{
  "best_global_step": 20000,
  "best_metric": 6.724239349365234,
  "best_model_checkpoint": "distilbert_km_20_v1/checkpoint-20000",
  "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": 2.979879856109619,
      "learning_rate": 5e-06,
      "loss": 12.2778,
      "step": 500
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 2.8630168437957764,
      "learning_rate": 1e-05,
      "loss": 10.3552,
      "step": 1000
    },
    {
      "epoch": 0.6297229219143576,
      "grad_norm": 20.070817947387695,
      "learning_rate": 1.5e-05,
      "loss": 8.7283,
      "step": 1500
    },
    {
      "epoch": 0.8396305625524769,
      "grad_norm": 19.459434509277344,
      "learning_rate": 2e-05,
      "loss": 8.069,
      "step": 2000
    },
    {
      "epoch": 1.0495382031905962,
      "grad_norm": 8.98868465423584,
      "learning_rate": 2.5e-05,
      "loss": 7.7697,
      "step": 2500
    },
    {
      "epoch": 1.2594458438287153,
      "grad_norm": 12.602555274963379,
      "learning_rate": 3e-05,
      "loss": 7.5799,
      "step": 3000
    },
    {
      "epoch": 1.4693534844668346,
      "grad_norm": 13.469198226928711,
      "learning_rate": 3.5e-05,
      "loss": 7.4587,
      "step": 3500
    },
    {
      "epoch": 1.6792611251049538,
      "grad_norm": 12.865194320678711,
      "learning_rate": 4e-05,
      "loss": 7.3759,
      "step": 4000
    },
    {
      "epoch": 1.8891687657430731,
      "grad_norm": 7.189900875091553,
      "learning_rate": 4.5e-05,
      "loss": 7.2546,
      "step": 4500
    },
    {
      "epoch": 2.0990764063811924,
      "grad_norm": 10.347587585449219,
      "learning_rate": 5e-05,
      "loss": 7.1411,
      "step": 5000
    },
    {
      "epoch": 2.3089840470193117,
      "grad_norm": 6.612061023712158,
      "learning_rate": 5.500000000000001e-05,
      "loss": 7.0627,
      "step": 5500
    },
    {
      "epoch": 2.5188916876574305,
      "grad_norm": 5.6443705558776855,
      "learning_rate": 6e-05,
      "loss": 7.0322,
      "step": 6000
    },
    {
      "epoch": 2.72879932829555,
      "grad_norm": 5.132519245147705,
      "learning_rate": 6.500000000000001e-05,
      "loss": 6.9857,
      "step": 6500
    },
    {
      "epoch": 2.938706968933669,
      "grad_norm": 9.376242637634277,
      "learning_rate": 7e-05,
      "loss": 6.9613,
      "step": 7000
    },
    {
      "epoch": 3.1486146095717884,
      "grad_norm": 6.01677942276001,
      "learning_rate": 7.500000000000001e-05,
      "loss": 6.8843,
      "step": 7500
    },
    {
      "epoch": 3.3585222502099077,
      "grad_norm": 5.246444225311279,
      "learning_rate": 8e-05,
      "loss": 6.8621,
      "step": 8000
    },
    {
      "epoch": 3.568429890848027,
      "grad_norm": 3.637566089630127,
      "learning_rate": 8.5e-05,
      "loss": 6.8555,
      "step": 8500
    },
    {
      "epoch": 3.7783375314861463,
      "grad_norm": 4.890215873718262,
      "learning_rate": 9e-05,
      "loss": 6.8308,
      "step": 9000
    },
    {
      "epoch": 3.988245172124265,
      "grad_norm": 3.280120849609375,
      "learning_rate": 9.5e-05,
      "loss": 6.8196,
      "step": 9500
    },
    {
      "epoch": 4.198152812762385,
      "grad_norm": 4.421185493469238,
      "learning_rate": 0.0001,
      "loss": 6.7273,
      "step": 10000
    },
    {
      "epoch": 4.198152812762385,
      "eval_accuracy": 0.1506441470269067,
      "eval_loss": 6.815770149230957,
      "eval_runtime": 0.819,
      "eval_samples_per_second": 584.825,
      "eval_steps_per_second": 6.105,
      "step": 10000
    },
    {
      "epoch": 4.408060453400504,
      "grad_norm": 2.504589796066284,
      "learning_rate": 9.899091826437942e-05,
