{
  "best_global_step": 10000,
  "best_metric": 9.065109252929688,
  "best_model_checkpoint": "bert_base_rand_20_v2/checkpoint-10000",
  "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": 3.0308218002319336,
      "learning_rate": 5e-06,
      "loss": 12.1977,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 2.4327733516693115,
      "learning_rate": 1e-05,
      "loss": 10.5454,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 1.899172067642212,
      "learning_rate": 1.5e-05,
      "loss": 10.0079,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 1.7947323322296143,
      "learning_rate": 2e-05,
      "loss": 9.8503,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 2.0414254665374756,
      "learning_rate": 2.5e-05,
      "loss": 9.7294,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 2.25095272064209,
      "learning_rate": 3e-05,
      "loss": 9.6169,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 2.219564914703369,
      "learning_rate": 3.5e-05,
      "loss": 9.5259,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 1.8111666440963745,
      "learning_rate": 4e-05,
      "loss": 9.4574,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 2.3417046070098877,
      "learning_rate": 4.5e-05,
      "loss": 9.3995,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 2.3426718711853027,
      "learning_rate": 5e-05,
      "loss": 9.3492,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 2.1550545692443848,
      "learning_rate": 5.500000000000001e-05,
      "loss": 9.3097,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 2.569795846939087,
      "learning_rate": 6e-05,
      "loss": 9.2719,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 2.7756941318511963,
      "learning_rate": 6.500000000000001e-05,
      "loss": 9.2391,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 2.712641477584839,
      "learning_rate": 7e-05,
      "loss": 9.209,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 2.3369410037994385,
      "learning_rate": 7.500000000000001e-05,
      "loss": 9.1855,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 2.314936399459839,
      "learning_rate": 8e-05,
      "loss": 9.1649,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 3.075246572494507,
      "learning_rate": 8.5e-05,
      "loss": 9.148,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 3.077697515487671,
      "learning_rate": 9e-05,
      "loss": 9.1222,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 2.9913086891174316,
      "learning_rate": 9.5e-05,
      "loss": 9.1057,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 3.597776412963867,
      "learning_rate": 0.0001,
      "loss": 9.0594,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.15092239628258994,
      "eval_loss": 9.065109252929688,
      "eval_runtime": 1.0336,
      "eval_samples_per_second": 463.438,
      "eval_steps_per_second": 4.838,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 2.595629930496216,
      "learning_rate": 9.899091826437942e-05,
      "loss": 9.0438,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 2.5200111865997314,
      "learning_rate": 9.798183652875883e-05,
      "loss": 9.0326,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 3.3044512271881104,
      "learning_rate": 9.697275479313825e-05,
      "loss": 9.0298,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 3.339869499206543,
      "learning_rate": 9.596367305751767e-05,
      "loss": 8.9946,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 3.565800666809082,
      "learning_rate": 9.495459132189707e-05,
      "loss": 8.8959,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 3.91796612739563,
      "learning_rate": 9.394550958627649e-05,
      "loss": 8.9122,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 3.0361363887786865,
      "learning_rate": 9.293642785065591e-05,
      "loss": 8.9154,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 3.6139206886291504,
      "learning_rate": 9.192734611503532e-05,
      "loss": 8.9138,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 3.5524585247039795,
      "learning_rate": 9.091826437941474e-05,
      "loss": 8.8435,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 2.9967706203460693,
      "learning_rate": 8.990918264379415e-05,
      "loss": 8.7773,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 2.7934579849243164,
      "learning_rate": 8.890010090817356e-05,
      "loss": 8.7888,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 3.5226430892944336,
      "learning_rate": 8.789101917255298e-05,
      "loss": 8.8033,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 4.111179351806641,
      "learning_rate": 8.68819374369324e-05,
      "loss": 8.8123,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 3.3247392177581787,
      "learning_rate": 8.58728557013118e-05,
      "loss": 8.6669,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 3.9535279273986816,
      "learning_rate": 8.486377396569122e-05,
      "loss": 8.6189,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 3.8891823291778564,
      "learning_rate": 8.385469223007064e-05,
      "loss": 8.6515,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 3.8274359703063965,
      "learning_rate": 8.284561049445006e-05,
      "loss": 8.6651,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 3.6684072017669678,
      "learning_rate": 8.183652875882947e-05,
      "loss": 8.6732,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 4.276801109313965,
      "learning_rate": 8.082744702320889e-05,
      "loss": 8.3804,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 4.779017925262451,
      "learning_rate": 7.98183652875883e-05,
      "loss": 8.3784,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.1525295322539914,
      "eval_loss": 9.502010345458984,
      "eval_runtime": 1.0346,
      "eval_samples_per_second": 462.997,
