{
  "best_metric": 0.9361970057366729,
  "best_model_checkpoint": "deberta-bib-style-classification/checkpoint-61266",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 61266,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.048966800509254726,
      "grad_norm": 0.18245625495910645,
      "learning_rate": 1.9836777331635818e-05,
      "loss": 0.1329,
      "step": 500
    },
    {
      "epoch": 0.09793360101850945,
      "grad_norm": 0.17618948221206665,
      "learning_rate": 1.9673554663271638e-05,
      "loss": 0.0446,
      "step": 1000
    },
    {
      "epoch": 0.14690040152776418,
      "grad_norm": 0.16028529405593872,
      "learning_rate": 1.9510331994907454e-05,
      "loss": 0.0436,
      "step": 1500
    },
    {
      "epoch": 0.1958672020370189,
      "grad_norm": 0.13800546526908875,
      "learning_rate": 1.934710932654327e-05,
      "loss": 0.0382,
      "step": 2000
    },
    {
      "epoch": 0.24483400254627363,
      "grad_norm": 0.1666691154241562,
      "learning_rate": 1.918388665817909e-05,
      "loss": 0.0317,
      "step": 2500
    },
    {
      "epoch": 0.29380080305552836,
      "grad_norm": 0.2547225058078766,
      "learning_rate": 1.9020663989814907e-05,
      "loss": 0.0276,
      "step": 3000
    },
    {
      "epoch": 0.3427676035647831,
      "grad_norm": 0.10508100688457489,
      "learning_rate": 1.8857441321450724e-05,
      "loss": 0.0236,
      "step": 3500
    },
    {
      "epoch": 0.3917344040740378,
      "grad_norm": 0.1274070292711258,
      "learning_rate": 1.8694218653086543e-05,
      "loss": 0.0208,
      "step": 4000
    },
    {
      "epoch": 0.44070120458329254,
      "grad_norm": 0.1652757227420807,
      "learning_rate": 1.853099598472236e-05,
      "loss": 0.0187,
      "step": 4500
    },
    {
      "epoch": 0.48966800509254726,
      "grad_norm": 0.15535283088684082,
      "learning_rate": 1.8367773316358176e-05,
      "loss": 0.0164,
      "step": 5000
    },
    {
      "epoch": 0.538634805601802,
      "grad_norm": 0.1361575722694397,
      "learning_rate": 1.8204550647993996e-05,
      "loss": 0.0151,
      "step": 5500
    },
    {
      "epoch": 0.5876016061110567,
      "grad_norm": 0.14795701205730438,
      "learning_rate": 1.8041327979629813e-05,
      "loss": 0.0141,
      "step": 6000
    },
    {
      "epoch": 0.6365684066203114,
      "grad_norm": 0.24855226278305054,
      "learning_rate": 1.787810531126563e-05,
      "loss": 0.0128,
      "step": 6500
    },
    {
      "epoch": 0.6855352071295662,
      "grad_norm": 0.11990305036306381,
      "learning_rate": 1.771488264290145e-05,
      "loss": 0.0119,
      "step": 7000
    },
    {
      "epoch": 0.7345020076388209,
      "grad_norm": 0.12674401700496674,
      "learning_rate": 1.7551659974537265e-05,
      "loss": 0.0109,
      "step": 7500
    },
    {
      "epoch": 0.7834688081480756,
      "grad_norm": 0.05565750598907471,
      "learning_rate": 1.7388437306173082e-05,
      "loss": 0.0103,
      "step": 8000
    },
    {
      "epoch": 0.8324356086573304,
      "grad_norm": 0.1362127959728241,
      "learning_rate": 1.72252146378089e-05,
      "loss": 0.0097,
      "step": 8500
    },
    {
      "epoch": 0.8814024091665851,
      "grad_norm": 0.1502208560705185,
      "learning_rate": 1.7062318414781447e-05,
      "loss": 0.0096,
      "step": 9000
    },
    {
      "epoch": 0.9303692096758398,
      "grad_norm": 0.1307108849287033,
      "learning_rate": 1.689942219175399e-05,
      "loss": 0.009,