      "loss": 6.7267,
      "step": 10500
    },
    {
      "epoch": 4.617968094038623,
      "grad_norm": 3.044358015060425,
      "learning_rate": 9.798183652875883e-05,
      "loss": 6.7188,
      "step": 11000
    },
    {
      "epoch": 4.827875734676742,
      "grad_norm": 2.3556456565856934,
      "learning_rate": 9.697275479313825e-05,
      "loss": 6.7113,
      "step": 11500
    },
    {
      "epoch": 5.037783375314861,
      "grad_norm": 3.3496720790863037,
      "learning_rate": 9.596367305751767e-05,
      "loss": 6.6624,
      "step": 12000
    },
    {
      "epoch": 5.247691015952981,
      "grad_norm": 3.383551597595215,
      "learning_rate": 9.495459132189707e-05,
      "loss": 6.5931,
      "step": 12500
    },
    {
      "epoch": 5.4575986565911,
      "grad_norm": 2.75087308883667,
      "learning_rate": 9.394550958627649e-05,
      "loss": 6.5883,
      "step": 13000
    },
    {
      "epoch": 5.667506297229219,
      "grad_norm": 3.307609796524048,
      "learning_rate": 9.293642785065591e-05,
      "loss": 6.5912,
      "step": 13500
    },
    {
      "epoch": 5.877413937867338,
      "grad_norm": 2.6411995887756348,
      "learning_rate": 9.192734611503532e-05,
      "loss": 6.572,
      "step": 14000
    },
    {
      "epoch": 6.087321578505458,
      "grad_norm": 3.9510626792907715,
      "learning_rate": 9.091826437941474e-05,
      "loss": 6.5285,
      "step": 14500
    },
    {
      "epoch": 6.297229219143577,
      "grad_norm": 2.562877893447876,
      "learning_rate": 8.990918264379415e-05,
      "loss": 6.4779,
      "step": 15000
    },
    {
      "epoch": 6.507136859781696,
      "grad_norm": 2.3623547554016113,
      "learning_rate": 8.890010090817356e-05,
      "loss": 6.4787,
      "step": 15500
    },
    {
      "epoch": 6.717044500419815,
      "grad_norm": 3.4063587188720703,
      "learning_rate": 8.789101917255298e-05,
      "loss": 6.4753,
      "step": 16000
    },
    {
      "epoch": 6.926952141057934,
      "grad_norm": 2.640484571456909,
      "learning_rate": 8.68819374369324e-05,
      "loss": 6.4748,
      "step": 16500
    },
    {
      "epoch": 7.136859781696054,
      "grad_norm": 2.721788167953491,
      "learning_rate": 8.58728557013118e-05,
      "loss": 6.4075,
      "step": 17000
    },
    {
      "epoch": 7.346767422334173,
      "grad_norm": 3.192110538482666,
      "learning_rate": 8.486377396569122e-05,
      "loss": 6.3868,
      "step": 17500
    },
    {
      "epoch": 7.5566750629722925,
      "grad_norm": 3.227266550064087,
      "learning_rate": 8.385469223007064e-05,
      "loss": 6.3922,
      "step": 18000
    },
    {
      "epoch": 7.766582703610411,
      "grad_norm": 3.3941075801849365,
      "learning_rate": 8.284561049445006e-05,
      "loss": 6.3962,
      "step": 18500
    },
    {
      "epoch": 7.97649034424853,
      "grad_norm": 2.9742696285247803,
      "learning_rate": 8.183652875882947e-05,
      "loss": 6.3993,
      "step": 19000
    },
    {
      "epoch": 8.18639798488665,
      "grad_norm": 1.6265788078308105,
      "learning_rate": 8.082744702320889e-05,
      "loss": 6.3158,
      "step": 19500
    },
    {
      "epoch": 8.39630562552477,
      "grad_norm": 2.549992799758911,
      "learning_rate": 7.98183652875883e-05,
      "loss": 6.314,
      "step": 20000
    },
    {
      "epoch": 8.39630562552477,
      "eval_accuracy": 0.15297847863295827,
      "eval_loss": 6.724239349365234,
      "eval_runtime": 0.7975,
      "eval_samples_per_second": 600.596,
      "eval_steps_per_second": 6.269,
      "step": 20000
    },
    {
      "epoch": 8.606213266162888,
      "grad_norm": 4.083359718322754,
      "learning_rate": 7.880928355196771e-05,
