{
  "best_metric": 3.6848576068878174,
  "best_model_checkpoint": "distilbert_lda_5_v1/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": 1.7918307781219482,
      "learning_rate": 5e-06,
      "loss": 10.8219,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 1.1442480087280273,
      "learning_rate": 1e-05,
      "loss": 9.0324,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 0.8822475671768188,
      "learning_rate": 1.5e-05,
      "loss": 8.5445,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 0.8581770658493042,
      "learning_rate": 2e-05,
      "loss": 8.3881,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 1.1691675186157227,
      "learning_rate": 2.5e-05,
      "loss": 8.2765,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 1.021052598953247,
      "learning_rate": 3e-05,
      "loss": 8.1775,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 0.9424431324005127,
      "learning_rate": 3.5e-05,
      "loss": 8.0997,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 0.9539915919303894,
      "learning_rate": 4e-05,
      "loss": 8.0423,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 1.213653326034546,
      "learning_rate": 4.5e-05,
      "loss": 7.9921,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 1.0332245826721191,
      "learning_rate": 5e-05,
      "loss": 7.9452,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 1.3403757810592651,
      "learning_rate": 5.500000000000001e-05,
      "loss": 7.9061,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 1.1255860328674316,
      "learning_rate": 6e-05,
      "loss": 7.8715,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 0.9401794672012329,
      "learning_rate": 6.500000000000001e-05,
      "loss": 7.8389,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 1.2805452346801758,
      "learning_rate": 7e-05,
      "loss": 7.8111,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 0.7816216349601746,
      "learning_rate": 7.500000000000001e-05,
      "loss": 7.7849,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 1.032690167427063,
      "learning_rate": 8e-05,
      "loss": 7.7636,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 0.8186590075492859,
      "learning_rate": 8.5e-05,
      "loss": 7.7477,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 1.407650113105774,
      "learning_rate": 9e-05,
      "loss": 7.7221,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 0.9254636764526367,
      "learning_rate": 9.5e-05,
      "loss": 7.7024,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 0.9009159803390503,
      "learning_rate": 0.0001,
      "loss": 7.6763,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.15217451793316453,
      "eval_loss": 7.603443622589111,
      "eval_runtime": 1.2926,
      "eval_samples_per_second": 370.579,
      "eval_steps_per_second": 3.868,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 1.137184739112854,
      "learning_rate": 9.899091826437942e-05,
      "loss": 7.6322,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 0.9898539185523987,
      "learning_rate": 9.798183652875883e-05,
      "loss": 7.5622,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 0.976759672164917,
      "learning_rate": 9.697275479313825e-05,
      "loss": 7.5279,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 1.132392168045044,
      "learning_rate": 9.596367305751767e-05,
      "loss": 7.5032,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 1.0882823467254639,
      "learning_rate": 9.495459132189707e-05,
      "loss": 7.4787,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 0.774067759513855,
      "learning_rate": 9.394550958627649e-05,
      "loss": 7.4645,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 1.0780774354934692,
      "learning_rate": 9.293642785065591e-05,
      "loss": 7.4589,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 0.7974427342414856,
      "learning_rate": 9.192734611503532e-05,
      "loss": 7.4434,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 1.0667096376419067,
      "learning_rate": 9.091826437941474e-05,
      "loss": 7.4306,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 0.9508041143417358,
      "learning_rate": 8.990918264379415e-05,
      "loss": 7.4194,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 1.1196380853652954,
      "learning_rate": 8.890010090817356e-05,
      "loss": 7.4091,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 0.9754195809364319,
      "learning_rate": 8.789101917255298e-05,
      "loss": 7.4017,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 0.9088879227638245,
      "learning_rate": 8.68819374369324e-05,
      "loss": 7.3935,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 0.926615297794342,
      "learning_rate": 8.58728557013118e-05,
      "loss": 7.3779,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 1.0158772468566895,
      "learning_rate": 8.486377396569122e-05,
      "loss": 7.3686,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 1.0636355876922607,
      "learning_rate": 8.385469223007064e-05,
      "loss": 7.3693,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 0.9028527140617371,
      "learning_rate": 8.284561049445006e-05,
      "loss": 7.3613,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 0.8352234363555908,
      "learning_rate": 8.183652875882947e-05,
      "loss": 7.3537,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 1.1861456632614136,
      "learning_rate": 8.082744702320889e-05,
      "loss": 7.292,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 1.3879952430725098,
      "learning_rate": 7.98183652875883e-05,
      "loss": 6.8215,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.26527119167204466,
      "eval_loss": 6.3711256980896,
      "eval_runtime": 1.2847,
      "eval_samples_per_second": 372.86,
      "eval_steps_per_second": 3.892,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 1.4695826768875122,
