{
  "best_global_step": 30000,
  "best_metric": 7.098018169403076,
  "best_model_checkpoint": "bert_base_km_100_v1/checkpoint-30000",
  "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": 3.002894639968872,
      "learning_rate": 5e-06,
      "loss": 13.7908,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 5.135726451873779,
      "learning_rate": 1e-05,
      "loss": 11.9879,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 10.664654731750488,
      "learning_rate": 1.5e-05,
      "loss": 10.5022,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 11.352895736694336,
      "learning_rate": 2e-05,
      "loss": 9.5351,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 12.367330551147461,
      "learning_rate": 2.5e-05,
      "loss": 8.893,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 13.371609687805176,
      "learning_rate": 3e-05,
      "loss": 8.4803,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 22.131290435791016,
      "learning_rate": 3.5e-05,
      "loss": 8.2377,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 17.044904708862305,
      "learning_rate": 4e-05,
      "loss": 8.0652,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 14.133843421936035,
      "learning_rate": 4.5e-05,
      "loss": 7.9757,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 14.358963012695312,
      "learning_rate": 5e-05,
      "loss": 7.8199,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 5.904665470123291,
      "learning_rate": 5.500000000000001e-05,
      "loss": 7.7312,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 5.751183986663818,
      "learning_rate": 6e-05,
      "loss": 7.7029,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 6.4560112953186035,
      "learning_rate": 6.500000000000001e-05,
      "loss": 7.6498,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 10.558186531066895,
      "learning_rate": 7e-05,
      "loss": 7.6096,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 11.515192985534668,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.5029,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 10.303491592407227,
      "learning_rate": 8e-05,
      "loss": 7.4629,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 8.893576622009277,
      "learning_rate": 8.5e-05,
      "loss": 7.4792,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 7.801995277404785,
      "learning_rate": 9e-05,
      "loss": 7.439,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 5.668314456939697,
      "learning_rate": 9.5e-05,
      "loss": 7.4032,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 6.2519941329956055,
      "learning_rate": 0.0001,
      "loss": 7.2948,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.14900247641837558,
      "eval_loss": 7.526218414306641,
      "eval_runtime": 1.0775,
      "eval_samples_per_second": 444.553,
      "eval_steps_per_second": 4.64,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 4.911835193634033,
      "learning_rate": 9.899091826437942e-05,
      "loss": 7.2972,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 5.0826497077941895,
      "learning_rate": 9.798183652875883e-05,
      "loss": 7.2856,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 7.869071006774902,
      "learning_rate": 9.697275479313825e-05,
      "loss": 7.2638,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 5.1057000160217285,
      "learning_rate": 9.596367305751767e-05,
      "loss": 7.2001,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 4.079736709594727,
      "learning_rate": 9.495459132189707e-05,
      "loss": 7.0994,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 4.135382175445557,
      "learning_rate": 9.394550958627649e-05,
      "loss": 7.1083,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 5.316285610198975,
      "learning_rate": 9.293642785065591e-05,
      "loss": 7.1029,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 4.814183712005615,
      "learning_rate": 9.192734611503532e-05,
      "loss": 7.0834,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 6.13992977142334,
      "learning_rate": 9.091826437941474e-05,
      "loss": 7.0153,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 4.1388630867004395,
      "learning_rate": 8.990918264379415e-05,
      "loss": 6.9587,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 4.303731441497803,
      "learning_rate": 8.890010090817356e-05,
      "loss": 6.959,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 6.334359645843506,
      "learning_rate": 8.789101917255298e-05,
      "loss": 6.9552,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 4.114571571350098,
      "learning_rate": 8.68819374369324e-05,
      "loss": 6.9595,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 5.140443325042725,
      "learning_rate": 8.58728557013118e-05,
      "loss": 6.8579,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 4.210533142089844,
      "learning_rate": 8.486377396569122e-05,
      "loss": 6.8121,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 4.975950717926025,
      "learning_rate": 8.385469223007064e-05,
      "loss": 6.8359,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 5.5863037109375,
      "learning_rate": 8.284561049445006e-05,
      "loss": 6.8422,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 4.225070953369141,
      "learning_rate": 8.183652875882947e-05,
      "loss": 6.8373,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 4.138884544372559,
      "learning_rate": 8.082744702320889e-05,
      "loss": 6.7071,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 4.142307281494141,
      "learning_rate": 7.98183652875883e-05,
      "loss": 6.7127,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15199640842896828,
      "eval_loss": 7.131800174713135,
      "eval_runtime": 1.0413,
      "eval_samples_per_second": 460.005,
