{
  "best_metric": 7.248484134674072,
  "best_model_checkpoint": "bert_base_lda_5_v1/checkpoint-50000",
  "epoch": 25.0,
  "eval_steps": 10000,
  "global_step": 59550,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.20990764063811923,
      "grad_norm": 2.1255838871002197,
      "learning_rate": 5e-06,
      "loss": 10.7417,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 1.4488760232925415,
      "learning_rate": 1e-05,
      "loss": 9.0086,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 0.9646936655044556,
      "learning_rate": 1.5e-05,
      "loss": 8.498,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 1.0156469345092773,
      "learning_rate": 2e-05,
      "loss": 8.3577,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 1.371415615081787,
      "learning_rate": 2.5e-05,
      "loss": 8.2488,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 0.9908320903778076,
      "learning_rate": 3e-05,
      "loss": 8.1487,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 1.1176950931549072,
      "learning_rate": 3.5e-05,
      "loss": 8.0726,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 0.8763735294342041,
      "learning_rate": 4e-05,
      "loss": 8.0113,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 1.3254985809326172,
      "learning_rate": 4.5e-05,
      "loss": 7.9577,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 1.0770165920257568,
      "learning_rate": 5e-05,
      "loss": 7.9093,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 1.4271862506866455,
      "learning_rate": 5.500000000000001e-05,
      "loss": 7.8686,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 1.2136560678482056,
      "learning_rate": 6e-05,
      "loss": 7.8339,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 0.9802820682525635,
      "learning_rate": 6.500000000000001e-05,
      "loss": 7.8035,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 1.314109444618225,
      "learning_rate": 7e-05,
      "loss": 7.7753,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 0.853410542011261,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.749,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 1.1303246021270752,
      "learning_rate": 8e-05,
      "loss": 7.727,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 1.5063821077346802,
      "learning_rate": 8.5e-05,
      "loss": 7.7015,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 1.3487807512283325,
      "learning_rate": 9e-05,
      "loss": 7.622,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 0.983832061290741,
      "learning_rate": 9.5e-05,
      "loss": 7.5675,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 1.388443112373352,
      "learning_rate": 0.0001,
      "loss": 7.5336,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.15086674643145329,
      "eval_loss": 7.482370853424072,
      "eval_runtime": 0.734,
      "eval_samples_per_second": 652.615,
      "eval_steps_per_second": 6.812,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 1.7055187225341797,
      "learning_rate": 9.899091826437942e-05,
      "loss": 7.5161,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 1.2820823192596436,
      "learning_rate": 9.798183652875883e-05,
      "loss": 7.4951,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 1.5211608409881592,
      "learning_rate": 9.697275479313825e-05,
      "loss": 7.4839,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 1.1569567918777466,
      "learning_rate": 9.596367305751767e-05,
      "loss": 7.4667,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 1.1066005229949951,
      "learning_rate": 9.495459132189707e-05,
      "loss": 7.4445,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 1.0754830837249756,
      "learning_rate": 9.394550958627649e-05,
      "loss": 7.4334,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 1.057267665863037,
      "learning_rate": 9.293642785065591e-05,
      "loss": 7.4284,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 0.9008902311325073,
      "learning_rate": 9.192734611503532e-05,
      "loss": 7.4144,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 1.082311987876892,
      "learning_rate": 9.091826437941474e-05,
      "loss": 7.4024,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 0.9966408014297485,
      "learning_rate": 8.990918264379415e-05,
      "loss": 7.3924,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 1.070543885231018,
      "learning_rate": 8.890010090817356e-05,
      "loss": 7.3824,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 1.0677157640457153,
      "learning_rate": 8.789101917255298e-05,
      "loss": 7.3756,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 0.7595410943031311,
      "learning_rate": 8.68819374369324e-05,
      "loss": 7.3676,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 0.7410305738449097,
      "learning_rate": 8.58728557013118e-05,
      "loss": 7.353,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 1.0340527296066284,
      "learning_rate": 8.486377396569122e-05,
      "loss": 7.3437,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 0.8954520225524902,
      "learning_rate": 8.385469223007064e-05,
      "loss": 7.3442,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 0.9272580742835999,
      "learning_rate": 8.284561049445006e-05,
      "loss": 7.3372,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 1.0480597019195557,
      "learning_rate": 8.183652875882947e-05,
      "loss": 7.3358,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 0.7353398203849792,
      "learning_rate": 8.082744702320889e-05,
      "loss": 7.3192,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 1.092934012413025,
      "learning_rate": 7.98183652875883e-05,
      "loss": 7.3176,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15244535480793514,
      "eval_loss": 7.3286027908325195,
      "eval_runtime": 0.7088,
      "eval_samples_per_second": 675.754,