      "loss": 6.3246,
      "step": 20500
    },
    {
      "epoch": 8.816120906801007,
      "grad_norm": 2.532240390777588,
      "learning_rate": 7.780020181634713e-05,
      "loss": 6.3183,
      "step": 21000
    },
    {
      "epoch": 9.026028547439127,
      "grad_norm": 2.9815914630889893,
      "learning_rate": 7.679112008072655e-05,
      "loss": 6.3116,
      "step": 21500
    },
    {
      "epoch": 9.235936188077247,
      "grad_norm": 3.675196409225464,
      "learning_rate": 7.578203834510595e-05,
      "loss": 6.2537,
      "step": 22000
    },
    {
      "epoch": 9.445843828715365,
      "grad_norm": 1.865236759185791,
      "learning_rate": 7.477295660948537e-05,
      "loss": 6.2575,
      "step": 22500
    },
    {
      "epoch": 9.655751469353484,
      "grad_norm": 5.006089210510254,
      "learning_rate": 7.376387487386479e-05,
      "loss": 6.2533,
      "step": 23000
    },
    {
      "epoch": 9.865659109991604,
      "grad_norm": 3.2789008617401123,
      "learning_rate": 7.27547931382442e-05,
      "loss": 6.2581,
      "step": 23500
    },
    {
      "epoch": 10.075566750629722,
      "grad_norm": 2.7520272731781006,
      "learning_rate": 7.174571140262362e-05,
      "loss": 6.2313,
      "step": 24000
    },
    {
      "epoch": 10.285474391267842,
      "grad_norm": 3.380290985107422,
      "learning_rate": 7.073662966700304e-05,
      "loss": 6.1987,
      "step": 24500
    },
    {
      "epoch": 10.495382031905962,
      "grad_norm": 2.2631707191467285,
      "learning_rate": 6.972754793138244e-05,
      "loss": 6.2037,
      "step": 25000
    },
    {
      "epoch": 10.705289672544081,
      "grad_norm": 4.062611103057861,
      "learning_rate": 6.871846619576186e-05,
      "loss": 6.2047,
      "step": 25500
    },
    {
      "epoch": 10.9151973131822,
      "grad_norm": 3.57633376121521,
      "learning_rate": 6.770938446014128e-05,
      "loss": 6.208,
      "step": 26000
    },
    {
      "epoch": 11.125104953820319,
      "grad_norm": 2.808443546295166,
      "learning_rate": 6.670030272452068e-05,
      "loss": 6.1745,
      "step": 26500
    },
    {
      "epoch": 11.335012594458439,
      "grad_norm": 2.608346462249756,
      "learning_rate": 6.56912209889001e-05,
      "loss": 6.1553,
      "step": 27000
    },
    {
      "epoch": 11.544920235096557,
      "grad_norm": 2.9710750579833984,
      "learning_rate": 6.468213925327952e-05,
      "loss": 6.1569,
      "step": 27500
    },
    {
      "epoch": 11.754827875734676,
      "grad_norm": 4.0407395362854,
      "learning_rate": 6.367305751765893e-05,
      "loss": 6.1556,
      "step": 28000
    },
    {
      "epoch": 11.964735516372796,
      "grad_norm": 4.5597076416015625,
      "learning_rate": 6.266397578203835e-05,
      "loss": 6.1589,
      "step": 28500
    },
    {
      "epoch": 12.174643157010916,
      "grad_norm": 3.4839115142822266,
      "learning_rate": 6.165489404641777e-05,
      "loss": 6.1252,
      "step": 29000
    },
    {
      "epoch": 12.384550797649034,
      "grad_norm": 3.5713751316070557,
      "learning_rate": 6.064581231079718e-05,
      "loss": 6.1147,
      "step": 29500
    },
    {
      "epoch": 12.594458438287154,
      "grad_norm": 3.418360710144043,
      "learning_rate": 5.963673057517659e-05,
      "loss": 6.1244,
      "step": 30000
    },
    {
      "epoch": 12.594458438287154,
      "eval_accuracy": 0.15334247418641744,
      "eval_loss": 6.790299892425537,
      "eval_runtime": 0.8132,
      "eval_samples_per_second": 589.062,
      "eval_steps_per_second": 6.149,
      "step": 30000
    },
    {
      "epoch": 12.804366078925273,
      "grad_norm": 2.959900140762329,
