{
  "best_global_step": 20000,
  "best_metric": 7.080865383148193,
  "best_model_checkpoint": "distilbert_km_100_v1/checkpoint-20000",
  "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": 2.71114182472229,
      "learning_rate": 5e-06,
      "loss": 13.9058,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 2.3751590251922607,
      "learning_rate": 1e-05,
      "loss": 12.1512,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 4.571344375610352,
      "learning_rate": 1.5e-05,
      "loss": 11.0564,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 6.6696577072143555,
      "learning_rate": 2e-05,
      "loss": 9.8414,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 10.527233123779297,
      "learning_rate": 2.5e-05,
      "loss": 8.9949,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 12.987953186035156,
      "learning_rate": 3e-05,
      "loss": 8.4729,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 20.146738052368164,
      "learning_rate": 3.5e-05,
      "loss": 8.1732,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 8.621335983276367,
      "learning_rate": 4e-05,
      "loss": 7.9989,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 16.972379684448242,
      "learning_rate": 4.5e-05,
      "loss": 7.8607,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 7.252130031585693,
      "learning_rate": 5e-05,
      "loss": 7.718,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 11.060754776000977,
      "learning_rate": 5.500000000000001e-05,
      "loss": 7.6305,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 13.376608848571777,
      "learning_rate": 6e-05,
      "loss": 7.601,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 8.831477165222168,
      "learning_rate": 6.500000000000001e-05,
      "loss": 7.5579,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 6.316098690032959,
      "learning_rate": 7e-05,
      "loss": 7.5369,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 10.88084888458252,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.4184,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 6.708969593048096,
      "learning_rate": 8e-05,
      "loss": 7.3983,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 8.515560150146484,
      "learning_rate": 8.5e-05,
      "loss": 7.4107,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 6.825647830963135,
      "learning_rate": 9e-05,
      "loss": 7.3863,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 6.149193286895752,
      "learning_rate": 9.5e-05,
      "loss": 7.3673,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 4.2241058349609375,
      "learning_rate": 0.0001,
      "loss": 7.2572,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.14886335179053395,
      "eval_loss": 7.41864013671875,
      "eval_runtime": 0.8267,
      "eval_samples_per_second": 579.386,
      "eval_steps_per_second": 6.048,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 4.625662803649902,
      "learning_rate": 9.899091826437942e-05,
      "loss": 7.267,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 6.140921592712402,
      "learning_rate": 9.798183652875883e-05,
      "loss": 7.2438,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 8.918416023254395,
      "learning_rate": 9.697275479313825e-05,
      "loss": 7.2413,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 7.2943115234375,
      "learning_rate": 9.596367305751767e-05,
      "loss": 7.1818,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 4.169000148773193,
      "learning_rate": 9.495459132189707e-05,
      "loss": 7.0833,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 5.2431840896606445,
      "learning_rate": 9.394550958627649e-05,
      "loss": 7.0926,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 4.885514259338379,
      "learning_rate": 9.293642785065591e-05,
      "loss": 7.0922,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 5.952739715576172,
      "learning_rate": 9.192734611503532e-05,
      "loss": 7.0712,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 5.947248458862305,
      "learning_rate": 9.091826437941474e-05,
      "loss": 7.0118,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 4.958252429962158,
      "learning_rate": 8.990918264379415e-05,
      "loss": 6.9516,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 3.531912088394165,
      "learning_rate": 8.890010090817356e-05,
      "loss": 6.9468,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 5.290979385375977,
      "learning_rate": 8.789101917255298e-05,
      "loss": 6.9526,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 4.644420623779297,
      "learning_rate": 8.68819374369324e-05,
      "loss": 6.9578,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 6.7554826736450195,
      "learning_rate": 8.58728557013118e-05,
      "loss": 6.8533,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 3.8146345615386963,
      "learning_rate": 8.486377396569122e-05,
      "loss": 6.8068,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 7.763440132141113,
      "learning_rate": 8.385469223007064e-05,
      "loss": 6.829,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 5.544511318206787,
      "learning_rate": 8.284561049445006e-05,
      "loss": 6.8373,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 4.934683322906494,
      "learning_rate": 8.183652875882947e-05,
      "loss": 6.8419,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 4.9083781242370605,
      "learning_rate": 8.082744702320889e-05,
      "loss": 6.7049,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 4.699130058288574,
      "learning_rate": 7.98183652875883e-05,
      "loss": 6.7045,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15250147310530598,
      "eval_loss": 7.080865383148193,
      "eval_runtime": 0.821,
      "eval_samples_per_second": 583.451,
      "eval_steps_per_second": 6.09,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 5.228707790374756,
