{
  "best_global_step": 10000,
  "best_metric": 10.05698299407959,
  "best_model_checkpoint": "bert_base_rand_50_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": 2.910057306289673,
      "learning_rate": 5e-06,
      "loss": 13.1533,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 1.9898585081100464,
      "learning_rate": 1e-05,
      "loss": 11.4747,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 2.152155637741089,
      "learning_rate": 1.5e-05,
      "loss": 10.9273,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 2.329932928085327,
      "learning_rate": 2e-05,
      "loss": 10.7736,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 2.404989242553711,
      "learning_rate": 2.5e-05,
      "loss": 10.6558,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 2.301668405532837,
      "learning_rate": 3e-05,
      "loss": 10.5437,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 2.6434061527252197,
      "learning_rate": 3.5e-05,
      "loss": 10.4519,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 2.504730701446533,
      "learning_rate": 4e-05,
      "loss": 10.3824,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 2.0936901569366455,
      "learning_rate": 4.5e-05,
      "loss": 10.3245,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 2.4597043991088867,
      "learning_rate": 5e-05,
      "loss": 10.2748,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 2.6838295459747314,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.2352,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 2.3891937732696533,
      "learning_rate": 6e-05,
      "loss": 10.1982,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 2.45198392868042,
      "learning_rate": 6.500000000000001e-05,
      "loss": 10.1658,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 3.1750247478485107,
      "learning_rate": 7e-05,
      "loss": 10.1385,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 2.406378984451294,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.1111,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 2.5311081409454346,
      "learning_rate": 8e-05,
      "loss": 10.0914,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 2.6217329502105713,
      "learning_rate": 8.5e-05,
      "loss": 10.0769,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 2.82147479057312,
      "learning_rate": 9e-05,
      "loss": 10.0563,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 2.4983294010162354,
      "learning_rate": 9.5e-05,
      "loss": 10.0398,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 3.1900744438171387,
      "learning_rate": 0.0001,
      "loss": 9.9562,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.1504215476223601,
      "eval_loss": 10.05698299407959,
      "eval_runtime": 1.0605,
      "eval_samples_per_second": 451.689,
      "eval_steps_per_second": 4.715,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 2.9458200931549072,
      "learning_rate": 9.899091826437942e-05,
      "loss": 9.9525,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 3.061589241027832,
      "learning_rate": 9.798183652875883e-05,
      "loss": 9.941,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 3.02740216255188,
      "learning_rate": 9.697275479313825e-05,
      "loss": 9.9422,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 3.07222056388855,
      "learning_rate": 9.596367305751767e-05,
      "loss": 9.898,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 3.3902053833007812,
      "learning_rate": 9.495459132189707e-05,
      "loss": 9.7382,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 3.5804977416992188,
      "learning_rate": 9.394550958627649e-05,
      "loss": 9.7568,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 3.2234046459198,
      "learning_rate": 9.293642785065591e-05,
      "loss": 9.7782,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 3.3916475772857666,
      "learning_rate": 9.192734611503532e-05,
      "loss": 9.7865,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 3.336322546005249,
      "learning_rate": 9.091826437941474e-05,
      "loss": 9.6658,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 3.5544092655181885,
      "learning_rate": 8.990918264379415e-05,
      "loss": 9.5483,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 3.418905735015869,
      "learning_rate": 8.890010090817356e-05,
      "loss": 9.5796,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 3.823829174041748,
      "learning_rate": 8.789101917255298e-05,
      "loss": 9.6023,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 3.9409022331237793,
      "learning_rate": 8.68819374369324e-05,
      "loss": 9.6217,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 4.098318099975586,
      "learning_rate": 8.58728557013118e-05,
      "loss": 9.3793,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 4.929503440856934,
      "learning_rate": 8.486377396569122e-05,
      "loss": 9.2799,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 4.504343032836914,
      "learning_rate": 8.385469223007064e-05,
      "loss": 9.3182,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 4.923043727874756,
      "learning_rate": 8.284561049445006e-05,
      "loss": 9.3535,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 4.430391311645508,
      "learning_rate": 8.183652875882947e-05,
      "loss": 9.3713,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 5.640526294708252,
      "learning_rate": 8.082744702320889e-05,
      "loss": 8.9282,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 5.674362659454346,
      "learning_rate": 7.98183652875883e-05,
      "loss": 8.9057,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15295041948427285,
      "eval_loss": 10.687986373901367,
      "eval_runtime": 1.0381,
      "eval_samples_per_second": 461.424,
      "eval_steps_per_second": 4.817,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 6.025655746459961,
