loss": 0.9707,
      "step": 810
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 2.7829211847796436,
      "learning_rate": 2.821351066936043e-05,
      "loss": 0.9281,
      "step": 820
    },
    {
      "epoch": 1.038148843026892,
      "grad_norm": 2.3690248065827264,
      "learning_rate": 2.767114384366555e-05,
      "loss": 0.9399,
      "step": 830
    },
    {
      "epoch": 1.050656660412758,
      "grad_norm": 2.5409598116910734,
      "learning_rate": 2.7127502159495782e-05,
      "loss": 0.8951,
      "step": 840
    },
    {
      "epoch": 1.0631644777986242,
      "grad_norm": 2.5575660182733673,
      "learning_rate": 2.6582845081054096e-05,
      "loss": 0.8859,
      "step": 850
    },
    {
      "epoch": 1.0756722951844904,
      "grad_norm": 2.243946653312665,
      "learning_rate": 2.6037432557161285e-05,
      "loss": 0.8429,
      "step": 860
    },
    {
      "epoch": 1.0881801125703565,
      "grad_norm": 2.727808580020501,
      "learning_rate": 2.5491524897190068e-05,
      "loss": 0.8958,
      "step": 870
    },
    {
      "epoch": 1.1006879299562227,
      "grad_norm": 2.6050024232102906,
      "learning_rate": 2.4945382646827058e-05,
      "loss": 0.9412,
      "step": 880
    },
    {
      "epoch": 1.1131957473420888,
      "grad_norm": 2.5841504477219135,
      "learning_rate": 2.4399266463721993e-05,
      "loss": 0.9089,
      "step": 890
    },
    {
      "epoch": 1.125703564727955,
      "grad_norm": 2.5085199599814882,
      "learning_rate": 2.3853436993083453e-05,
      "loss": 0.9373,
      "step": 900
    },
    {
      "epoch": 1.1382113821138211,
      "grad_norm": 3.2343558948374165,
      "learning_rate": 2.3308154743280595e-05,
      "loss": 0.8741,
      "step": 910
    },
    {
      "epoch": 1.1507191994996873,
      "grad_norm": 2.881822507701942,
      "learning_rate": 2.2763679961510137e-05,
      "loss": 0.8959,
      "step": 920
    },
    {
      "epoch": 1.1632270168855534,
      "grad_norm": 2.6590136429428104,
      "learning_rate": 2.222027250958805e-05,
      "loss": 0.8447,
      "step": 930
    },
    {
      "epoch": 1.1757348342714196,
      "grad_norm": 2.330687894654819,
      "learning_rate": 2.1678191739925107e-05,
      "loss": 0.8689,
      "step": 940
    },
    {
      "epoch": 1.1882426516572857,
      "grad_norm": 2.790243974607849,
      "learning_rate": 2.1137696371745608e-05,
      "loss": 0.8875,
      "step": 950
    },
    {
      "epoch": 1.200750469043152,
      "grad_norm": 2.283914922416874,
      "learning_rate": 2.059904436760835e-05,
      "loss": 0.8459,
      "step": 960
    },
    {
      "epoch": 1.2132582864290182,
      "grad_norm": 2.575042681933137,
      "learning_rate": 2.006249281028859e-05,
      "loss": 0.8405,
      "step": 970
    },
    {
      "epoch": 1.2257661038148844,
      "grad_norm": 2.5311184713219,
      "learning_rate": 1.9528297780080067e-05,
      "loss": 0.9238,
      "step": 980
    },
    {
      "epoch": 1.2382739212007505,
      "grad_norm": 2.7281405763745727,
      "learning_rate": 1.899671423257534e-05,
      "loss": 0.906,
      "step": 990
    },
    {
      "epoch": 1.2507817385866167,
      "grad_norm": 2.273017241171145,
      "learning_rate": 1.8467995876983002e-05,
      "loss": 0.8293,
      "step": 1000
    },
    {
      "epoch": 1.2507817385866167,
      "eval_loss": 1.3726614713668823,
      "eval_runtime": 51.9356,
      "eval_samples_per_second": 109.462,
      "eval_steps_per_second": 13.69,
      "step": 1000
    },
    {
      "epoch": 1.2632895559724828,
      "grad_norm": 2.8020838753185022,
