{
  "best_global_step": 10000,
  "best_metric": 10.877986907958984,
  "best_model_checkpoint": "tiny_bert_rand_100_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": 2.5572659969329834,
      "learning_rate": 5e-06,
      "loss": 14.3831,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 1.9128535985946655,
      "learning_rate": 1e-05,
      "loss": 12.8302,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 1.3849263191223145,
      "learning_rate": 1.5e-05,
      "loss": 11.8293,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 1.4482187032699585,
      "learning_rate": 2e-05,
      "loss": 11.6299,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 1.5666471719741821,
      "learning_rate": 2.5e-05,
      "loss": 11.5164,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 1.5316394567489624,
      "learning_rate": 3e-05,
      "loss": 11.4096,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 1.624151587486267,
      "learning_rate": 3.5e-05,
      "loss": 11.3235,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 1.6171917915344238,
      "learning_rate": 4e-05,
      "loss": 11.2436,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 1.6842340230941772,
      "learning_rate": 4.5e-05,
      "loss": 11.168,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 1.6750656366348267,
      "learning_rate": 5e-05,
      "loss": 11.0996,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 1.8050826787948608,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.0498,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 1.8148760795593262,
      "learning_rate": 6e-05,
      "loss": 11.0198,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 1.6439528465270996,
      "learning_rate": 6.500000000000001e-05,
      "loss": 10.9905,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 1.6980109214782715,
      "learning_rate": 7e-05,
      "loss": 10.9666,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 1.8215588331222534,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.8994,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 2.0708038806915283,
      "learning_rate": 8e-05,
      "loss": 10.8626,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 2.0195438861846924,
      "learning_rate": 8.5e-05,
      "loss": 10.8542,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 2.1393017768859863,
      "learning_rate": 9e-05,
      "loss": 10.8307,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 2.1128833293914795,
      "learning_rate": 9.5e-05,
      "loss": 10.8188,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 2.402693033218384,
      "learning_rate": 0.0001,
      "loss": 10.6718,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.15031024792008682,
      "eval_loss": 10.877986907958984,
      "eval_runtime": 0.7377,
      "eval_samples_per_second": 649.29,
      "eval_steps_per_second": 6.778,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 2.3706765174865723,
      "learning_rate": 9.899091826437942e-05,
      "loss": 10.6627,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 2.860837459564209,
      "learning_rate": 9.798183652875883e-05,
      "loss": 10.6533,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 2.6545329093933105,
      "learning_rate": 9.697275479313825e-05,
      "loss": 10.6544,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 2.755854845046997,
      "learning_rate": 9.596367305751767e-05,
      "loss": 10.6097,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 3.319854259490967,
      "learning_rate": 9.495459132189707e-05,
      "loss": 10.4385,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 2.9512271881103516,
      "learning_rate": 9.394550958627649e-05,
      "loss": 10.4491,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 3.0148348808288574,
      "learning_rate": 9.293642785065591e-05,
      "loss": 10.4647,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 3.2384345531463623,
      "learning_rate": 9.192734611503532e-05,
      "loss": 10.4676,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 2.9073562622070312,
      "learning_rate": 9.091826437941474e-05,
      "loss": 10.3749,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 3.051823377609253,
      "learning_rate": 8.990918264379415e-05,
      "loss": 10.2731,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 3.5354576110839844,
      "learning_rate": 8.890010090817356e-05,
      "loss": 10.297,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 3.0191292762756348,
      "learning_rate": 8.789101917255298e-05,
      "loss": 10.3226,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 3.1657397747039795,
      "learning_rate": 8.68819374369324e-05,
      "loss": 10.344,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 3.2006120681762695,
      "learning_rate": 8.58728557013118e-05,
      "loss": 10.1945,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 3.8116540908813477,
      "learning_rate": 8.486377396569122e-05,
      "loss": 10.1432,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 3.2532706260681152,
      "learning_rate": 8.385469223007064e-05,
      "loss": 10.1818,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 3.331171989440918,
      "learning_rate": 8.284561049445006e-05,
      "loss": 10.2187,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 3.5330629348754883,
      "learning_rate": 8.183652875882947e-05,
      "loss": 10.2291,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 3.3741745948791504,
      "learning_rate": 8.082744702320889e-05,
      "loss": 10.0128,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 3.654201030731201,
      "learning_rate": 7.98183652875883e-05,
      "loss": 10.0246,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.1526137097000477,
      "eval_loss": 11.152030944824219,
      "eval_runtime": 0.7071,
      "eval_samples_per_second": 677.426,
