{
  "best_global_step": 10000,
  "best_metric": 10.777170181274414,
  "best_model_checkpoint": "bert_base_rand_100_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": 3.0288546085357666,
      "learning_rate": 5e-06,
      "loss": 13.8221,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 2.2684197425842285,
      "learning_rate": 1e-05,
      "loss": 12.1665,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 2.185971975326538,
      "learning_rate": 1.5e-05,
      "loss": 11.624,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 2.3456804752349854,
      "learning_rate": 2e-05,
      "loss": 11.4706,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 2.188506841659546,
      "learning_rate": 2.5e-05,
      "loss": 11.3489,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 2.1402158737182617,
      "learning_rate": 3e-05,
      "loss": 11.2399,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 2.537099599838257,
      "learning_rate": 3.5e-05,
      "loss": 11.1498,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 2.090782880783081,
      "learning_rate": 4e-05,
      "loss": 11.0823,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 2.455458402633667,
      "learning_rate": 4.5e-05,
      "loss": 11.0244,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 2.6351730823516846,
      "learning_rate": 5e-05,
      "loss": 10.9748,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 2.457446575164795,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.9391,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 2.370234727859497,
      "learning_rate": 6e-05,
      "loss": 10.9038,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 2.3302018642425537,
      "learning_rate": 6.500000000000001e-05,
      "loss": 10.8736,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 2.375312089920044,
      "learning_rate": 7e-05,
      "loss": 10.8467,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 2.4444057941436768,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.8111,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 2.5382955074310303,
      "learning_rate": 8e-05,
      "loss": 10.7894,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 2.60207462310791,
      "learning_rate": 8.5e-05,
      "loss": 10.78,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 2.5621426105499268,
      "learning_rate": 9e-05,
      "loss": 10.7584,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 2.618440628051758,
      "learning_rate": 9.5e-05,
      "loss": 10.7483,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 2.7958285808563232,
      "learning_rate": 0.0001,
      "loss": 10.6199,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.1508945713570216,
      "eval_loss": 10.777170181274414,
      "eval_runtime": 1.0602,
      "eval_samples_per_second": 451.803,
      "eval_steps_per_second": 4.716,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 2.811058282852173,
      "learning_rate": 9.899091826437942e-05,
      "loss": 10.624,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 3.198634147644043,
      "learning_rate": 9.798183652875883e-05,
      "loss": 10.6146,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 3.002030372619629,
      "learning_rate": 9.697275479313825e-05,
      "loss": 10.6227,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 3.1160995960235596,
      "learning_rate": 9.596367305751767e-05,
      "loss": 10.5634,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 3.492047071456909,
      "learning_rate": 9.495459132189707e-05,
      "loss": 10.3606,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 3.3820676803588867,
      "learning_rate": 9.394550958627649e-05,
      "loss": 10.3831,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 3.412482738494873,
      "learning_rate": 9.293642785065591e-05,
      "loss": 10.408,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 3.3706846237182617,
      "learning_rate": 9.192734611503532e-05,
      "loss": 10.4226,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 3.5451669692993164,
      "learning_rate": 9.091826437941474e-05,
      "loss": 10.2732,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 3.801152229309082,
      "learning_rate": 8.990918264379415e-05,
      "loss": 10.1065,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 3.8326215744018555,
      "learning_rate": 8.890010090817356e-05,
      "loss": 10.1457,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 4.030295372009277,
      "learning_rate": 8.789101917255298e-05,
      "loss": 10.1759,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 3.953282117843628,
      "learning_rate": 8.68819374369324e-05,
      "loss": 10.2084,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 4.436263084411621,
      "learning_rate": 8.58728557013118e-05,
      "loss": 9.8891,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 5.093210697174072,
      "learning_rate": 8.486377396569122e-05,
      "loss": 9.7582,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 4.858946323394775,
      "learning_rate": 8.385469223007064e-05,
      "loss": 9.8111,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 5.1670427322387695,
      "learning_rate": 8.284561049445006e-05,
      "loss": 9.8575,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 4.948832035064697,
      "learning_rate": 8.183652875882947e-05,
      "loss": 9.8647,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 6.108199596405029,
      "learning_rate": 8.082744702320889e-05,
      "loss": 9.3266,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 6.050924777984619,
      "learning_rate": 7.98183652875883e-05,
      "loss": 9.3028,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15210864502371,
      "eval_loss": 11.480384826660156,
      "eval_runtime": 1.0443,
      "eval_samples_per_second": 458.691,
      "eval_steps_per_second": 4.788,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 6.519136428833008,