      "learning_rate": 7.880928355196771e-05,
      "loss": 6.2123,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 1.40931236743927,
      "learning_rate": 7.780020181634713e-05,
      "loss": 5.6834,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 1.4449570178985596,
      "learning_rate": 7.679112008072655e-05,
      "loss": 5.3505,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 1.3005647659301758,
      "learning_rate": 7.578203834510595e-05,
      "loss": 5.1007,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 1.3084704875946045,
      "learning_rate": 7.477295660948537e-05,
      "loss": 4.9223,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 1.312973976135254,
      "learning_rate": 7.376387487386479e-05,
      "loss": 4.8019,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 1.4718126058578491,
      "learning_rate": 7.27547931382442e-05,
      "loss": 4.7063,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 1.281914472579956,
      "learning_rate": 7.174571140262362e-05,
      "loss": 4.6258,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 1.484652042388916,
      "learning_rate": 7.073662966700304e-05,
      "loss": 4.5622,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 1.3344671726226807,
      "learning_rate": 6.972754793138244e-05,
      "loss": 4.5007,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 1.456946611404419,
      "learning_rate": 6.871846619576186e-05,
      "loss": 4.4562,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 1.3045765161514282,
      "learning_rate": 6.770938446014128e-05,
      "loss": 4.4135,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 1.356879711151123,
      "learning_rate": 6.670030272452068e-05,
      "loss": 4.3659,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 1.2806565761566162,
      "learning_rate": 6.56912209889001e-05,
      "loss": 4.3283,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 1.4152148962020874,
      "learning_rate": 6.468213925327952e-05,
      "loss": 4.2935,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 1.3798558712005615,
      "learning_rate": 6.367305751765893e-05,
      "loss": 4.2654,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 1.2828043699264526,
      "learning_rate": 6.266397578203835e-05,
      "loss": 4.2388,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 1.5551649332046509,
      "learning_rate": 6.165489404641777e-05,
      "loss": 4.2116,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 1.4031449556350708,
      "learning_rate": 6.064581231079718e-05,
      "loss": 4.1827,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 1.3126291036605835,
      "learning_rate": 5.963673057517659e-05,
      "loss": 4.1639,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.5321095783081959,
      "eval_loss": 4.053627967834473,
      "eval_runtime": 1.3197,
      "eval_samples_per_second": 362.949,
      "eval_steps_per_second": 3.789,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 1.310651421546936,
      "learning_rate": 5.8627648839556e-05,
      "loss": 4.1412,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 1.379449486732483,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 4.1257,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 1.3750325441360474,
      "learning_rate": 5.660948536831484e-05,
      "loss": 4.1018,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 1.297393560409546,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 4.0827,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 1.3493528366088867,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 4.0687,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 1.287725567817688,
      "learning_rate": 5.358224016145308e-05,
      "loss": 4.0513,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 1.3341923952102661,
      "learning_rate": 5.257315842583249e-05,
      "loss": 4.034,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 1.4937100410461426,
      "learning_rate": 5.15640766902119e-05,
      "loss": 4.0162,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 1.3979895114898682,
      "learning_rate": 5.055499495459133e-05,
      "loss": 4.0053,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 1.38764226436615,
      "learning_rate": 4.954591321897074e-05,
      "loss": 3.9912,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 1.2655898332595825,
      "learning_rate": 4.853683148335015e-05,
      "loss": 3.9822,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 1.3540881872177124,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 3.9655,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 1.3853086233139038,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 3.9519,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 1.2957534790039062,
      "learning_rate": 4.55095862764884e-05,
      "loss": 3.9399,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 1.384169340133667,
      "learning_rate": 4.450050454086781e-05,
      "loss": 3.934,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 1.3049677610397339,
      "learning_rate": 4.349142280524723e-05,
      "loss": 3.9246,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 1.2977432012557983,
      "learning_rate": 4.248234106962664e-05,
      "loss": 3.9133,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 1.291612148284912,
      "learning_rate": 4.147325933400605e-05,
      "loss": 3.8995,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 1.2773422002792358,
      "learning_rate": 4.046417759838547e-05,
      "loss": 3.8924,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 1.261099100112915,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 3.88,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.5682684759448245,
      "eval_loss": 3.779179573059082,
      "eval_runtime": 1.291,
      "eval_samples_per_second": 371.023,