      "learning_rate": 5.8627648839556e-05,
      "loss": 6.1135,
      "step": 30500
    },
    {
      "epoch": 13.014273719563391,
      "grad_norm": 2.8760225772857666,
      "learning_rate": 5.7618567103935416e-05,
      "loss": 6.1178,
      "step": 31000
    },
    {
      "epoch": 13.224181360201511,
      "grad_norm": 1.8898249864578247,
      "learning_rate": 5.660948536831484e-05,
      "loss": 6.0845,
      "step": 31500
    },
    {
      "epoch": 13.43408900083963,
      "grad_norm": 1.2864826917648315,
      "learning_rate": 5.5600403632694254e-05,
      "loss": 6.0808,
      "step": 32000
    },
    {
      "epoch": 13.64399664147775,
      "grad_norm": 1.7948169708251953,
      "learning_rate": 5.4591321897073666e-05,
      "loss": 6.0931,
      "step": 32500
    },
    {
      "epoch": 13.853904282115868,
      "grad_norm": 2.9857394695281982,
      "learning_rate": 5.358224016145308e-05,
      "loss": 6.0859,
      "step": 33000
    },
    {
      "epoch": 14.063811922753988,
      "grad_norm": 3.7488107681274414,
      "learning_rate": 5.257315842583249e-05,
      "loss": 6.074,
      "step": 33500
    },
    {
      "epoch": 14.273719563392108,
      "grad_norm": 2.5495424270629883,
      "learning_rate": 5.15640766902119e-05,
      "loss": 6.0556,
      "step": 34000
    },
    {
      "epoch": 14.483627204030226,
      "grad_norm": 2.880817413330078,
      "learning_rate": 5.055499495459133e-05,
      "loss": 6.056,
      "step": 34500
    },
    {
      "epoch": 14.693534844668346,
      "grad_norm": 3.28692626953125,
      "learning_rate": 4.954591321897074e-05,
      "loss": 6.0569,
      "step": 35000
    },
    {
      "epoch": 14.903442485306465,
      "grad_norm": 3.140390157699585,
      "learning_rate": 4.853683148335015e-05,
      "loss": 6.0584,
      "step": 35500
    },
    {
      "epoch": 15.113350125944585,
      "grad_norm": 2.4942727088928223,
      "learning_rate": 4.7527749747729566e-05,
      "loss": 6.0405,
      "step": 36000
    },
    {
      "epoch": 15.323257766582703,
      "grad_norm": 2.881721258163452,
      "learning_rate": 4.6518668012108985e-05,
      "loss": 6.0333,
      "step": 36500
    },
    {
      "epoch": 15.533165407220823,
      "grad_norm": 2.832490921020508,
      "learning_rate": 4.55095862764884e-05,
      "loss": 6.0298,
      "step": 37000
    },
    {
      "epoch": 15.743073047858942,
      "grad_norm": 2.047809362411499,
      "learning_rate": 4.450050454086781e-05,
      "loss": 6.0302,
      "step": 37500
    },
    {
      "epoch": 15.95298068849706,
      "grad_norm": 3.266771078109741,
      "learning_rate": 4.349142280524723e-05,
      "loss": 6.0291,
      "step": 38000
    },
    {
      "epoch": 16.162888329135182,
      "grad_norm": 3.3096954822540283,
      "learning_rate": 4.248234106962664e-05,
      "loss": 6.0135,
      "step": 38500
    },
    {
      "epoch": 16.3727959697733,
      "grad_norm": 1.3869737386703491,
      "learning_rate": 4.147325933400605e-05,
      "loss": 6.0074,
      "step": 39000
    },
    {
      "epoch": 16.582703610411418,
      "grad_norm": 2.332829475402832,
      "learning_rate": 4.046417759838547e-05,
      "loss": 6.0114,
      "step": 39500
    },
    {
      "epoch": 16.79261125104954,
      "grad_norm": 4.7054338455200195,
      "learning_rate": 3.9455095862764884e-05,
      "loss": 6.0033,
      "step": 40000
    },
    {
      "epoch": 16.79261125104954,
      "eval_accuracy": 0.15190086351912077,
      "eval_loss": 6.952190399169922,
      "eval_runtime": 0.797,
      "eval_samples_per_second": 601.001,
      "eval_steps_per_second": 6.273,
      "step": 40000
    },
    {
      "epoch": 17.002518891687657,