      "eval_steps_per_second": 7.071,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 3.711669445037842,
      "learning_rate": 7.880928355196771e-05,
      "loss": 10.0486,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 3.6666271686553955,
      "learning_rate": 7.780020181634713e-05,
      "loss": 10.0912,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 3.9761109352111816,
      "learning_rate": 7.679112008072655e-05,
      "loss": 10.059,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 4.273479461669922,
      "learning_rate": 7.578203834510595e-05,
      "loss": 9.8307,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 4.344827651977539,
      "learning_rate": 7.477295660948537e-05,
      "loss": 9.8636,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 4.09625768661499,
      "learning_rate": 7.376387487386479e-05,
      "loss": 9.9045,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 4.540858745574951,
      "learning_rate": 7.27547931382442e-05,
      "loss": 9.9167,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 4.661898136138916,
      "learning_rate": 7.174571140262362e-05,
      "loss": 9.8152,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 4.3805413246154785,
      "learning_rate": 7.073662966700304e-05,
      "loss": 9.637,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 5.069484710693359,
      "learning_rate": 6.972754793138244e-05,
      "loss": 9.6558,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 4.9267377853393555,
      "learning_rate": 6.871846619576186e-05,
      "loss": 9.6887,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 5.0347185134887695,
      "learning_rate": 6.770938446014128e-05,
      "loss": 9.7129,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 5.755176067352295,
      "learning_rate": 6.670030272452068e-05,
      "loss": 9.5086,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 6.077139377593994,
      "learning_rate": 6.56912209889001e-05,
      "loss": 9.3825,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 5.781816005706787,
      "learning_rate": 6.468213925327952e-05,
      "loss": 9.4355,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 5.980619430541992,
      "learning_rate": 6.367305751765893e-05,
      "loss": 9.4479,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 5.7310028076171875,
      "learning_rate": 6.266397578203835e-05,
      "loss": 9.4925,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 6.134041786193848,
      "learning_rate": 6.165489404641777e-05,
      "loss": 9.1644,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 6.186347961425781,
      "learning_rate": 6.064581231079718e-05,
      "loss": 9.1214,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 6.692824840545654,
      "learning_rate": 5.963673057517659e-05,
      "loss": 9.1704,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.1528667767299997,
      "eval_loss": 11.740485191345215,
      "eval_runtime": 0.7083,
      "eval_samples_per_second": 676.273,
      "eval_steps_per_second": 7.059,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 6.976140022277832,
      "learning_rate": 5.8627648839556e-05,
      "loss": 9.2022,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 6.846307754516602,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 9.1976,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 7.347531795501709,
      "learning_rate": 5.660948536831484e-05,
      "loss": 8.8159,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 7.434515476226807,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 8.8614,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 7.774038314819336,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 8.9232,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 7.294342517852783,
      "learning_rate": 5.358224016145308e-05,
      "loss": 8.9482,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 7.699012279510498,
      "learning_rate": 5.257315842583249e-05,
      "loss": 8.8241,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 8.599494934082031,
      "learning_rate": 5.15640766902119e-05,
      "loss": 8.574,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 8.204407691955566,
      "learning_rate": 5.055499495459133e-05,
      "loss": 8.6138,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 8.588254928588867,
      "learning_rate": 4.954591321897074e-05,
      "loss": 8.6584,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 8.4804048538208,
      "learning_rate": 4.853683148335015e-05,
      "loss": 8.6803,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 9.133394241333008,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 8.4714,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 9.314265251159668,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 8.3259,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 9.212820053100586,
      "learning_rate": 4.55095862764884e-05,
      "loss": 8.382,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 8.549520492553711,
      "learning_rate": 4.450050454086781e-05,
      "loss": 8.4137,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 9.525304794311523,
      "learning_rate": 4.349142280524723e-05,
      "loss": 8.4491,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 9.197854042053223,
      "learning_rate": 4.248234106962664e-05,
      "loss": 8.1381,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 9.554337501525879,
      "learning_rate": 4.147325933400605e-05,
      "loss": 8.1103,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 9.267251014709473,
      "learning_rate": 4.046417759838547e-05,
      "loss": 8.1396,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 10.400641441345215,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 8.1839,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15055511943478747,
      "eval_loss": 12.560386657714844,
      "eval_runtime": 0.7171,
      "eval_samples_per_second": 667.961,