      "learning_rate": 1.7942395055039756e-05,
      "loss": 0.818,
      "step": 1010
    },
    {
      "epoch": 1.275797373358349,
      "grad_norm": 2.814873162280655,
      "learning_rate": 1.742016262057507e-05,
      "loss": 0.8782,
      "step": 1020
    },
    {
      "epoch": 1.2883051907442151,
      "grad_norm": 2.5555727855199133,
      "learning_rate": 1.690154781978604e-05,
      "loss": 0.8692,
      "step": 1030
    },
    {
      "epoch": 1.3008130081300813,
      "grad_norm": 2.9198901354453866,
      "learning_rate": 1.638679817227951e-05,
      "loss": 0.885,
      "step": 1040
    },
    {
      "epoch": 1.3133208255159474,
      "grad_norm": 2.326734936151972,
      "learning_rate": 1.5876159352938202e-05,
      "loss": 0.8594,
      "step": 1050
    },
    {
      "epoch": 1.3258286429018136,
      "grad_norm": 2.6527776239267333,
      "learning_rate": 1.5369875074667365e-05,
      "loss": 0.864,
      "step": 1060
    },
    {
      "epoch": 1.3383364602876797,
      "grad_norm": 2.719137361822375,
      "learning_rate": 1.4868186972077708e-05,
      "loss": 0.8384,
      "step": 1070
    },
    {
      "epoch": 1.3508442776735459,
      "grad_norm": 2.23395715978574,
      "learning_rate": 1.4371334486160354e-05,
      "loss": 0.7987,
      "step": 1080
    },
    {
      "epoch": 1.3633520950594122,
      "grad_norm": 2.538354497553029,
      "learning_rate": 1.3879554750008653e-05,
      "loss": 0.8451,
      "step": 1090
    },
    {
      "epoch": 1.3758599124452782,
      "grad_norm": 2.4429406057964735,
      "learning_rate": 1.3393082475641544e-05,
      "loss": 0.836,
      "step": 1100
    },
    {
      "epoch": 1.3883677298311445,
      "grad_norm": 2.1166767893102234,
      "learning_rate": 1.2912149841982388e-05,
      "loss": 0.8215,
      "step": 1110
    },
    {
      "epoch": 1.4008755472170107,
      "grad_norm": 2.2346931729430732,
      "learning_rate": 1.2436986384046786e-05,
      "loss": 0.7785,
      "step": 1120
    },
    {
      "epoch": 1.4133833646028768,
      "grad_norm": 2.494815885218028,
      "learning_rate": 1.1967818883392306e-05,
      "loss": 0.7624,
      "step": 1130
    },
    {
      "epoch": 1.425891181988743,
      "grad_norm": 2.901143519765259,
      "learning_rate": 1.150487125988224e-05,
      "loss": 0.82,
      "step": 1140
    },
    {
      "epoch": 1.4383989993746091,
      "grad_norm": 2.7828290624179957,
      "learning_rate": 1.1048364464815297e-05,
      "loss": 0.8018,
      "step": 1150
    },
    {
      "epoch": 1.4509068167604753,
      "grad_norm": 2.4761447552027196,
      "learning_rate": 1.0598516375471978e-05,
      "loss": 0.8224,
      "step": 1160
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 2.7960949007283014,
      "learning_rate": 1.0155541691128212e-05,
      "loss": 0.8362,
      "step": 1170
    },
    {
      "epoch": 1.4759224515322076,
      "grad_norm": 2.8586426222751355,
      "learning_rate": 9.719651830585668e-06,
      "loss": 0.814,
      "step": 1180
    },
    {
      "epoch": 1.4884302689180737,
      "grad_norm": 2.444704855440996,
      "learning_rate": 9.291054831267749e-06,
      "loss": 0.812,
      "step": 1190
    },
    {
      "epoch": 1.50093808630394,
      "grad_norm": 2.203245268486062,
      "learning_rate": 8.869955249929509e-06,
      "loss": 0.756,
      "step": 1200
    },
    {
      "epoch": 1.513445903689806,
      "grad_norm": 2.1667676187504643,
      "learning_rate": 8.456554065028651e-06,
      "loss": 0.7866,
      "step": 1210
    },
    {
      "epoch": 1.5259537210756724,