      "grad_norm": 2.9552462100982666,
      "learning_rate": 3.84460141271443e-05,
      "loss": 6.0056,
      "step": 40500
    },
    {
      "epoch": 17.212426532325775,
      "grad_norm": 1.4525129795074463,
      "learning_rate": 3.7436932391523715e-05,
      "loss": 5.9887,
      "step": 41000
    },
    {
      "epoch": 17.422334172963897,
      "grad_norm": 3.132192850112915,
      "learning_rate": 3.642785065590313e-05,
      "loss": 5.9865,
      "step": 41500
    },
    {
      "epoch": 17.632241813602015,
      "grad_norm": 2.6738736629486084,
      "learning_rate": 3.541876892028255e-05,
      "loss": 5.9882,
      "step": 42000
    },
    {
      "epoch": 17.842149454240133,
      "grad_norm": 2.3155324459075928,
      "learning_rate": 3.440968718466196e-05,
      "loss": 5.9855,
      "step": 42500
    },
    {
      "epoch": 18.052057094878254,
      "grad_norm": 2.224963903427124,
      "learning_rate": 3.340060544904137e-05,
      "loss": 5.9807,
      "step": 43000
    },
    {
      "epoch": 18.261964735516372,
      "grad_norm": 1.8887211084365845,
      "learning_rate": 3.239152371342079e-05,
      "loss": 5.9685,
      "step": 43500
    },
    {
      "epoch": 18.471872376154494,
      "grad_norm": 4.511129856109619,
      "learning_rate": 3.13824419778002e-05,
      "loss": 5.9687,
      "step": 44000
    },
    {
      "epoch": 18.68178001679261,
      "grad_norm": 4.113503456115723,
      "learning_rate": 3.0373360242179615e-05,
      "loss": 5.971,
      "step": 44500
    },
    {
      "epoch": 18.89168765743073,
      "grad_norm": 2.4949326515197754,
      "learning_rate": 2.9364278506559034e-05,
      "loss": 5.9703,
      "step": 45000
    },
    {
      "epoch": 19.10159529806885,
      "grad_norm": 1.3216335773468018,
      "learning_rate": 2.8355196770938446e-05,
      "loss": 5.966,
      "step": 45500
    },
    {
      "epoch": 19.31150293870697,
      "grad_norm": 0.9572254419326782,
      "learning_rate": 2.734611503531786e-05,
      "loss": 5.9499,
      "step": 46000
    },
    {
      "epoch": 19.521410579345087,
      "grad_norm": 3.608302354812622,
      "learning_rate": 2.6337033299697278e-05,
      "loss": 5.9516,
      "step": 46500
    },
    {
      "epoch": 19.73131821998321,
      "grad_norm": 1.6361244916915894,
      "learning_rate": 2.532795156407669e-05,
      "loss": 5.9526,
      "step": 47000
    },
    {
      "epoch": 19.941225860621326,
      "grad_norm": 1.7329849004745483,
      "learning_rate": 2.4318869828456106e-05,
      "loss": 5.9516,
      "step": 47500
    },
    {
      "epoch": 20.151133501259444,
      "grad_norm": 2.2567718029022217,
      "learning_rate": 2.330978809283552e-05,
      "loss": 5.9422,
      "step": 48000
    },
    {
      "epoch": 20.361041141897566,
      "grad_norm": 3.4628493785858154,
      "learning_rate": 2.2300706357214934e-05,
      "loss": 5.9412,
      "step": 48500
    },
    {
      "epoch": 20.570948782535684,
      "grad_norm": 1.9243237972259521,
      "learning_rate": 2.129162462159435e-05,
      "loss": 5.9362,
      "step": 49000
    },
    {
      "epoch": 20.7808564231738,
      "grad_norm": 3.8992137908935547,
      "learning_rate": 2.0282542885973765e-05,
      "loss": 5.9359,
      "step": 49500
    },
    {
      "epoch": 20.990764063811923,
      "grad_norm": 3.216963529586792,
      "learning_rate": 1.927346115035318e-05,
      "loss": 5.9317,
      "step": 50000
    },
    {
      "epoch": 20.990764063811923,
      "eval_accuracy": 0.15229764207811142,
      "eval_loss": 7.097256660461426,
      "eval_runtime": 0.801,
      "eval_samples_per_second": 598.018,
      "eval_steps_per_second": 6.242,
      "step": 50000
    },