      "eval_steps_per_second": 6.972,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 9.977014541625977,
      "learning_rate": 3.84460141271443e-05,
      "loss": 8.2094,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 9.805234909057617,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 7.8527,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 10.767175674438477,
      "learning_rate": 3.642785065590313e-05,
      "loss": 7.8971,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 10.366438865661621,
      "learning_rate": 3.541876892028255e-05,
      "loss": 7.9309,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 10.878716468811035,
      "learning_rate": 3.440968718466196e-05,
      "loss": 7.9694,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 9.409741401672363,
      "learning_rate": 3.340060544904137e-05,
      "loss": 7.8826,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 10.080101013183594,
      "learning_rate": 3.239152371342079e-05,
      "loss": 7.6611,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 10.352005004882812,
      "learning_rate": 3.13824419778002e-05,
      "loss": 7.7109,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 10.708700180053711,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 7.751,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 10.8505277633667,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 7.7861,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 10.504780769348145,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 7.6194,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 10.147440910339355,
      "learning_rate": 2.734611503531786e-05,
      "loss": 7.5122,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 12.098567962646484,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 7.5393,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 11.324095726013184,
      "learning_rate": 2.532795156407669e-05,
      "loss": 7.5554,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 11.75081729888916,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 7.5874,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 10.735489845275879,
      "learning_rate": 2.330978809283552e-05,
      "loss": 7.4249,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 12.878035545349121,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 7.3677,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 10.3027982711792,
      "learning_rate": 2.129162462159435e-05,
      "loss": 7.3934,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 11.211211204528809,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 7.417,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 10.59797477722168,
      "learning_rate": 1.927346115035318e-05,
      "loss": 7.439,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.1508957860206914,
      "eval_loss": 13.642802238464355,
      "eval_runtime": 0.7211,
      "eval_samples_per_second": 664.246,
      "eval_steps_per_second": 6.934,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 11.477992057800293,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 7.2468,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 10.462298393249512,
      "learning_rate": 1.725529767911201e-05,
      "loss": 7.2659,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 11.381058692932129,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 7.2813,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 12.398669242858887,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 7.283,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 9.217413902282715,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 7.263,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 9.947029113769531,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 7.151,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 10.395926475524902,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 7.1564,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 11.355154037475586,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 7.1697,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 9.985529899597168,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 7.1781,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 10.420571327209473,
      "learning_rate": 9.182643794147326e-06,
      "loss": 7.1445,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 11.58276081085205,
      "learning_rate": 8.173562058526741e-06,
      "loss": 7.071,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 10.119522094726562,
      "learning_rate": 7.164480322906156e-06,
      "loss": 7.1054,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 10.20256519317627,
      "learning_rate": 6.155398587285571e-06,
      "loss": 7.0796,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 10.59414005279541,
      "learning_rate": 5.146316851664986e-06,
      "loss": 7.0984,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 10.851070404052734,
      "learning_rate": 4.1372351160444e-06,
      "loss": 7.0555,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 10.763017654418945,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 7.0411,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 10.992400169372559,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 7.0502,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 10.790609359741211,
      "learning_rate": 1.109989909182644e-06,
      "loss": 7.0339,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 10.67917251586914,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 7.0328,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 3.058354515764736e+17,
      "train_loss": 9.145212555059759,
      "train_runtime": 12209.163,
      "train_samples_per_second": 468.171,
      "train_steps_per_second": 4.877
    }
  ],
  "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": 3.058354515764736e+17,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}