      "eval_steps_per_second": 4.833,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 4.9919114112854,
      "learning_rate": 7.880928355196771e-05,
      "loss": 8.3976,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 5.021790504455566,
      "learning_rate": 7.780020181634713e-05,
      "loss": 8.4266,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 6.880457401275635,
      "learning_rate": 7.679112008072655e-05,
      "loss": 8.3783,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 6.020832538604736,
      "learning_rate": 7.578203834510595e-05,
      "loss": 8.0255,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 6.427469253540039,
      "learning_rate": 7.477295660948537e-05,
      "loss": 8.0499,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 5.471770286560059,
      "learning_rate": 7.376387487386479e-05,
      "loss": 8.0971,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 6.466521263122559,
      "learning_rate": 7.27547931382442e-05,
      "loss": 8.0974,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 5.689241409301758,
      "learning_rate": 7.174571140262362e-05,
      "loss": 7.9726,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 5.892643451690674,
      "learning_rate": 7.073662966700304e-05,
      "loss": 7.746,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 7.06170654296875,
      "learning_rate": 6.972754793138244e-05,
      "loss": 7.7692,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 7.507574081420898,
      "learning_rate": 6.871846619576186e-05,
      "loss": 7.8097,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 7.282630920410156,
      "learning_rate": 6.770938446014128e-05,
      "loss": 7.8392,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 7.8448872566223145,
      "learning_rate": 6.670030272452068e-05,
      "loss": 7.6247,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 6.813558578491211,
      "learning_rate": 6.56912209889001e-05,
      "loss": 7.52,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 5.603688716888428,
      "learning_rate": 6.468213925327952e-05,
      "loss": 7.5587,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 8.152605056762695,
      "learning_rate": 6.367305751765893e-05,
      "loss": 7.5688,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 6.765694618225098,
      "learning_rate": 6.266397578203835e-05,
      "loss": 7.6036,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 9.186474800109863,
      "learning_rate": 6.165489404641777e-05,
      "loss": 7.3235,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 8.772801399230957,
      "learning_rate": 6.064581231079718e-05,
      "loss": 7.2951,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 9.275589942932129,
      "learning_rate": 5.963673057517659e-05,
      "loss": 7.3382,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15303466994991186,
      "eval_loss": 10.855603218078613,
      "eval_runtime": 1.0198,
      "eval_samples_per_second": 469.721,
      "eval_steps_per_second": 4.903,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 7.982213020324707,
      "learning_rate": 5.8627648839556e-05,
      "loss": 7.3658,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 8.000374794006348,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 7.3535,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 9.556083679199219,
      "learning_rate": 5.660948536831484e-05,
      "loss": 7.0701,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 9.914329528808594,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 7.1059,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 7.568287372589111,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 7.1469,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 6.821398735046387,
      "learning_rate": 5.358224016145308e-05,
      "loss": 7.1523,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 7.772975444793701,
      "learning_rate": 5.257315842583249e-05,
      "loss": 7.0788,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 9.745587348937988,
      "learning_rate": 5.15640766902119e-05,
      "loss": 6.8992,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 7.389908313751221,
      "learning_rate": 5.055499495459133e-05,
      "loss": 6.9267,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 7.512205123901367,
      "learning_rate": 4.954591321897074e-05,
      "loss": 6.9509,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 8.74570083618164,
      "learning_rate": 4.853683148335015e-05,
      "loss": 6.9629,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 9.084261894226074,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 6.8317,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 8.2465238571167,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 6.7407,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 8.073356628417969,
      "learning_rate": 4.55095862764884e-05,
      "loss": 6.7606,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 7.8887529373168945,
      "learning_rate": 4.450050454086781e-05,
      "loss": 6.7849,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 10.014334678649902,
      "learning_rate": 4.349142280524723e-05,
      "loss": 6.8052,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 7.972960948944092,
      "learning_rate": 4.248234106962664e-05,
      "loss": 6.6332,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 7.208271503448486,
      "learning_rate": 4.147325933400605e-05,
      "loss": 6.6161,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 11.550618171691895,
      "learning_rate": 4.046417759838547e-05,
      "loss": 6.6255,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 9.207111358642578,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 6.6369,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.1519849725243916,
      "eval_loss": 11.952146530151367,
      "eval_runtime": 1.0125,
      "eval_samples_per_second": 473.089,