      "learning_rate": 7.880928355196771e-05,
      "loss": 6.7228,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 4.703908443450928,
      "learning_rate": 7.780020181634713e-05,
      "loss": 6.733,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 5.058104515075684,
      "learning_rate": 7.679112008072655e-05,
      "loss": 6.7193,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 4.291502952575684,
      "learning_rate": 7.578203834510595e-05,
      "loss": 6.5905,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 4.533291816711426,
      "learning_rate": 7.477295660948537e-05,
      "loss": 6.6081,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 5.64436149597168,
      "learning_rate": 7.376387487386479e-05,
      "loss": 6.6309,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 4.511686325073242,
      "learning_rate": 7.27547931382442e-05,
      "loss": 6.6302,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 5.592338562011719,
      "learning_rate": 7.174571140262362e-05,
      "loss": 6.5845,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 4.574922561645508,
      "learning_rate": 7.073662966700304e-05,
      "loss": 6.5117,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 6.213656425476074,
      "learning_rate": 6.972754793138244e-05,
      "loss": 6.5176,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 5.106657981872559,
      "learning_rate": 6.871846619576186e-05,
      "loss": 6.535,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 5.494438171386719,
      "learning_rate": 6.770938446014128e-05,
      "loss": 6.545,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 4.9139084815979,
      "learning_rate": 6.670030272452068e-05,
      "loss": 6.4669,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 6.39097785949707,
      "learning_rate": 6.56912209889001e-05,
      "loss": 6.431,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 4.48000431060791,
      "learning_rate": 6.468213925327952e-05,
      "loss": 6.4372,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 4.766469955444336,
      "learning_rate": 6.367305751765893e-05,
      "loss": 6.4482,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 3.4688408374786377,
      "learning_rate": 6.266397578203835e-05,
      "loss": 6.4604,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 5.803608417510986,
      "learning_rate": 6.165489404641777e-05,
      "loss": 6.3709,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 4.9567670822143555,
      "learning_rate": 6.064581231079718e-05,
      "loss": 6.359,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 4.016043186187744,
      "learning_rate": 5.963673057517659e-05,
      "loss": 6.3773,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15381817164283515,
      "eval_loss": 7.200456619262695,
      "eval_runtime": 0.8293,
      "eval_samples_per_second": 577.62,
      "eval_steps_per_second": 6.029,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 6.485772609710693,
      "learning_rate": 5.8627648839556e-05,
      "loss": 6.3784,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 4.030270099639893,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 6.3795,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 5.271803855895996,
      "learning_rate": 5.660948536831484e-05,
      "loss": 6.3031,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 5.648588180541992,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 6.3069,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 4.713584899902344,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 6.3169,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 4.5393242835998535,
      "learning_rate": 5.358224016145308e-05,
      "loss": 6.3167,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 3.9688968658447266,
      "learning_rate": 5.257315842583249e-05,
      "loss": 6.2945,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 3.948341131210327,
      "learning_rate": 5.15640766902119e-05,
      "loss": 6.2569,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 4.375942230224609,
      "learning_rate": 5.055499495459133e-05,
      "loss": 6.2646,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 4.566441535949707,
      "learning_rate": 4.954591321897074e-05,
      "loss": 6.2598,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 5.5283894538879395,
      "learning_rate": 4.853683148335015e-05,
      "loss": 6.269,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 4.043588161468506,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 6.2448,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 4.9567551612854,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 6.2211,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 3.3084328174591064,
      "learning_rate": 4.55095862764884e-05,
      "loss": 6.2154,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 3.049226999282837,
      "learning_rate": 4.450050454086781e-05,
      "loss": 6.2207,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 6.377516746520996,
      "learning_rate": 4.349142280524723e-05,
      "loss": 6.2177,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 4.754726409912109,
      "learning_rate": 4.248234106962664e-05,
      "loss": 6.1901,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 4.511970043182373,
      "learning_rate": 4.147325933400605e-05,
      "loss": 6.1801,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 6.209725379943848,
      "learning_rate": 4.046417759838547e-05,
      "loss": 6.1857,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 5.476673126220703,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 6.1723,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15173264550857912,
      "eval_loss": 7.318363666534424,
      "eval_runtime": 0.8314,
      "eval_samples_per_second": 576.156,