      "eval_steps_per_second": 7.054,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 0.8529198169708252,
      "learning_rate": 7.880928355196771e-05,
      "loss": 7.3111,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 0.8961474299430847,
      "learning_rate": 7.780020181634713e-05,
      "loss": 7.3097,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 1.184098720550537,
      "learning_rate": 7.679112008072655e-05,
      "loss": 7.3022,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 0.8562668561935425,
      "learning_rate": 7.578203834510595e-05,
      "loss": 7.2918,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 0.8222872018814087,
      "learning_rate": 7.477295660948537e-05,
      "loss": 7.2894,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 0.8184618949890137,
      "learning_rate": 7.376387487386479e-05,
      "loss": 7.2879,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 0.9152312874794006,
      "learning_rate": 7.27547931382442e-05,
      "loss": 7.2822,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 0.8646574020385742,
      "learning_rate": 7.174571140262362e-05,
      "loss": 7.2715,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 0.9313002228736877,
      "learning_rate": 7.073662966700304e-05,
      "loss": 7.2725,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 0.8215687870979309,
      "learning_rate": 6.972754793138244e-05,
      "loss": 7.2634,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 1.0029321908950806,
      "learning_rate": 6.871846619576186e-05,
      "loss": 7.2653,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 0.797988772392273,
      "learning_rate": 6.770938446014128e-05,
      "loss": 7.2673,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 1.0155805349349976,
      "learning_rate": 6.670030272452068e-05,
      "loss": 7.2549,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 0.8314929604530334,
      "learning_rate": 6.56912209889001e-05,
      "loss": 7.252,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 0.9168637990951538,
      "learning_rate": 6.468213925327952e-05,
      "loss": 7.2459,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 0.8579038977622986,
      "learning_rate": 6.367305751765893e-05,
      "loss": 7.2438,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 0.8211594223976135,
      "learning_rate": 6.266397578203835e-05,
      "loss": 7.243,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 1.0437767505645752,
      "learning_rate": 6.165489404641777e-05,
      "loss": 7.2366,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 0.9614302515983582,
      "learning_rate": 6.064581231079718e-05,
      "loss": 7.2297,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 0.8940654397010803,
      "learning_rate": 5.963673057517659e-05,
      "loss": 7.2331,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15541315723200044,
      "eval_loss": 7.2804460525512695,
      "eval_runtime": 0.7124,
      "eval_samples_per_second": 672.404,
      "eval_steps_per_second": 7.019,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 0.7710630297660828,
      "learning_rate": 5.8627648839556e-05,
      "loss": 7.228,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 0.8717989921569824,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 7.2311,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 0.9049319624900818,
      "learning_rate": 5.660948536831484e-05,
      "loss": 7.2201,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 0.8338859677314758,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 7.218,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 0.8981912732124329,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 7.2201,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 0.9057620763778687,
      "learning_rate": 5.358224016145308e-05,
      "loss": 7.2166,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 0.8201689124107361,
      "learning_rate": 5.257315842583249e-05,
      "loss": 7.2122,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 0.97395259141922,
      "learning_rate": 5.15640766902119e-05,
      "loss": 7.2045,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 1.0435025691986084,
      "learning_rate": 5.055499495459133e-05,
      "loss": 7.2061,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 0.9251586198806763,
      "learning_rate": 4.954591321897074e-05,
      "loss": 7.2045,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 0.826401948928833,
      "learning_rate": 4.853683148335015e-05,
      "loss": 7.2044,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 0.8331254124641418,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 7.1978,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 1.0407625436782837,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 7.1956,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 0.8447533249855042,
      "learning_rate": 4.55095862764884e-05,
      "loss": 7.1927,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 0.9017349481582642,
      "learning_rate": 4.450050454086781e-05,
      "loss": 7.1936,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 0.8850695490837097,
      "learning_rate": 4.349142280524723e-05,
      "loss": 7.1919,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 0.8294333219528198,
      "learning_rate": 4.248234106962664e-05,
      "loss": 7.1896,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 0.8609002828598022,
      "learning_rate": 4.147325933400605e-05,
      "loss": 7.1819,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 0.7830792665481567,
      "learning_rate": 4.046417759838547e-05,
      "loss": 7.1851,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 0.7615496516227722,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 7.1765,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15439609734215543,
      "eval_loss": 7.25421667098999,
      "eval_runtime": 0.7294,
      "eval_samples_per_second": 656.742,