      "learning_rate": 7.880928355196771e-05,
      "loss": 9.3288,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 6.966094493865967,
      "learning_rate": 7.780020181634713e-05,
      "loss": 9.3887,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 6.537182331085205,
      "learning_rate": 7.679112008072655e-05,
      "loss": 9.3129,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 7.5293426513671875,
      "learning_rate": 7.578203834510595e-05,
      "loss": 8.7479,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 7.810515880584717,
      "learning_rate": 7.477295660948537e-05,
      "loss": 8.798,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 7.096532821655273,
      "learning_rate": 7.376387487386479e-05,
      "loss": 8.8574,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 7.4897141456604,
      "learning_rate": 7.27547931382442e-05,
      "loss": 8.8796,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 7.99169397354126,
      "learning_rate": 7.174571140262362e-05,
      "loss": 8.6745,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 7.682992458343506,
      "learning_rate": 7.073662966700304e-05,
      "loss": 8.3111,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 7.966315746307373,
      "learning_rate": 6.972754793138244e-05,
      "loss": 8.3631,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 7.781931400299072,
      "learning_rate": 6.871846619576186e-05,
      "loss": 8.4012,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 7.852003574371338,
      "learning_rate": 6.770938446014128e-05,
      "loss": 8.4645,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 7.70206356048584,
      "learning_rate": 6.670030272452068e-05,
      "loss": 8.1223,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 8.802687644958496,
      "learning_rate": 6.56912209889001e-05,
      "loss": 7.9423,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 8.93272876739502,
      "learning_rate": 6.468213925327952e-05,
      "loss": 7.9878,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 9.18610668182373,
      "learning_rate": 6.367305751765893e-05,
      "loss": 8.0387,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 8.444122314453125,
      "learning_rate": 6.266397578203835e-05,
      "loss": 8.0803,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 8.10969352722168,
      "learning_rate": 6.165489404641777e-05,
      "loss": 7.6323,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 9.190276145935059,
      "learning_rate": 6.064581231079718e-05,
      "loss": 7.577,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 9.622087478637695,
      "learning_rate": 5.963673057517659e-05,
      "loss": 7.6531,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15426588689593418,
      "eval_loss": 12.849151611328125,
      "eval_runtime": 1.0649,
      "eval_samples_per_second": 449.811,
      "eval_steps_per_second": 4.695,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 7.7016377449035645,
      "learning_rate": 5.8627648839556e-05,
      "loss": 7.6969,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 10.706731796264648,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 7.6693,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 8.698975563049316,
      "learning_rate": 5.660948536831484e-05,
      "loss": 7.225,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 9.907671928405762,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 7.2746,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 9.54379653930664,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 7.3404,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 8.690727233886719,
      "learning_rate": 5.358224016145308e-05,
      "loss": 7.3524,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 8.512101173400879,
      "learning_rate": 5.257315842583249e-05,
      "loss": 7.2405,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 8.534492492675781,
      "learning_rate": 5.15640766902119e-05,
      "loss": 6.9742,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 10.620044708251953,
      "learning_rate": 5.055499495459133e-05,
      "loss": 7.0145,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 9.569381713867188,
      "learning_rate": 4.954591321897074e-05,
      "loss": 7.0483,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 9.324925422668457,
      "learning_rate": 4.853683148335015e-05,
      "loss": 7.0639,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 9.158879280090332,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 6.9082,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 11.017550468444824,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 6.7696,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 10.319367408752441,
      "learning_rate": 4.55095862764884e-05,
      "loss": 6.7957,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 10.475912094116211,
      "learning_rate": 4.450050454086781e-05,
      "loss": 6.8285,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 11.010168075561523,
      "learning_rate": 4.349142280524723e-05,
      "loss": 6.864,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 9.048985481262207,
      "learning_rate": 4.248234106962664e-05,
      "loss": 6.6573,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 7.930765628814697,
      "learning_rate": 4.147325933400605e-05,
      "loss": 6.6427,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 11.305169105529785,
      "learning_rate": 4.046417759838547e-05,
      "loss": 6.6512,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 9.738286972045898,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 6.6672,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15122799147695412,
      "eval_loss": 13.983076095581055,
      "eval_runtime": 1.0738,
      "eval_samples_per_second": 446.098,