      "eval_steps_per_second": 4.802,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 3.5271034240722656,
      "learning_rate": 7.880928355196771e-05,
      "loss": 6.7255,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 4.482149124145508,
      "learning_rate": 7.780020181634713e-05,
      "loss": 6.7317,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 4.684220314025879,
      "learning_rate": 7.679112008072655e-05,
      "loss": 6.7172,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 3.8146228790283203,
      "learning_rate": 7.578203834510595e-05,
      "loss": 6.5957,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 4.040112018585205,
      "learning_rate": 7.477295660948537e-05,
      "loss": 6.6093,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 5.058006286621094,
      "learning_rate": 7.376387487386479e-05,
      "loss": 6.6295,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 5.521398544311523,
      "learning_rate": 7.27547931382442e-05,
      "loss": 6.6277,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 5.516049861907959,
      "learning_rate": 7.174571140262362e-05,
      "loss": 6.5878,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 6.593186855316162,
      "learning_rate": 7.073662966700304e-05,
      "loss": 6.4999,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 5.228586196899414,
      "learning_rate": 6.972754793138244e-05,
      "loss": 6.5132,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 6.407562732696533,
      "learning_rate": 6.871846619576186e-05,
      "loss": 6.525,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 4.208524703979492,
      "learning_rate": 6.770938446014128e-05,
      "loss": 6.5374,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 4.562515735626221,
      "learning_rate": 6.670030272452068e-05,
      "loss": 6.4583,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 4.330069541931152,
      "learning_rate": 6.56912209889001e-05,
      "loss": 6.4155,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 5.040678977966309,
      "learning_rate": 6.468213925327952e-05,
      "loss": 6.4306,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 5.712588787078857,
      "learning_rate": 6.367305751765893e-05,
      "loss": 6.434,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 4.494241714477539,
      "learning_rate": 6.266397578203835e-05,
      "loss": 6.4491,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 4.308427810668945,
      "learning_rate": 6.165489404641777e-05,
      "loss": 6.3521,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 5.474401950836182,
      "learning_rate": 6.064581231079718e-05,
      "loss": 6.3362,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 5.09849739074707,
      "learning_rate": 5.963673057517659e-05,
      "loss": 6.3555,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15393010045610991,
      "eval_loss": 7.098018169403076,
      "eval_runtime": 1.0277,
      "eval_samples_per_second": 466.067,
      "eval_steps_per_second": 4.865,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 5.969018936157227,
      "learning_rate": 5.8627648839556e-05,
      "loss": 6.3577,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 5.244491100311279,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 6.3575,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 6.345074653625488,
      "learning_rate": 5.660948536831484e-05,
      "loss": 6.2705,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 4.351828575134277,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 6.2855,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 4.810791969299316,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 6.2899,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 4.124624252319336,
      "learning_rate": 5.358224016145308e-05,
      "loss": 6.2921,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 3.5357728004455566,
      "learning_rate": 5.257315842583249e-05,
      "loss": 6.2632,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 5.915287494659424,
      "learning_rate": 5.15640766902119e-05,
      "loss": 6.2242,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 4.83486270904541,
      "learning_rate": 5.055499495459133e-05,
      "loss": 6.2293,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 7.130947113037109,
      "learning_rate": 4.954591321897074e-05,
      "loss": 6.2364,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 5.0645751953125,
      "learning_rate": 4.853683148335015e-05,
      "loss": 6.2397,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 5.081307888031006,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 6.2012,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 6.204087257385254,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 6.1852,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 3.782597064971924,
      "learning_rate": 4.55095862764884e-05,
      "loss": 6.1806,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 4.19584846496582,
      "learning_rate": 4.450050454086781e-05,
      "loss": 6.1801,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 6.997094631195068,
      "learning_rate": 4.349142280524723e-05,
      "loss": 6.1836,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 3.930828094482422,
      "learning_rate": 4.248234106962664e-05,
      "loss": 6.1527,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 6.202143669128418,
      "learning_rate": 4.147325933400605e-05,
      "loss": 6.1421,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 4.179339408874512,
      "learning_rate": 4.046417759838547e-05,
      "loss": 6.1481,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 4.812616348266602,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 6.135,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15204104519457218,
      "eval_loss": 7.231070518493652,
      "eval_runtime": 1.023,
