{
  "best_global_step": 10000,
  "best_metric": 8.407378196716309,
  "best_model_checkpoint": "distilbert_rand_10_v2/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": 3.4146053791046143,
      "learning_rate": 5e-06,
      "loss": 11.5904,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 2.1660385131835938,
      "learning_rate": 1e-05,
      "loss": 9.8865,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 2.5809595584869385,
      "learning_rate": 1.5e-05,
      "loss": 9.3602,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 1.6309263706207275,
      "learning_rate": 2e-05,
      "loss": 9.2047,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 2.1653664112091064,
      "learning_rate": 2.5e-05,
      "loss": 9.0717,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 2.7581591606140137,
      "learning_rate": 3e-05,
      "loss": 8.9602,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 1.9575462341308594,
      "learning_rate": 3.5e-05,
      "loss": 8.8652,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 2.1996233463287354,
      "learning_rate": 4e-05,
      "loss": 8.7901,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 2.6220545768737793,
      "learning_rate": 4.5e-05,
      "loss": 8.7313,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 2.0743510723114014,
      "learning_rate": 5e-05,
      "loss": 8.6809,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 2.642824649810791,
      "learning_rate": 5.500000000000001e-05,
      "loss": 8.6392,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 2.903501033782959,
      "learning_rate": 6e-05,
      "loss": 8.6022,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 3.285515546798706,
      "learning_rate": 6.500000000000001e-05,
      "loss": 8.5689,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 1.971403956413269,
      "learning_rate": 7e-05,
      "loss": 8.5401,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 3.1255595684051514,
      "learning_rate": 7.500000000000001e-05,
      "loss": 8.5093,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 2.656951904296875,
      "learning_rate": 8e-05,
      "loss": 8.4851,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 3.4468624591827393,
      "learning_rate": 8.5e-05,
      "loss": 8.4695,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 3.1533572673797607,
      "learning_rate": 9e-05,
      "loss": 8.4446,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 2.3316454887390137,
      "learning_rate": 9.5e-05,
      "loss": 8.4269,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 3.0319182872772217,
      "learning_rate": 0.0001,
      "loss": 8.365,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.15081109658031666,
      "eval_loss": 8.407378196716309,
      "eval_runtime": 0.8408,
      "eval_samples_per_second": 569.669,
      "eval_steps_per_second": 5.946,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 2.309774398803711,
      "learning_rate": 9.899091826437942e-05,
      "loss": 8.3594,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 2.7297723293304443,
      "learning_rate": 9.798183652875883e-05,
      "loss": 8.3457,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 3.922558546066284,
      "learning_rate": 9.697275479313825e-05,
      "loss": 8.3465,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 2.4545271396636963,
      "learning_rate": 9.596367305751767e-05,
      "loss": 8.3154,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 3.2359399795532227,
      "learning_rate": 9.495459132189707e-05,
      "loss": 8.2332,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 3.1461598873138428,
      "learning_rate": 9.394550958627649e-05,
      "loss": 8.238,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 3.263474464416504,
      "learning_rate": 9.293642785065591e-05,
      "loss": 8.2416,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 3.8544559478759766,
      "learning_rate": 9.192734611503532e-05,
      "loss": 8.2415,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 3.529215097427368,
      "learning_rate": 9.091826437941474e-05,
      "loss": 8.1915,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 2.7152795791625977,
      "learning_rate": 8.990918264379415e-05,
      "loss": 8.1465,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 3.661522388458252,
      "learning_rate": 8.890010090817356e-05,
      "loss": 8.1528,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 2.550381898880005,
      "learning_rate": 8.789101917255298e-05,
      "loss": 8.1596,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 2.9908108711242676,
      "learning_rate": 8.68819374369324e-05,
      "loss": 8.1649,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 2.929835557937622,
      "learning_rate": 8.58728557013118e-05,
      "loss": 8.0896,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 3.0883374214172363,
      "learning_rate": 8.486377396569122e-05,
      "loss": 8.061,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 3.6443467140197754,
      "learning_rate": 8.385469223007064e-05,
      "loss": 8.0805,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 2.828655481338501,
      "learning_rate": 8.284561049445006e-05,
      "loss": 8.0882,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 2.587986946105957,
      "learning_rate": 8.183652875882947e-05,
      "loss": 8.0905,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 3.1316235065460205,
      "learning_rate": 8.082744702320889e-05,
      "loss": 7.9656,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 2.5518126487731934,
      "learning_rate": 7.98183652875883e-05,
      "loss": 7.9655,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15188417183422656,
      "eval_loss": 8.548937797546387,
      "eval_runtime": 0.8127,
      "eval_samples_per_second": 589.419,
      "eval_steps_per_second": 6.153,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 3.2196760177612305,
