{
  "best_global_step": 50000,
  "best_metric": 6.1598076820373535,
  "best_model_checkpoint": "distilbert_km_5_v2/checkpoint-50000",
  "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": 3.6239705085754395,
      "learning_rate": 5e-06,
      "loss": 10.8643,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 9.112265586853027,
      "learning_rate": 1e-05,
      "loss": 8.8081,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 9.361543655395508,
      "learning_rate": 1.5e-05,
      "loss": 7.7539,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 8.929161071777344,
      "learning_rate": 2e-05,
      "loss": 7.4084,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 5.102548122406006,
      "learning_rate": 2.5e-05,
      "loss": 7.2304,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 6.74715518951416,
      "learning_rate": 3e-05,
      "loss": 7.0823,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 2.6494035720825195,
      "learning_rate": 3.5e-05,
      "loss": 6.9562,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 4.500717639923096,
      "learning_rate": 4e-05,
      "loss": 6.8548,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 3.333782911300659,
      "learning_rate": 4.5e-05,
      "loss": 6.7755,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 2.0406346321105957,
      "learning_rate": 5e-05,
      "loss": 6.6788,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 2.6579527854919434,
      "learning_rate": 5.500000000000001e-05,
      "loss": 6.6198,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 1.9155195951461792,
      "learning_rate": 6e-05,
      "loss": 6.5878,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 2.0430564880371094,
      "learning_rate": 6.500000000000001e-05,
      "loss": 6.5593,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 2.4071273803710938,
      "learning_rate": 7e-05,
      "loss": 6.5363,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 3.474665880203247,
      "learning_rate": 7.500000000000001e-05,
      "loss": 6.473,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 1.8387290239334106,
      "learning_rate": 8e-05,
      "loss": 6.4553,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 1.6159054040908813,
      "learning_rate": 8.5e-05,
      "loss": 6.4511,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 1.459579348564148,
      "learning_rate": 9e-05,
      "loss": 6.4312,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 2.3029682636260986,
      "learning_rate": 9.5e-05,
      "loss": 6.4139,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 2.19469952583313,
      "learning_rate": 0.0001,
      "loss": 6.3534,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.15103369598486324,
      "eval_loss": 6.31992244720459,
      "eval_runtime": 0.866,
      "eval_samples_per_second": 553.108,
      "eval_steps_per_second": 5.774,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 1.5890544652938843,
      "learning_rate": 9.899091826437942e-05,
      "loss": 6.345,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 4.346758842468262,
      "learning_rate": 9.798183652875883e-05,
      "loss": 6.3315,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 1.4556849002838135,
      "learning_rate": 9.697275479313825e-05,
      "loss": 6.3282,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 1.899580478668213,
      "learning_rate": 9.596367305751767e-05,
      "loss": 6.3036,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 1.6178083419799805,
      "learning_rate": 9.495459132189707e-05,
      "loss": 6.2554,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 1.2845096588134766,
      "learning_rate": 9.394550958627649e-05,
      "loss": 6.2448,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 2.576080799102783,
      "learning_rate": 9.293642785065591e-05,
      "loss": 6.2492,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 1.3754308223724365,
      "learning_rate": 9.192734611503532e-05,
      "loss": 6.237,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 3.0778098106384277,
      "learning_rate": 9.091826437941474e-05,
      "loss": 6.2123,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 1.8809382915496826,
      "learning_rate": 8.990918264379415e-05,
      "loss": 6.1876,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 1.2240134477615356,
      "learning_rate": 8.890010090817356e-05,
      "loss": 6.1805,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 1.9700826406478882,
      "learning_rate": 8.789101917255298e-05,
      "loss": 6.1735,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 1.0418548583984375,
      "learning_rate": 8.68819374369324e-05,
      "loss": 6.1697,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 1.7506479024887085,
      "learning_rate": 8.58728557013118e-05,
      "loss": 6.1395,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 0.9085572361946106,
      "learning_rate": 8.486377396569122e-05,
      "loss": 6.1208,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 1.7142499685287476,
      "learning_rate": 8.385469223007064e-05,
      "loss": 6.1237,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 2.2456912994384766,
      "learning_rate": 8.284561049445006e-05,
      "loss": 6.1165,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 1.1050975322723389,
      "learning_rate": 8.183652875882947e-05,
      "loss": 6.1185,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 0.995062530040741,
      "learning_rate": 8.082744702320889e-05,
      "loss": 6.0826,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 1.0620806217193604,
      "learning_rate": 7.98183652875883e-05,
      "loss": 6.0866,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15325907011981257,
      "eval_loss": 6.24980354309082,
      "eval_runtime": 0.7949,
      "eval_samples_per_second": 602.593,
      "eval_steps_per_second": 6.29,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 2.747081756591797,