      "eval_steps_per_second": 4.938,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 7.137587070465088,
      "learning_rate": 3.84460141271443e-05,
      "loss": 6.6614,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 8.455475807189941,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 6.4812,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 9.873649597167969,
      "learning_rate": 3.642785065590313e-05,
      "loss": 6.5059,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 8.446501731872559,
      "learning_rate": 3.541876892028255e-05,
      "loss": 6.5169,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 7.7715606689453125,
      "learning_rate": 3.440968718466196e-05,
      "loss": 6.5316,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 7.825333118438721,
      "learning_rate": 3.340060544904137e-05,
      "loss": 6.498,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 8.917506217956543,
      "learning_rate": 3.239152371342079e-05,
      "loss": 6.4094,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 8.458283424377441,
      "learning_rate": 3.13824419778002e-05,
      "loss": 6.4178,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 8.396074295043945,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 6.4292,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 6.289218902587891,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 6.4439,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 9.249333381652832,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 6.3816,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 5.880438804626465,
      "learning_rate": 2.734611503531786e-05,
      "loss": 6.337,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 9.66485595703125,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 6.3425,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 7.285576343536377,
      "learning_rate": 2.532795156407669e-05,
      "loss": 6.3536,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 8.842156410217285,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 6.351,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 8.728751182556152,
      "learning_rate": 2.330978809283552e-05,
      "loss": 6.3055,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 7.451524257659912,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 6.2863,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 5.038097381591797,
      "learning_rate": 2.129162462159435e-05,
      "loss": 6.2799,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 5.486204147338867,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 6.2762,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 7.932175159454346,
      "learning_rate": 1.927346115035318e-05,
      "loss": 6.2858,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.1512602685956206,
      "eval_loss": 12.46147346496582,
      "eval_runtime": 1.0119,
      "eval_samples_per_second": 473.349,
      "eval_steps_per_second": 4.941,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 7.7092485427856445,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 6.2279,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 9.494937896728516,
      "learning_rate": 1.725529767911201e-05,
      "loss": 6.2366,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 9.652212142944336,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 6.228,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 5.58165979385376,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 6.2309,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 8.985339164733887,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 6.2171,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 7.544305801391602,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 6.1848,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 8.620584487915039,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 6.1863,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 8.475058555603027,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 6.189,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 4.212444305419922,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 6.1791,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 4.587650299072266,
      "learning_rate": 9.182643794147326e-06,
      "loss": 6.1679,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 6.570645809173584,
      "learning_rate": 8.173562058526741e-06,
      "loss": 6.1543,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 7.142970561981201,
      "learning_rate": 7.164480322906156e-06,
      "loss": 6.1603,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 5.22387170791626,
      "learning_rate": 6.155398587285571e-06,
      "loss": 6.1463,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 4.836696147918701,
      "learning_rate": 5.146316851664986e-06,
      "loss": 6.1529,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 5.709256172180176,
      "learning_rate": 4.1372351160444e-06,
      "loss": 6.1382,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 7.1039276123046875,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 6.141,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 4.547121047973633,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 6.1454,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 4.302024841308594,
      "learning_rate": 1.109989909182644e-06,
      "loss": 6.1342,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 5.072787761688232,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 6.1273,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 1.5151126801503744e+18,
      "train_loss": 7.625829259710688,
      "train_runtime": 24701.7833,
      "train_samples_per_second": 231.399,
      "train_steps_per_second": 2.411
    }
  ],
  "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": 1.5151126801503744e+18,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}