      "learning_rate": 7.880928355196771e-05,
      "loss": 7.9753,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 3.6576881408691406,
      "learning_rate": 7.780020181634713e-05,
      "loss": 7.9913,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 4.159181594848633,
      "learning_rate": 7.679112008072655e-05,
      "loss": 7.9617,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 4.127835273742676,
      "learning_rate": 7.578203834510595e-05,
      "loss": 7.7796,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 4.776088237762451,
      "learning_rate": 7.477295660948537e-05,
      "loss": 7.7962,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 4.269143581390381,
      "learning_rate": 7.376387487386479e-05,
      "loss": 7.8227,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 3.852692127227783,
      "learning_rate": 7.27547931382442e-05,
      "loss": 7.8206,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 4.89370584487915,
      "learning_rate": 7.174571140262362e-05,
      "loss": 7.7265,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 4.955141067504883,
      "learning_rate": 7.073662966700304e-05,
      "loss": 7.5545,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 4.927492141723633,
      "learning_rate": 6.972754793138244e-05,
      "loss": 7.5655,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 5.925957202911377,
      "learning_rate": 6.871846619576186e-05,
      "loss": 7.5898,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 5.453761100769043,
      "learning_rate": 6.770938446014128e-05,
      "loss": 7.6113,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 5.880764007568359,
      "learning_rate": 6.670030272452068e-05,
      "loss": 7.4247,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 6.225951671600342,
      "learning_rate": 6.56912209889001e-05,
      "loss": 7.3243,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 5.917329788208008,
      "learning_rate": 6.468213925327952e-05,
      "loss": 7.3475,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 6.238253116607666,
      "learning_rate": 6.367305751765893e-05,
      "loss": 7.3563,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 5.542497634887695,
      "learning_rate": 6.266397578203835e-05,
      "loss": 7.3786,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 6.531023025512695,
      "learning_rate": 6.165489404641777e-05,
      "loss": 7.133,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 6.812910556793213,
      "learning_rate": 6.064581231079718e-05,
      "loss": 7.105,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 6.612903594970703,
      "learning_rate": 5.963673057517659e-05,
      "loss": 7.1358,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15393010045610991,
      "eval_loss": 9.573535919189453,
      "eval_runtime": 0.8016,
      "eval_samples_per_second": 597.572,
      "eval_steps_per_second": 6.238,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 6.361575603485107,
      "learning_rate": 5.8627648839556e-05,
      "loss": 7.1651,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 7.888774394989014,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 7.1605,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 7.795629024505615,
      "learning_rate": 5.660948536831484e-05,
      "loss": 6.8972,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 7.270820140838623,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 6.9282,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 8.208027839660645,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 6.9628,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 7.839036464691162,
      "learning_rate": 5.358224016145308e-05,
      "loss": 6.9704,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 9.733901977539062,
      "learning_rate": 5.257315842583249e-05,
      "loss": 6.8931,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 9.443537712097168,
      "learning_rate": 5.15640766902119e-05,
      "loss": 6.7346,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 6.763957500457764,
      "learning_rate": 5.055499495459133e-05,
      "loss": 6.7597,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 8.699044227600098,
      "learning_rate": 4.954591321897074e-05,
      "loss": 6.7844,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 8.743997573852539,
      "learning_rate": 4.853683148335015e-05,
      "loss": 6.7968,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 7.996423721313477,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 6.6783,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 7.6162238121032715,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 6.5914,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 10.055530548095703,
      "learning_rate": 4.55095862764884e-05,
      "loss": 6.6121,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 5.347414016723633,
      "learning_rate": 4.450050454086781e-05,
      "loss": 6.6377,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 8.751012802124023,
      "learning_rate": 4.349142280524723e-05,
      "loss": 6.6495,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 8.579747200012207,
      "learning_rate": 4.248234106962664e-05,
      "loss": 6.498,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 7.676190376281738,
      "learning_rate": 4.147325933400605e-05,
      "loss": 6.4814,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 9.743263244628906,
      "learning_rate": 4.046417759838547e-05,
      "loss": 6.4815,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 6.231374740600586,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 6.503,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15134013681731523,
      "eval_loss": 10.85237979888916,
      "eval_runtime": 0.8076,
      "eval_samples_per_second": 593.137,