      "eval_steps_per_second": 6.855,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 0.7594569325447083,
      "learning_rate": 3.84460141271443e-05,
      "loss": 7.1826,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 0.7539288401603699,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 7.1734,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 0.9915943741798401,
      "learning_rate": 3.642785065590313e-05,
      "loss": 7.1718,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 2.3651840686798096,
      "learning_rate": 3.541876892028255e-05,
      "loss": 7.1728,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 0.9876560568809509,
      "learning_rate": 3.440968718466196e-05,
      "loss": 7.1721,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 0.8784790635108948,
      "learning_rate": 3.340060544904137e-05,
      "loss": 7.1685,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 0.7426952719688416,
      "learning_rate": 3.239152371342079e-05,
      "loss": 7.1623,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 0.8913703560829163,
      "learning_rate": 3.13824419778002e-05,
      "loss": 7.1636,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 0.7314404845237732,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 7.1626,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 0.8047787547111511,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 7.1668,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 0.7927625179290771,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 7.1633,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 0.8079816102981567,
      "learning_rate": 2.734611503531786e-05,
      "loss": 7.1514,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 0.9051825404167175,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 7.1542,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 0.852149248123169,
      "learning_rate": 2.532795156407669e-05,
      "loss": 7.1555,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 0.9161846041679382,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 7.1539,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 0.7693049311637878,
      "learning_rate": 2.330978809283552e-05,
      "loss": 7.15,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 0.773891806602478,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 7.1472,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 0.8220585584640503,
      "learning_rate": 2.129162462159435e-05,
      "loss": 7.1452,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 0.7439760565757751,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 7.1451,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 0.8007863759994507,
      "learning_rate": 1.927346115035318e-05,
      "loss": 7.1457,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.15246586480500182,
      "eval_loss": 7.248484134674072,
      "eval_runtime": 0.7082,
      "eval_samples_per_second": 676.396,
      "eval_steps_per_second": 7.06,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 0.7827761769294739,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 7.14,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 0.8271605372428894,
      "learning_rate": 1.725529767911201e-05,
      "loss": 7.1411,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 0.7786771655082703,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 7.1403,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 0.8063676357269287,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 7.1401,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 0.7963306307792664,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 7.1395,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 0.7689283490180969,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 7.1308,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 0.8235142230987549,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 7.1338,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 0.7854271531105042,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 7.1361,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 0.7933940887451172,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 7.1324,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 0.7498176693916321,
      "learning_rate": 9.182643794147326e-06,
      "loss": 7.1309,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 0.7532030940055847,
      "learning_rate": 8.173562058526741e-06,
      "loss": 7.1293,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 0.9057742953300476,
      "learning_rate": 7.164480322906156e-06,
      "loss": 7.1291,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 0.8138079047203064,
      "learning_rate": 6.155398587285571e-06,
      "loss": 7.1246,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 0.8002745509147644,
      "learning_rate": 5.146316851664986e-06,
      "loss": 7.1282,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 0.7847145199775696,
      "learning_rate": 4.1372351160444e-06,
      "loss": 7.1268,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 0.8464835286140442,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 7.1263,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 0.7655928730964661,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 7.1229,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 0.8248621225357056,
      "learning_rate": 1.109989909182644e-06,
      "loss": 7.1237,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 0.736918032169342,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 7.1229,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 1.5149101316039424e+18,
      "train_loss": 7.379782975178421,
      "train_runtime": 17091.3155,
      "train_samples_per_second": 334.437,
      "train_steps_per_second": 3.484
    }
  ],
  "logging_steps": 500,
  "max_steps": 59550,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5149101316039424e+18,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}