      "eval_samples_per_second": 468.253,
      "eval_steps_per_second": 4.888,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 4.862933158874512,
      "learning_rate": 3.84460141271443e-05,
      "loss": 6.1445,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 6.304798126220703,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 6.1078,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 5.20837926864624,
      "learning_rate": 3.642785065590313e-05,
      "loss": 6.107,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 4.82801628112793,
      "learning_rate": 3.541876892028255e-05,
      "loss": 6.1097,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 3.805234909057617,
      "learning_rate": 3.440968718466196e-05,
      "loss": 6.1104,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 6.158802509307861,
      "learning_rate": 3.340060544904137e-05,
      "loss": 6.098,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 3.9957692623138428,
      "learning_rate": 3.239152371342079e-05,
      "loss": 6.0724,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 4.466031074523926,
      "learning_rate": 3.13824419778002e-05,
      "loss": 6.0746,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 3.126889944076538,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 6.0783,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 5.483389854431152,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 6.0729,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 4.574634552001953,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 6.0652,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 3.5171802043914795,
      "learning_rate": 2.734611503531786e-05,
      "loss": 6.0435,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 3.9887149333953857,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 6.0481,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 2.9643571376800537,
      "learning_rate": 2.532795156407669e-05,
      "loss": 6.051,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 2.521474838256836,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 6.0406,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 4.337699890136719,
      "learning_rate": 2.330978809283552e-05,
      "loss": 6.0307,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 3.6067092418670654,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 6.0288,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 2.4788684844970703,
      "learning_rate": 2.129162462159435e-05,
      "loss": 6.0214,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 4.681838035583496,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 6.0191,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 2.167496919631958,
      "learning_rate": 1.927346115035318e-05,
      "loss": 6.02,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.1513163428379174,
      "eval_loss": 7.350063800811768,
      "eval_runtime": 1.0203,
      "eval_samples_per_second": 469.458,
      "eval_steps_per_second": 4.9,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 5.429543495178223,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 6.0045,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 5.106986999511719,
      "learning_rate": 1.725529767911201e-05,
      "loss": 6.0066,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 2.921922206878662,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 6.0007,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 5.90492582321167,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 5.9977,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 1.8845158815383911,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 5.9948,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 1.6476936340332031,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 5.9793,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 3.108468770980835,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 5.9821,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 3.931105136871338,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 5.9845,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 2.8887312412261963,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 5.9789,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 3.0071818828582764,
      "learning_rate": 9.182643794147326e-06,
      "loss": 5.9757,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 2.399688243865967,
      "learning_rate": 8.173562058526741e-06,
      "loss": 5.9704,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 4.868059158325195,
      "learning_rate": 7.164480322906156e-06,
      "loss": 5.9694,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 3.1572744846343994,
      "learning_rate": 6.155398587285571e-06,
      "loss": 5.9632,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 3.1717700958251953,
      "learning_rate": 5.146316851664986e-06,
      "loss": 5.9649,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 3.5136799812316895,
      "learning_rate": 4.1372351160444e-06,
      "loss": 5.9587,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 1.139844298362732,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 5.9566,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 3.28973126411438,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 5.953,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 0.9112282991409302,
      "learning_rate": 1.109989909182644e-06,
      "loss": 5.9528,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 0.9846378564834595,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 5.9512,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 1.5161929390646784e+18,
      "train_loss": 6.7256628781822325,
      "train_runtime": 24874.6527,
      "train_samples_per_second": 229.791,
      "train_steps_per_second": 2.394
    }
  ],
  "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
}