      "learning_rate": 7.880928355196771e-05,
      "loss": 8.9315,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 6.160457134246826,
      "learning_rate": 7.780020181634713e-05,
      "loss": 8.9815,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 6.719803333282471,
      "learning_rate": 7.679112008072655e-05,
      "loss": 8.9172,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 5.918151378631592,
      "learning_rate": 7.578203834510595e-05,
      "loss": 8.4531,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 6.931684970855713,
      "learning_rate": 7.477295660948537e-05,
      "loss": 8.4912,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 7.023995876312256,
      "learning_rate": 7.376387487386479e-05,
      "loss": 8.5459,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 7.726203441619873,
      "learning_rate": 7.27547931382442e-05,
      "loss": 8.5581,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 7.165088653564453,
      "learning_rate": 7.174571140262362e-05,
      "loss": 8.394,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 6.688276767730713,
      "learning_rate": 7.073662966700304e-05,
      "loss": 8.1134,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 8.269146919250488,
      "learning_rate": 6.972754793138244e-05,
      "loss": 8.1468,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 8.100911140441895,
      "learning_rate": 6.871846619576186e-05,
      "loss": 8.1843,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 6.64196252822876,
      "learning_rate": 6.770938446014128e-05,
      "loss": 8.2232,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 6.788018226623535,
      "learning_rate": 6.670030272452068e-05,
      "loss": 7.9551,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 8.822239875793457,
      "learning_rate": 6.56912209889001e-05,
      "loss": 7.8074,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 7.363283634185791,
      "learning_rate": 6.468213925327952e-05,
      "loss": 7.8626,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 7.27040958404541,
      "learning_rate": 6.367305751765893e-05,
      "loss": 7.8825,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 8.485837936401367,
      "learning_rate": 6.266397578203835e-05,
      "loss": 7.9275,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 7.935208320617676,
      "learning_rate": 6.165489404641777e-05,
      "loss": 7.5554,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 9.276970863342285,
      "learning_rate": 6.064581231079718e-05,
      "loss": 7.5234,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 7.733733177185059,
      "learning_rate": 5.963673057517659e-05,
      "loss": 7.5834,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15415395808265944,
      "eval_loss": 12.090158462524414,
      "eval_runtime": 1.028,
      "eval_samples_per_second": 465.948,
      "eval_steps_per_second": 4.864,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 6.689446449279785,
      "learning_rate": 5.8627648839556e-05,
      "loss": 7.6097,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 9.101981163024902,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 7.5891,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 9.931775093078613,
      "learning_rate": 5.660948536831484e-05,
      "loss": 7.224,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 10.987419128417969,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 7.2794,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 8.850003242492676,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 7.3255,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 9.087993621826172,
      "learning_rate": 5.358224016145308e-05,
      "loss": 7.3346,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 8.229413986206055,
      "learning_rate": 5.257315842583249e-05,
      "loss": 7.2403,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 9.181028366088867,
      "learning_rate": 5.15640766902119e-05,
      "loss": 7.0142,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 11.603790283203125,
      "learning_rate": 5.055499495459133e-05,
      "loss": 7.0506,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 7.527580738067627,
      "learning_rate": 4.954591321897074e-05,
      "loss": 7.0818,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 9.465856552124023,
      "learning_rate": 4.853683148335015e-05,
      "loss": 7.097,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 8.077656745910645,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 6.938,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 9.453032493591309,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 6.808,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 8.367673873901367,
      "learning_rate": 4.55095862764884e-05,
      "loss": 6.8492,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 10.33227252960205,
      "learning_rate": 4.450050454086781e-05,
      "loss": 6.884,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 9.6149263381958,
      "learning_rate": 4.349142280524723e-05,
      "loss": 6.8992,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 9.623023986816406,
      "learning_rate": 4.248234106962664e-05,
      "loss": 6.6825,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 10.136953353881836,
      "learning_rate": 4.147325933400605e-05,
      "loss": 6.6731,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 7.8549981117248535,
      "learning_rate": 4.046417759838547e-05,
      "loss": 6.6816,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 10.028986930847168,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 6.6925,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15083548278569026,
      "eval_loss": 13.089590072631836,
      "eval_runtime": 1.0293,
      "eval_samples_per_second": 465.376,