      "eval_steps_per_second": 6.014,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 5.484135150909424,
      "learning_rate": 3.84460141271443e-05,
      "loss": 6.184,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 4.58940315246582,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 6.1442,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 4.109139442443848,
      "learning_rate": 3.642785065590313e-05,
      "loss": 6.1462,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 5.724867820739746,
      "learning_rate": 3.541876892028255e-05,
      "loss": 6.1504,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 4.447635650634766,
      "learning_rate": 3.440968718466196e-05,
      "loss": 6.151,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 3.7838315963745117,
      "learning_rate": 3.340060544904137e-05,
      "loss": 6.1421,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 1.9362503290176392,
      "learning_rate": 3.239152371342079e-05,
      "loss": 6.1197,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 4.64004373550415,
      "learning_rate": 3.13824419778002e-05,
      "loss": 6.1227,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 4.569913864135742,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 6.1204,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 4.237504482269287,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 6.1246,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 2.905588388442993,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 6.1106,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 3.679658889770508,
      "learning_rate": 2.734611503531786e-05,
      "loss": 6.0924,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 6.915002346038818,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 6.0912,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 4.801191806793213,
      "learning_rate": 2.532795156407669e-05,
      "loss": 6.0961,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 6.099165916442871,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 6.0895,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 3.534881114959717,
      "learning_rate": 2.330978809283552e-05,
      "loss": 6.0793,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 4.622105121612549,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 6.0719,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 3.0045816898345947,
      "learning_rate": 2.129162462159435e-05,
      "loss": 6.0749,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 5.151672840118408,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 6.0711,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 3.802955389022827,
      "learning_rate": 1.927346115035318e-05,
      "loss": 6.0693,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.1507556004149494,
      "eval_loss": 7.467113494873047,
      "eval_runtime": 0.8265,
      "eval_samples_per_second": 579.53,
      "eval_steps_per_second": 6.049,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 4.134366512298584,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 6.0567,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 5.10377311706543,
      "learning_rate": 1.725529767911201e-05,
      "loss": 6.0565,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 2.235971689224243,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 6.0552,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 4.676805019378662,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 6.0546,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 1.945378065109253,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 6.0485,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 3.0484297275543213,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 6.0324,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 2.8624603748321533,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 6.0375,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 3.1307296752929688,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 6.0384,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 3.2458927631378174,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 6.0308,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 1.7762402296066284,
      "learning_rate": 9.182643794147326e-06,
      "loss": 6.0273,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 2.609205961227417,
      "learning_rate": 8.173562058526741e-06,
      "loss": 6.0242,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 2.721087694168091,
      "learning_rate": 7.164480322906156e-06,
      "loss": 6.0246,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 2.8588500022888184,
      "learning_rate": 6.155398587285571e-06,
      "loss": 6.0171,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 2.748302459716797,
      "learning_rate": 5.146316851664986e-06,
      "loss": 6.0194,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 3.2302844524383545,
      "learning_rate": 4.1372351160444e-06,
      "loss": 6.013,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 3.746107816696167,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 6.0149,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 4.354255199432373,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 6.0122,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 1.9858312606811523,
      "learning_rate": 1.109989909182644e-06,
      "loss": 6.0097,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 1.0150333642959595,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 6.0079,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 7.69437063436032e+17,
      "train_loss": 6.748248844995507,
      "train_runtime": 17139.2382,
      "train_samples_per_second": 333.502,
      "train_steps_per_second": 3.474
    }
  ],
  "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": 7.69437063436032e+17,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}