    {
      "epoch": 21.20067170445004,
      "grad_norm": 1.906050443649292,
      "learning_rate": 1.8264379414732593e-05,
      "loss": 5.9266,
      "step": 50500
    },
    {
      "epoch": 21.410579345088163,
      "grad_norm": 3.7155673503875732,
      "learning_rate": 1.725529767911201e-05,
      "loss": 5.9268,
      "step": 51000
    },
    {
      "epoch": 21.62048698572628,
      "grad_norm": 3.0590012073516846,
      "learning_rate": 1.6246215943491424e-05,
      "loss": 5.9255,
      "step": 51500
    },
    {
      "epoch": 21.8303946263644,
      "grad_norm": 3.9387123584747314,
      "learning_rate": 1.5237134207870837e-05,
      "loss": 5.923,
      "step": 52000
    },
    {
      "epoch": 22.04030226700252,
      "grad_norm": 3.1659605503082275,
      "learning_rate": 1.4228052472250252e-05,
      "loss": 5.9214,
      "step": 52500
    },
    {
      "epoch": 22.250209907640638,
      "grad_norm": 1.2721869945526123,
      "learning_rate": 1.3218970736629668e-05,
      "loss": 5.9107,
      "step": 53000
    },
    {
      "epoch": 22.460117548278756,
      "grad_norm": 2.527693271636963,
      "learning_rate": 1.2209889001009082e-05,
      "loss": 5.9146,
      "step": 53500
    },
    {
      "epoch": 22.670025188916878,
      "grad_norm": 1.426554799079895,
      "learning_rate": 1.1200807265388496e-05,
      "loss": 5.915,
      "step": 54000
    },
    {
      "epoch": 22.879932829554996,
      "grad_norm": 0.9008957147598267,
      "learning_rate": 1.0191725529767912e-05,
      "loss": 5.9109,
      "step": 54500
    },
    {
      "epoch": 23.089840470193113,
      "grad_norm": 3.173042058944702,
      "learning_rate": 9.182643794147326e-06,
      "loss": 5.9073,
      "step": 55000
    },
    {
      "epoch": 23.299748110831235,
      "grad_norm": 2.263507127761841,
      "learning_rate": 8.173562058526741e-06,
      "loss": 5.9034,
      "step": 55500
    },
    {
      "epoch": 23.509655751469353,
      "grad_norm": 1.3971517086029053,
      "learning_rate": 7.164480322906156e-06,
      "loss": 5.9052,
      "step": 56000
    },
    {
      "epoch": 23.719563392107474,
      "grad_norm": 2.0616908073425293,
      "learning_rate": 6.155398587285571e-06,
      "loss": 5.9011,
      "step": 56500
    },
    {
      "epoch": 23.929471032745592,
      "grad_norm": 1.2195613384246826,
      "learning_rate": 5.146316851664986e-06,
      "loss": 5.9019,
      "step": 57000
    },
    {
      "epoch": 24.13937867338371,
      "grad_norm": 0.8809313178062439,
      "learning_rate": 4.1372351160444e-06,
      "loss": 5.8987,
      "step": 57500
    },
    {
      "epoch": 24.349286314021832,
      "grad_norm": 4.2466864585876465,
      "learning_rate": 3.1281533804238145e-06,
      "loss": 5.901,
      "step": 58000
    },
    {
      "epoch": 24.55919395465995,
      "grad_norm": 2.344043254852295,
      "learning_rate": 2.1190716448032293e-06,
      "loss": 5.8948,
      "step": 58500
    },
    {
      "epoch": 24.769101595298068,
      "grad_norm": 2.070852041244507,
      "learning_rate": 1.109989909182644e-06,
      "loss": 5.8955,
      "step": 59000
    },
    {
      "epoch": 24.97900923593619,
      "grad_norm": 0.8052342534065247,
      "learning_rate": 1.0090817356205853e-07,
      "loss": 5.8938,
      "step": 59500
    },
    {
      "epoch": 25.0,
      "step": 59550,
      "total_flos": 7.68356804521728e+17,
      "train_loss": 6.3866113235127715,
      "train_runtime": 16782.5165,
      "train_samples_per_second": 340.591,
      "train_steps_per_second": 3.548
    }
  ],
  "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": 7.68356804521728e+17,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}