{
  "best_global_step": 10000,
  "best_metric": 8.348302841186523,
  "best_model_checkpoint": "bert_base_rand_10_v1/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": 2.738006830215454,
      "learning_rate": 5e-06,
      "loss": 11.5311,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 2.344233989715576,
      "learning_rate": 1e-05,
      "loss": 9.8497,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 2.4206228256225586,
      "learning_rate": 1.5e-05,
      "loss": 9.3046,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 2.4757237434387207,
      "learning_rate": 2e-05,
      "loss": 9.147,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 2.196883201599121,
      "learning_rate": 2.5e-05,
      "loss": 9.0266,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 2.7844467163085938,
      "learning_rate": 3e-05,
      "loss": 8.9159,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 2.8705782890319824,
      "learning_rate": 3.5e-05,
      "loss": 8.8255,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 2.582951545715332,
      "learning_rate": 4e-05,
      "loss": 8.7585,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 1.4926308393478394,
      "learning_rate": 4.5e-05,
      "loss": 8.7001,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 2.2659192085266113,
      "learning_rate": 5e-05,
      "loss": 8.65,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 2.5833137035369873,
      "learning_rate": 5.500000000000001e-05,
      "loss": 8.6084,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 3.8351919651031494,
      "learning_rate": 6e-05,
      "loss": 8.5711,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 2.171334743499756,
      "learning_rate": 6.500000000000001e-05,
      "loss": 8.5377,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 2.449404716491699,
      "learning_rate": 7e-05,
      "loss": 8.5089,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 2.330808401107788,
      "learning_rate": 7.500000000000001e-05,
      "loss": 8.4853,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 2.690354108810425,
      "learning_rate": 8e-05,
      "loss": 8.4633,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 2.8651325702667236,
      "learning_rate": 8.5e-05,
      "loss": 8.4461,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 2.2023866176605225,
      "learning_rate": 9e-05,
      "loss": 8.4208,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 2.938070774078369,
      "learning_rate": 9.5e-05,
      "loss": 8.4022,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 3.0227391719818115,
      "learning_rate": 0.0001,
      "loss": 8.3701,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.15103369598486324,
      "eval_loss": 8.348302841186523,
      "eval_runtime": 1.0336,
      "eval_samples_per_second": 463.443,
      "eval_steps_per_second": 4.838,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 3.1094465255737305,
      "learning_rate": 9.899091826437942e-05,
      "loss": 8.3574,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 2.78938364982605,
      "learning_rate": 9.798183652875883e-05,
      "loss": 8.3416,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 3.089522123336792,
      "learning_rate": 9.697275479313825e-05,
      "loss": 8.335,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 3.6678249835968018,
      "learning_rate": 9.596367305751767e-05,
      "loss": 8.3097,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 2.9043314456939697,
      "learning_rate": 9.495459132189707e-05,
      "loss": 8.2502,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 2.5822110176086426,
      "learning_rate": 9.394550958627649e-05,
      "loss": 8.2493,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 3.309600830078125,
      "learning_rate": 9.293642785065591e-05,
      "loss": 8.2504,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 2.201144218444824,
      "learning_rate": 9.192734611503532e-05,
      "loss": 8.2451,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 2.9270811080932617,
      "learning_rate": 9.091826437941474e-05,
      "loss": 8.1972,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 3.376603603363037,
      "learning_rate": 8.990918264379415e-05,
      "loss": 8.1578,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 3.8584399223327637,
      "learning_rate": 8.890010090817356e-05,
      "loss": 8.1597,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 3.572781801223755,
      "learning_rate": 8.789101917255298e-05,
      "loss": 8.173,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 3.0658411979675293,
      "learning_rate": 8.68819374369324e-05,
      "loss": 8.1711,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 2.8477954864501953,
      "learning_rate": 8.58728557013118e-05,
      "loss": 8.0911,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 3.0082051753997803,
      "learning_rate": 8.486377396569122e-05,
      "loss": 8.0602,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 2.8394031524658203,
      "learning_rate": 8.385469223007064e-05,
      "loss": 8.0758,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 3.414165735244751,
      "learning_rate": 8.284561049445006e-05,
      "loss": 8.0894,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 3.3969035148620605,
      "learning_rate": 8.183652875882947e-05,
      "loss": 8.0884,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 3.785381555557251,
      "learning_rate": 8.082744702320889e-05,
      "loss": 7.9348,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 4.17163610458374,
      "learning_rate": 7.98183652875883e-05,
      "loss": 7.9389,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15238923651056427,
      "eval_loss": 8.604613304138184,
      "eval_runtime": 1.0146,
      "eval_samples_per_second": 472.088,
      "eval_steps_per_second": 4.928,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 3.9699599742889404,