      "eval_steps_per_second": 6.191,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 7.749892234802246,
      "learning_rate": 3.84460141271443e-05,
      "loss": 6.5225,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 7.678645133972168,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 6.3674,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 10.171128273010254,
      "learning_rate": 3.642785065590313e-05,
      "loss": 6.3858,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 6.341461658477783,
      "learning_rate": 3.541876892028255e-05,
      "loss": 6.3952,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 7.1425981521606445,
      "learning_rate": 3.440968718466196e-05,
      "loss": 6.4122,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 5.010819911956787,
      "learning_rate": 3.340060544904137e-05,
      "loss": 6.3795,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 7.978843688964844,
      "learning_rate": 3.239152371342079e-05,
      "loss": 6.3053,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 10.343291282653809,
      "learning_rate": 3.13824419778002e-05,
      "loss": 6.3135,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 9.226387977600098,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 6.3232,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 8.74514389038086,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 6.3412,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 7.375455856323242,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 6.2916,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 6.498550891876221,
      "learning_rate": 2.734611503531786e-05,
      "loss": 6.262,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 6.347827434539795,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 6.2613,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 6.730015754699707,
      "learning_rate": 2.532795156407669e-05,
      "loss": 6.2659,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 9.48201847076416,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 6.2674,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 4.89863395690918,
      "learning_rate": 2.330978809283552e-05,
      "loss": 6.2391,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 6.4890336990356445,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 6.2171,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 6.135959148406982,
      "learning_rate": 2.129162462159435e-05,
      "loss": 6.2152,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 6.25450325012207,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 6.2156,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 4.749207496643066,
      "learning_rate": 1.927346115035318e-05,
      "loss": 6.2241,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.1507556004149494,
      "eval_loss": 11.444902420043945,
      "eval_runtime": 0.8053,
      "eval_samples_per_second": 594.799,
      "eval_steps_per_second": 6.209,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 7.05684757232666,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 6.1818,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 5.781315803527832,
      "learning_rate": 1.725529767911201e-05,
      "loss": 6.1921,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 6.954950332641602,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 6.1811,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 7.798590660095215,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 6.1871,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 5.431859493255615,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 6.1766,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 4.973404884338379,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 6.152,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 6.679101467132568,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 6.1525,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 5.500085353851318,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 6.1571,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 7.6365461349487305,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 6.1471,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 3.036820650100708,
      "learning_rate": 9.182643794147326e-06,
      "loss": 6.1454,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 5.347593307495117,
      "learning_rate": 8.173562058526741e-06,
      "loss": 6.1275,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 5.75042724609375,
      "learning_rate": 7.164480322906156e-06,
      "loss": 6.1373,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 4.797982215881348,
      "learning_rate": 6.155398587285571e-06,
      "loss": 6.1255,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 4.1490583419799805,
      "learning_rate": 5.146316851664986e-06,
      "loss": 6.1323,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 5.225616931915283,
      "learning_rate": 4.1372351160444e-06,
      "loss": 6.1193,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 5.23792028427124,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 6.1238,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 4.848769664764404,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 6.1198,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 6.059590816497803,
      "learning_rate": 1.109989909182644e-06,
      "loss": 6.1163,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 5.657757759094238,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 6.1065,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 7.6822177215744e+17,
      "train_loss": 7.320337596672308,
      "train_runtime": 16714.9526,
      "train_samples_per_second": 341.968,
      "train_steps_per_second": 3.563
    }
  ],
  "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": 7.6822177215744e+17,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}