      "grad_norm": 3.1729468036439368,
      "learning_rate": 8.051048580804457e-06,
      "loss": 0.7789,
      "step": 1220
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 2.745706957042119,
      "learning_rate": 7.65363233311028e-06,
      "loss": 0.7651,
      "step": 1230
    },
    {
      "epoch": 1.5509693558474047,
      "grad_norm": 2.3285021876802614,
      "learning_rate": 7.264494997044522e-06,
      "loss": 0.7461,
      "step": 1240
    },
    {
      "epoch": 1.5634771732332708,
      "grad_norm": 2.703446713628546,
      "learning_rate": 6.88382229642433e-06,
      "loss": 0.7933,
      "step": 1250
    },
    {
      "epoch": 1.575984990619137,
      "grad_norm": 2.4555911035434517,
      "learning_rate": 6.51179591514505e-06,
      "loss": 0.7563,
      "step": 1260
    },
    {
      "epoch": 1.5884928080050031,
      "grad_norm": 2.0388567105663604,
      "learning_rate": 6.1485934104678285e-06,
      "loss": 0.6997,
      "step": 1270
    },
    {
      "epoch": 1.6010006253908693,
      "grad_norm": 2.998906503082893,
      "learning_rate": 5.794388128276798e-06,
      "loss": 0.7702,
      "step": 1280
    },
    {
      "epoch": 1.6135084427767354,
      "grad_norm": 2.295408095489897,
      "learning_rate": 5.449349120346137e-06,
      "loss": 0.7681,
      "step": 1290
    },
    {
      "epoch": 1.6260162601626016,
      "grad_norm": 2.3383927307138155,
      "learning_rate": 5.113641063656618e-06,
      "loss": 0.7848,
      "step": 1300
    },
    {
      "epoch": 1.6385240775484677,
      "grad_norm": 2.535009363777371,
      "learning_rate": 4.787424181800174e-06,
      "loss": 0.7713,
      "step": 1310
    },
    {
      "epoch": 1.6510318949343339,
      "grad_norm": 2.443338473601547,
      "learning_rate": 4.470854168509819e-06,
      "loss": 0.7888,
      "step": 1320
    },
    {
      "epoch": 1.6635397123202003,
      "grad_norm": 2.686883685963269,
      "learning_rate": 4.164082113351672e-06,
      "loss": 0.7497,
      "step": 1330
    },
    {
      "epoch": 1.6760475297060662,
      "grad_norm": 2.8068580095390674,
      "learning_rate": 3.867254429614281e-06,
      "loss": 0.7899,
      "step": 1340
    },
    {
      "epoch": 1.6885553470919326,
      "grad_norm": 2.3048887226109063,
      "learning_rate": 3.580512784429921e-06,
      "loss": 0.7631,
      "step": 1350
    },
    {
      "epoch": 1.7010631644777985,
      "grad_norm": 2.3839076230191307,
      "learning_rate": 3.3039940311609868e-06,
      "loss": 0.7005,
      "step": 1360
    },
    {
      "epoch": 1.7135709818636649,
      "grad_norm": 2.750016598535585,
      "learning_rate": 3.0378301440839253e-06,
      "loss": 0.7584,
      "step": 1370
    },
    {
      "epoch": 1.726078799249531,
      "grad_norm": 2.445902129036907,
      "learning_rate": 2.7821481554018065e-06,
      "loss": 0.7177,
      "step": 1380
    },
    {
      "epoch": 1.7385866166353972,
      "grad_norm": 2.459439087514897,
      "learning_rate": 2.5370700946155456e-06,
      "loss": 0.7107,
      "step": 1390
    },
    {
      "epoch": 1.7510944340212633,
      "grad_norm": 2.3917637382771217,
      "learning_rate": 2.3027129302828494e-06,
      "loss": 0.7252,
      "step": 1400
    },
    {
      "epoch": 1.7636022514071295,
      "grad_norm": 2.5825813580196977,
      "learning_rate": 2.0791885141925344e-06,
      "loss": 0.7265,
      "step": 1410
    },
    {
      "epoch": 1.7761100687929956,
      "grad_norm": 2.7444524417938907,
      "learning_rate": 1.8666035279809535e-06,
      "loss": 0.7868,
      "step": 1420