      "eval_steps_per_second": 4.657,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 9.445182800292969,
      "learning_rate": 3.84460141271443e-05,
      "loss": 6.6849,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 7.16201639175415,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 6.5182,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 9.42516803741455,
      "learning_rate": 3.642785065590313e-05,
      "loss": 6.5356,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 7.983398914337158,
      "learning_rate": 3.541876892028255e-05,
      "loss": 6.5536,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 9.222135543823242,
      "learning_rate": 3.440968718466196e-05,
      "loss": 6.5673,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 6.936710834503174,
      "learning_rate": 3.340060544904137e-05,
      "loss": 6.5335,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 8.71493148803711,
      "learning_rate": 3.239152371342079e-05,
      "loss": 6.4655,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 8.3333740234375,
      "learning_rate": 3.13824419778002e-05,
      "loss": 6.47,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 8.062196731567383,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 6.4879,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 9.523862838745117,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 6.5013,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 11.169639587402344,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 6.4436,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 8.897358894348145,
      "learning_rate": 2.734611503531786e-05,
      "loss": 6.4142,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 10.57607364654541,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 6.4186,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 7.845455646514893,
      "learning_rate": 2.532795156407669e-05,
      "loss": 6.4111,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 10.096842765808105,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 6.4198,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 5.987013339996338,
      "learning_rate": 2.330978809283552e-05,
      "loss": 6.3938,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 9.082942962646484,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 6.3737,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 7.940201759338379,
      "learning_rate": 2.129162462159435e-05,
      "loss": 6.3672,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 7.548001766204834,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 6.3627,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 8.274439811706543,
      "learning_rate": 1.927346115035318e-05,
      "loss": 6.3804,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.15159671404940142,
      "eval_loss": 14.204442024230957,
      "eval_runtime": 1.0518,
      "eval_samples_per_second": 455.422,
      "eval_steps_per_second": 4.754,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 6.281366348266602,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 6.3318,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 9.802014350891113,
      "learning_rate": 1.725529767911201e-05,
      "loss": 6.3398,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 8.149238586425781,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 6.3349,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 6.593752861022949,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 6.3284,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 2.956167459487915,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 6.3249,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 4.512640953063965,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 6.2946,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 11.271622657775879,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 6.2875,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 7.6845808029174805,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 6.3013,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 5.525491714477539,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 6.2917,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 5.898003101348877,
      "learning_rate": 9.182643794147326e-06,
      "loss": 6.2772,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 8.67507553100586,
      "learning_rate": 8.173562058526741e-06,
      "loss": 6.2608,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 9.189558029174805,
      "learning_rate": 7.164480322906156e-06,
      "loss": 6.2795,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 5.64956521987915,
      "learning_rate": 6.155398587285571e-06,
      "loss": 6.2567,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 7.6284403800964355,
      "learning_rate": 5.146316851664986e-06,
      "loss": 6.2608,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 8.063921928405762,
      "learning_rate": 4.1372351160444e-06,
      "loss": 6.2456,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 7.865649223327637,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 6.2525,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 6.730928897857666,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 6.2519,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 5.551456928253174,
      "learning_rate": 1.109989909182644e-06,
      "loss": 6.245,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 5.154201030731201,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 6.2324,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 1.5161929390646784e+18,
      "train_loss": 8.272559419851358,
      "train_runtime": 25341.6856,
      "train_samples_per_second": 225.556,
      "train_steps_per_second": 2.35
    }
  ],
  "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": 1.5161929390646784e+18,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}