      "eval_steps_per_second": 4.858,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 6.354678630828857,
      "learning_rate": 3.84460141271443e-05,
      "loss": 6.7083,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 6.525017738342285,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 6.5198,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 7.60914945602417,
      "learning_rate": 3.642785065590313e-05,
      "loss": 6.5327,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 9.217438697814941,
      "learning_rate": 3.541876892028255e-05,
      "loss": 6.5481,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 6.969649791717529,
      "learning_rate": 3.440968718466196e-05,
      "loss": 6.5782,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 6.439877986907959,
      "learning_rate": 3.340060544904137e-05,
      "loss": 6.5368,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 8.004172325134277,
      "learning_rate": 3.239152371342079e-05,
      "loss": 6.4379,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 8.296880722045898,
      "learning_rate": 3.13824419778002e-05,
      "loss": 6.4548,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 7.450301647186279,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 6.4665,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 8.170196533203125,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 6.4865,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 6.22751522064209,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 6.4313,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 6.186279296875,
      "learning_rate": 2.734611503531786e-05,
      "loss": 6.3868,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 8.941252708435059,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 6.3871,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 9.781423568725586,
      "learning_rate": 2.532795156407669e-05,
      "loss": 6.393,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 8.490645408630371,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 6.394,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 4.097350597381592,
      "learning_rate": 2.330978809283552e-05,
      "loss": 6.36,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 7.565592288970947,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 6.344,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 6.653237342834473,
      "learning_rate": 2.129162462159435e-05,
      "loss": 6.3385,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 6.17768669128418,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 6.3382,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 7.017146587371826,
      "learning_rate": 1.927346115035318e-05,
      "loss": 6.3514,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.15142849132251102,
      "eval_loss": 13.681550025939941,
      "eval_runtime": 1.0348,
      "eval_samples_per_second": 462.869,
      "eval_steps_per_second": 4.832,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 6.599613666534424,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 6.3027,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 7.01460599899292,
      "learning_rate": 1.725529767911201e-05,
      "loss": 6.3129,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 7.102719783782959,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 6.303,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 4.671485424041748,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 6.2972,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 3.865253448486328,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 6.2948,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 5.468708038330078,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 6.2647,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 10.580549240112305,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 6.2631,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 10.577978134155273,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 6.2738,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 5.840587615966797,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 6.2606,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 5.225489139556885,
      "learning_rate": 9.182643794147326e-06,
      "loss": 6.2496,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 7.5391011238098145,
      "learning_rate": 8.173562058526741e-06,
      "loss": 6.2349,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 7.059267520904541,
      "learning_rate": 7.164480322906156e-06,
      "loss": 6.2453,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 6.118034362792969,
      "learning_rate": 6.155398587285571e-06,
      "loss": 6.224,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 5.363215446472168,
      "learning_rate": 5.146316851664986e-06,
      "loss": 6.234,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 7.0721306800842285,
      "learning_rate": 4.1372351160444e-06,
      "loss": 6.216,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 5.451009273529053,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 6.2235,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 5.595957279205322,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 6.2172,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 4.651698589324951,
      "learning_rate": 1.109989909182644e-06,
      "loss": 6.2153,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 5.345389366149902,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 6.2052,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 1.5155177772432384e+18,
      "train_loss": 8.016993000789613,
      "train_runtime": 24845.6888,
      "train_samples_per_second": 230.059,
      "train_steps_per_second": 2.397
    }
  ],
  "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": 1.5155177772432384e+18,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}