    },
    {
      "epoch": 1.7886178861788617,
      "grad_norm": 2.5747339796466777,
      "learning_rate": 1.6650594322160097e-06,
      "loss": 0.7461,
      "step": 1430
    },
    {
      "epoch": 1.8011257035647281,
      "grad_norm": 2.814780313810251,
      "learning_rate": 1.4746524179729742e-06,
      "loss": 0.751,
      "step": 1440
    },
    {
      "epoch": 1.813633520950594,
      "grad_norm": 2.491280187376505,
      "learning_rate": 1.295473360925345e-06,
      "loss": 0.7407,
      "step": 1450
    },
    {
      "epoch": 1.8261413383364604,
      "grad_norm": 2.6865531055864786,
      "learning_rate": 1.1276077779725335e-06,
      "loss": 0.7467,
      "step": 1460
    },
    {
      "epoch": 1.8386491557223263,
      "grad_norm": 2.693944976015148,
      "learning_rate": 9.711357864251647e-07,
      "loss": 0.7721,
      "step": 1470
    },
    {
      "epoch": 1.8511569731081927,
      "grad_norm": 3.1854255386603527,
      "learning_rate": 8.261320657674626e-07,
      "loss": 0.7555,
      "step": 1480
    },
    {
      "epoch": 1.8636647904940586,
      "grad_norm": 2.3969657119662906,
      "learning_rate": 6.926658220148929e-07,
      "loss": 0.7728,
      "step": 1490
    },
    {
      "epoch": 1.876172607879925,
      "grad_norm": 2.4361472021651105,
      "learning_rate": 5.708007546841893e-07,
      "loss": 0.7086,
      "step": 1500
    },
    {
      "epoch": 1.876172607879925,
      "eval_loss": 1.2464503049850464,
      "eval_runtime": 51.9233,
      "eval_samples_per_second": 109.489,
      "eval_steps_per_second": 13.693,
      "step": 1500
    },
    {
      "epoch": 1.8886804252657912,
      "grad_norm": 2.5813463203755656,
      "learning_rate": 4.6059502639142773e-07,
      "loss": 0.6916,
      "step": 1510
    },
    {
      "epoch": 1.9011882426516573,
      "grad_norm": 2.8984929947738176,
      "learning_rate": 3.6210123509273775e-07,
      "loss": 0.7647,
      "step": 1520
    },
    {
      "epoch": 1.9136960600375235,
      "grad_norm": 2.4332442721477934,
      "learning_rate": 2.753663889808328e-07,
      "loss": 0.7037,
      "step": 1530
    },
    {
      "epoch": 1.9262038774233896,
      "grad_norm": 2.7482039407993035,
      "learning_rate": 2.0043188404937075e-07,
      "loss": 0.7467,
      "step": 1540
    },
    {
      "epoch": 1.9387116948092558,
      "grad_norm": 2.6495770008884647,
      "learning_rate": 1.3733348433589143e-07,
      "loss": 0.7894,
      "step": 1550
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 2.6742202900643752,
      "learning_rate": 8.610130485265655e-08,
      "loss": 0.805,
      "step": 1560
    },
    {
      "epoch": 1.9637273295809883,
      "grad_norm": 2.445319151525402,
      "learning_rate": 4.67597972136663e-08,
      "loss": 0.7277,
      "step": 1570
    },
    {
      "epoch": 1.9762351469668542,
      "grad_norm": 2.5097808639896324,
      "learning_rate": 1.9327737964616733e-08,
      "loss": 0.7574,
      "step": 1580
    },
    {
      "epoch": 1.9887429643527206,
      "grad_norm": 2.5217973584786435,
      "learning_rate": 3.8182196213903955e-09,
      "loss": 0.7318,
      "step": 1590
    },
    {
      "epoch": 1.9987492182614135,
      "step": 1598,
      "total_flos": 18204158066688.0,
      "train_loss": 1.1366474037623973,
      "train_runtime": 1015.6993,
      "train_samples_per_second": 100.746,
      "train_steps_per_second": 1.573
    }
  ],
  "logging_steps": 10,
  "max_steps": 1598,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 18204158066688.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}