      "learning_rate": 7.880928355196771e-05,
      "loss": 6.074,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 1.7315388917922974,
      "learning_rate": 7.780020181634713e-05,
      "loss": 6.0768,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 0.9869686365127563,
      "learning_rate": 7.679112008072655e-05,
      "loss": 6.0646,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 1.1722387075424194,
      "learning_rate": 7.578203834510595e-05,
      "loss": 6.0443,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 1.2412378787994385,
      "learning_rate": 7.477295660948537e-05,
      "loss": 6.0375,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 1.4818612337112427,
      "learning_rate": 7.376387487386479e-05,
      "loss": 6.0324,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 0.8582746982574463,
      "learning_rate": 7.27547931382442e-05,
      "loss": 6.0322,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 1.6660131216049194,
      "learning_rate": 7.174571140262362e-05,
      "loss": 6.0157,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 1.989464282989502,
      "learning_rate": 7.073662966700304e-05,
      "loss": 6.0099,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 1.0022387504577637,
      "learning_rate": 6.972754793138244e-05,
      "loss": 6.0006,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 1.2185399532318115,
      "learning_rate": 6.871846619576186e-05,
      "loss": 6.0002,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 2.3096652030944824,
      "learning_rate": 6.770938446014128e-05,
      "loss": 6.001,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 1.4585367441177368,
      "learning_rate": 6.670030272452068e-05,
      "loss": 5.9834,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 0.8468912243843079,
      "learning_rate": 6.56912209889001e-05,
      "loss": 5.9767,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 1.3908807039260864,
      "learning_rate": 6.468213925327952e-05,
      "loss": 5.971,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 1.800117015838623,
      "learning_rate": 6.367305751765893e-05,
      "loss": 5.9669,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 1.4885984659194946,
      "learning_rate": 6.266397578203835e-05,
      "loss": 5.9635,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 0.7347907423973083,
      "learning_rate": 6.165489404641777e-05,
      "loss": 5.954,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 1.437314510345459,
      "learning_rate": 6.064581231079718e-05,
      "loss": 5.9428,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 0.8958004713058472,
      "learning_rate": 5.963673057517659e-05,
      "loss": 5.9471,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15510535299549486,
      "eval_loss": 6.205569267272949,
      "eval_runtime": 0.8013,
      "eval_samples_per_second": 597.742,
      "eval_steps_per_second": 6.239,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 2.1559407711029053,
      "learning_rate": 5.8627648839556e-05,
      "loss": 5.9424,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 0.7265110015869141,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 5.9402,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 2.1399364471435547,
      "learning_rate": 5.660948536831484e-05,
      "loss": 5.9276,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 3.5693092346191406,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 5.9228,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 2.570362091064453,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 5.9253,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 0.8022028803825378,
      "learning_rate": 5.358224016145308e-05,
      "loss": 5.9203,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 0.7353616952896118,
      "learning_rate": 5.257315842583249e-05,
      "loss": 5.913,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 2.391524314880371,
      "learning_rate": 5.15640766902119e-05,
      "loss": 5.9068,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 2.1767020225524902,
      "learning_rate": 5.055499495459133e-05,
      "loss": 5.9041,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 1.295410394668579,
      "learning_rate": 4.954591321897074e-05,
      "loss": 5.9022,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 0.9406413435935974,
      "learning_rate": 4.853683148335015e-05,
      "loss": 5.9007,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 1.7114624977111816,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 5.893,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 0.9910393357276917,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 5.8903,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 0.7706008553504944,
      "learning_rate": 4.55095862764884e-05,
      "loss": 5.8853,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 1.8005712032318115,
      "learning_rate": 4.450050454086781e-05,
      "loss": 5.8824,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 0.9181882739067078,
      "learning_rate": 4.349142280524723e-05,
      "loss": 5.8824,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 0.7467831373214722,
      "learning_rate": 4.248234106962664e-05,
      "loss": 5.8783,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 0.8850783109664917,
      "learning_rate": 4.147325933400605e-05,
      "loss": 5.8694,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 0.8134591579437256,
      "learning_rate": 4.046417759838547e-05,
      "loss": 5.8727,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 0.8487093448638916,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 5.862,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15302231692273185,
      "eval_loss": 6.215011119842529,
      "eval_runtime": 0.819,
      "eval_samples_per_second": 584.845,