      "learning_rate": 7.880928355196771e-05,
      "loss": 7.9438,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 3.6396028995513916,
      "learning_rate": 7.780020181634713e-05,
      "loss": 7.9638,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 4.428347587585449,
      "learning_rate": 7.679112008072655e-05,
      "loss": 7.926,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 4.6094512939453125,
      "learning_rate": 7.578203834510595e-05,
      "loss": 7.6864,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 5.198417663574219,
      "learning_rate": 7.477295660948537e-05,
      "loss": 7.7098,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 4.8224687576293945,
      "learning_rate": 7.376387487386479e-05,
      "loss": 7.736,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 5.061791896820068,
      "learning_rate": 7.27547931382442e-05,
      "loss": 7.7395,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 5.589750289916992,
      "learning_rate": 7.174571140262362e-05,
      "loss": 7.6216,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 5.2049431800842285,
      "learning_rate": 7.073662966700304e-05,
      "loss": 7.4373,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 6.537095546722412,
      "learning_rate": 6.972754793138244e-05,
      "loss": 7.4505,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 6.407931804656982,
      "learning_rate": 6.871846619576186e-05,
      "loss": 7.4753,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 5.707658290863037,
      "learning_rate": 6.770938446014128e-05,
      "loss": 7.4999,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 6.896782398223877,
      "learning_rate": 6.670030272452068e-05,
      "loss": 7.324,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 7.2015380859375,
      "learning_rate": 6.56912209889001e-05,
      "loss": 7.2343,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 5.525259017944336,
      "learning_rate": 6.468213925327952e-05,
      "loss": 7.2577,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 6.090493202209473,
      "learning_rate": 6.367305751765893e-05,
      "loss": 7.2702,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 6.514997482299805,
      "learning_rate": 6.266397578203835e-05,
      "loss": 7.2886,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 6.655533313751221,
      "learning_rate": 6.165489404641777e-05,
      "loss": 7.069,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 7.9436469078063965,
      "learning_rate": 6.064581231079718e-05,
      "loss": 7.0465,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 5.946670055389404,
      "learning_rate": 5.963673057517659e-05,
      "loss": 7.0842,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15379018943951647,
      "eval_loss": 9.748668670654297,
      "eval_runtime": 1.0175,
      "eval_samples_per_second": 470.761,
      "eval_steps_per_second": 4.914,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 9.042770385742188,
      "learning_rate": 5.8627648839556e-05,
      "loss": 7.1036,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 6.537632465362549,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 7.0945,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 6.758927345275879,
      "learning_rate": 5.660948536831484e-05,
      "loss": 6.8662,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 7.688127517700195,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 6.899,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 6.743930339813232,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 6.9313,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 7.3534088134765625,
      "learning_rate": 5.358224016145308e-05,
      "loss": 6.9362,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 6.898927688598633,
      "learning_rate": 5.257315842583249e-05,
      "loss": 6.8695,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 6.760592460632324,
      "learning_rate": 5.15640766902119e-05,
      "loss": 6.734,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 7.926515102386475,
      "learning_rate": 5.055499495459133e-05,
      "loss": 6.7535,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 7.2941670417785645,
      "learning_rate": 4.954591321897074e-05,
      "loss": 6.7748,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 6.363612651824951,
      "learning_rate": 4.853683148335015e-05,
      "loss": 6.787,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 5.911663055419922,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 6.6904,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 9.882594108581543,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 6.6176,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 7.49859094619751,
      "learning_rate": 4.55095862764884e-05,
      "loss": 6.6384,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 5.741410732269287,
      "learning_rate": 4.450050454086781e-05,
      "loss": 6.6537,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 7.008117198944092,
      "learning_rate": 4.349142280524723e-05,
      "loss": 6.6679,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 7.95073938369751,
      "learning_rate": 4.248234106962664e-05,
      "loss": 6.5461,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 6.109167575836182,
      "learning_rate": 4.147325933400605e-05,
      "loss": 6.5349,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 6.490021228790283,
      "learning_rate": 4.046417759838547e-05,
      "loss": 6.5422,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 8.00367259979248,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 6.5437,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15232140854547493,
      "eval_loss": 10.738933563232422,
      "eval_runtime": 1.0122,
      "eval_samples_per_second": 473.237,