      "eval_steps_per_second": 3.873,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 1.27846097946167,
      "learning_rate": 3.84460141271443e-05,
      "loss": 3.8766,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 1.2726914882659912,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 3.8622,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 1.480125904083252,
      "learning_rate": 3.642785065590313e-05,
      "loss": 3.8538,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 1.3478950262069702,
      "learning_rate": 3.541876892028255e-05,
      "loss": 3.8525,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 1.432916522026062,
      "learning_rate": 3.440968718466196e-05,
      "loss": 3.8426,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 1.3933850526809692,
      "learning_rate": 3.340060544904137e-05,
      "loss": 3.8333,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 1.2548130750656128,
      "learning_rate": 3.239152371342079e-05,
      "loss": 3.8229,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 1.3895797729492188,
      "learning_rate": 3.13824419778002e-05,
      "loss": 3.8216,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 1.3689067363739014,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 3.8149,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 1.3041462898254395,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 3.8147,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 1.2991325855255127,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 3.8014,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 1.3189241886138916,
      "learning_rate": 2.734611503531786e-05,
      "loss": 3.7886,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 1.3324452638626099,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 3.7847,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 1.344330906867981,
      "learning_rate": 2.532795156407669e-05,
      "loss": 3.7806,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 1.4348926544189453,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 3.7796,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 1.337296962738037,
      "learning_rate": 2.330978809283552e-05,
      "loss": 3.7701,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 1.3380999565124512,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 3.7671,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 1.416075348854065,
      "learning_rate": 2.129162462159435e-05,
      "loss": 3.7604,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 1.33714759349823,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 3.7566,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 1.4324113130569458,
      "learning_rate": 1.927346115035318e-05,
      "loss": 3.7563,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.5794431827739928,
      "eval_loss": 3.6848576068878174,
      "eval_runtime": 1.2987,
      "eval_samples_per_second": 368.82,
      "eval_steps_per_second": 3.85,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 1.3554551601409912,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 3.7431,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 1.3318324089050293,
      "learning_rate": 1.725529767911201e-05,
      "loss": 3.7476,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 1.3750087022781372,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 3.7398,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 1.379205346107483,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 3.7376,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 1.3981910943984985,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 3.7341,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 1.3243833780288696,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 3.7255,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 1.3958662748336792,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 3.7234,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 1.3633182048797607,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 3.7259,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 1.3260027170181274,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 3.7206,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 1.3657246828079224,
      "learning_rate": 9.182643794147326e-06,
      "loss": 3.7169,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 1.2816228866577148,
      "learning_rate": 8.173562058526741e-06,
      "loss": 3.7114,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 1.407158613204956,
      "learning_rate": 7.164480322906156e-06,
      "loss": 3.7092,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 1.3041377067565918,
      "learning_rate": 6.155398587285571e-06,
      "loss": 3.7049,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 1.3433361053466797,
      "learning_rate": 5.146316851664986e-06,
      "loss": 3.7107,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 1.3582652807235718,
      "learning_rate": 4.1372351160444e-06,
      "loss": 3.7058,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 1.3640893697738647,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 3.7061,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 1.2843689918518066,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 3.6981,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 1.3331875801086426,
      "learning_rate": 1.109989909182644e-06,
      "loss": 3.6998,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 1.3424105644226074,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 3.7036,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 7.68154255975296e+17,
      "train_loss": 5.303749319952542,
      "train_runtime": 32819.324,
      "train_samples_per_second": 174.165,
      "train_steps_per_second": 1.814
    }
  ],
  "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
}