      "eval_steps_per_second": 6.105,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 0.820103645324707,
      "learning_rate": 3.84460141271443e-05,
      "loss": 5.8684,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 0.7368544936180115,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 5.8585,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 1.2730772495269775,
      "learning_rate": 3.642785065590313e-05,
      "loss": 5.8542,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 1.0919069051742554,
      "learning_rate": 3.541876892028255e-05,
      "loss": 5.857,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 0.7412800788879395,
      "learning_rate": 3.440968718466196e-05,
      "loss": 5.8527,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 1.8040186166763306,
      "learning_rate": 3.340060544904137e-05,
      "loss": 5.8497,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 0.7469385266304016,
      "learning_rate": 3.239152371342079e-05,
      "loss": 5.8419,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 1.1077488660812378,
      "learning_rate": 3.13824419778002e-05,
      "loss": 5.8419,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 1.1853009462356567,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 5.8422,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 2.191572427749634,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 5.8459,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 0.7320278286933899,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 5.8397,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 0.7785986065864563,
      "learning_rate": 2.734611503531786e-05,
      "loss": 5.8294,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 0.8866362571716309,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 5.8299,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 1.5244886875152588,
      "learning_rate": 2.532795156407669e-05,
      "loss": 5.8309,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 0.7803938984870911,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 5.8269,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 0.8089988231658936,
      "learning_rate": 2.330978809283552e-05,
      "loss": 5.8238,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 0.7548121809959412,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 5.8203,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 0.7919092178344727,
      "learning_rate": 2.129162462159435e-05,
      "loss": 5.819,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 0.7366911172866821,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 5.8163,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 0.768332302570343,
      "learning_rate": 1.927346115035318e-05,
      "loss": 5.8189,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.15311071859141503,
      "eval_loss": 6.1598076820373535,
      "eval_runtime": 0.8306,
      "eval_samples_per_second": 576.688,
      "eval_steps_per_second": 6.02,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 0.7508776187896729,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 5.8124,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 0.8071050643920898,
      "learning_rate": 1.725529767911201e-05,
      "loss": 5.8136,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 1.8220573663711548,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 5.8131,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 0.8811066746711731,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 5.8105,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 0.7641807198524475,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 5.8103,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 0.7622039318084717,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 5.7994,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 0.7833624482154846,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 5.8041,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 0.7755321860313416,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 5.8056,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 3.2827467918395996,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 5.8017,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 1.9679166078567505,
      "learning_rate": 9.182643794147326e-06,
      "loss": 5.8,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 0.7793216705322266,
      "learning_rate": 8.173562058526741e-06,
      "loss": 5.7998,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 0.7761842608451843,
      "learning_rate": 7.164480322906156e-06,
      "loss": 5.7984,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 0.7610192894935608,
      "learning_rate": 6.155398587285571e-06,
      "loss": 5.7934,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 0.7657565474510193,
      "learning_rate": 5.146316851664986e-06,
      "loss": 5.7973,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 0.7501471042633057,
      "learning_rate": 4.1372351160444e-06,
      "loss": 5.7937,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 0.7807060480117798,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 5.7962,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 0.7652791738510132,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 5.7912,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 0.7461200952529907,
      "learning_rate": 1.109989909182644e-06,
      "loss": 5.7923,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 0.7574649453163147,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 5.7921,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 7.68154255975296e+17,
      "train_loss": 6.137595424443909,
      "train_runtime": 16763.2895,
      "train_samples_per_second": 340.982,
      "train_steps_per_second": 3.552
    }
  ],
  "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": 7.68154255975296e+17,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}