      "eval_steps_per_second": 4.94,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 5.87666654586792,
      "learning_rate": 3.84460141271443e-05,
      "loss": 6.5665,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 5.679211139678955,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 6.4336,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 9.243278503417969,
      "learning_rate": 3.642785065590313e-05,
      "loss": 6.4466,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 8.360687255859375,
      "learning_rate": 3.541876892028255e-05,
      "loss": 6.4602,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 8.06490421295166,
      "learning_rate": 3.440968718466196e-05,
      "loss": 6.4648,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 6.15424108505249,
      "learning_rate": 3.340060544904137e-05,
      "loss": 6.439,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 8.923002243041992,
      "learning_rate": 3.239152371342079e-05,
      "loss": 6.3649,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 9.478067398071289,
      "learning_rate": 3.13824419778002e-05,
      "loss": 6.3789,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 7.185568809509277,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 6.3862,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 8.0621919631958,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 6.3875,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 5.572691440582275,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 6.3328,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 8.722589492797852,
      "learning_rate": 2.734611503531786e-05,
      "loss": 6.2937,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 7.654910564422607,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 6.2893,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 5.344693660736084,
      "learning_rate": 2.532795156407669e-05,
      "loss": 6.2995,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 6.080219268798828,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 6.2997,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 7.3079047203063965,
      "learning_rate": 2.330978809283552e-05,
      "loss": 6.2509,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 10.298888206481934,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 6.2305,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 5.902312755584717,
      "learning_rate": 2.129162462159435e-05,
      "loss": 6.2225,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 4.045109272003174,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 6.2261,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 8.121593475341797,
      "learning_rate": 1.927346115035318e-05,
      "loss": 6.2373,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.15187708526088542,
      "eval_loss": 11.188393592834473,
      "eval_runtime": 1.0174,
      "eval_samples_per_second": 470.791,
      "eval_steps_per_second": 4.914,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 7.056311130523682,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 6.1635,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 5.717972755432129,
      "learning_rate": 1.725529767911201e-05,
      "loss": 6.1727,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 5.620604991912842,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 6.1709,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 10.900132179260254,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 6.1712,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 3.5598325729370117,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 6.1611,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 3.418588399887085,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 6.1202,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 6.921347141265869,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 6.1211,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 4.688838958740234,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 6.1305,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 8.118000030517578,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 6.1212,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 3.7799837589263916,
      "learning_rate": 9.182643794147326e-06,
      "loss": 6.1083,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 6.724481105804443,
      "learning_rate": 8.173562058526741e-06,
      "loss": 6.0856,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 5.506434440612793,
      "learning_rate": 7.164480322906156e-06,
      "loss": 6.0983,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 4.985790729522705,
      "learning_rate": 6.155398587285571e-06,
      "loss": 6.088,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 5.027515888214111,
      "learning_rate": 5.146316851664986e-06,
      "loss": 6.0916,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 4.3696088790893555,
      "learning_rate": 4.1372351160444e-06,
      "loss": 6.0744,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 7.100973606109619,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 6.0786,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 3.8557090759277344,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 6.0781,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 4.056675910949707,
      "learning_rate": 1.109989909182644e-06,
      "loss": 6.0672,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 5.770939350128174,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 6.0644,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 1.5149776477860864e+18,
      "train_loss": 7.302537185323028,
      "train_runtime": 24682.558,
      "train_samples_per_second": 231.58,
      "train_steps_per_second": 2.413
    }
  ],
  "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": 1.5149776477860864e+18,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}