      "step": 9500
    },
    {
      "epoch": 0.9793360101850945,
      "grad_norm": 0.08258962631225586,
      "learning_rate": 1.6736199523389808e-05,
      "loss": 0.0088,
      "step": 10000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7270709032884696,
      "eval_f1": 0.8196123147092359,
      "eval_loss": 0.007612535264343023,
      "eval_roc_auc": 0.8736920143065684,
      "eval_runtime": 56.0999,
      "eval_samples_per_second": 128.467,
      "eval_steps_per_second": 16.061,
      "step": 10211
    },
    {
      "epoch": 1.0283028106943493,
      "grad_norm": 0.15880635380744934,
      "learning_rate": 1.6572976855025628e-05,
      "loss": 0.0086,
      "step": 10500
    },
    {
      "epoch": 1.077269611203604,
      "grad_norm": 0.04505603387951851,
      "learning_rate": 1.6409754186661444e-05,
      "loss": 0.0082,
      "step": 11000
    },
    {
      "epoch": 1.1262364117128587,
      "grad_norm": 0.1436477154493332,
      "learning_rate": 1.624653151829726e-05,
      "loss": 0.0076,
      "step": 11500
    },
    {
      "epoch": 1.1752032122221134,
      "grad_norm": 0.10293476283550262,
      "learning_rate": 1.608330884993308e-05,
      "loss": 0.0074,
      "step": 12000
    },
    {
      "epoch": 1.2241700127313682,
      "grad_norm": 0.12684179842472076,
      "learning_rate": 1.5920086181568897e-05,
      "loss": 0.0076,
      "step": 12500
    },
    {
      "epoch": 1.2731368132406229,
      "grad_norm": 0.09429904818534851,
      "learning_rate": 1.5756863513204713e-05,
      "loss": 0.0073,
      "step": 13000
    },
    {
      "epoch": 1.3221036137498776,
      "grad_norm": 0.24173329770565033,
      "learning_rate": 1.5593640844840533e-05,
      "loss": 0.0068,
      "step": 13500
    },
    {
      "epoch": 1.3710704142591323,
      "grad_norm": 0.15347008407115936,
      "learning_rate": 1.543041817647635e-05,
      "loss": 0.0069,
      "step": 14000
    },
    {
      "epoch": 1.420037214768387,
      "grad_norm": 0.30062130093574524,
      "learning_rate": 1.5267195508112166e-05,
      "loss": 0.0064,
      "step": 14500
    },
    {
      "epoch": 1.4690040152776418,
      "grad_norm": 0.0312146358191967,
      "learning_rate": 1.5103972839747984e-05,
      "loss": 0.0065,
      "step": 15000
    },
    {
      "epoch": 1.5179708157868965,
      "grad_norm": 0.19778664410114288,
      "learning_rate": 1.4941076616720531e-05,
      "loss": 0.0063,
      "step": 15500
    },
    {
      "epoch": 1.5669376162961512,
      "grad_norm": 0.07010342180728912,
      "learning_rate": 1.4778180393693078e-05,
      "loss": 0.0058,
      "step": 16000
    },
    {
      "epoch": 1.615904416805406,
      "grad_norm": 0.11643481999635696,
      "learning_rate": 1.4614957725328896e-05,
      "loss": 0.0058,
      "step": 16500
    },
    {
      "epoch": 1.6648712173146607,
      "grad_norm": 0.14050887525081635,
      "learning_rate": 1.4452061502301439e-05,
      "loss": 0.0059,
      "step": 17000
    },
    {
      "epoch": 1.7138380178239154,
      "grad_norm": 0.09967122972011566,
      "learning_rate": 1.4288838833937257e-05,
      "loss": 0.0053,
      "step": 17500
    },
    {
      "epoch": 1.7628048183331702,
      "grad_norm": 0.06283292174339294,
      "learning_rate": 1.4125616165573075e-05,
      "loss": 0.0057,
      "step": 18000
    },
    {
      "epoch": 1.8117716188424249,
      "grad_norm": 0.04395497962832451,
      "learning_rate": 1.3962393497208892e-05,
      "loss": 0.0051,
      "step": 18500
    },
    {
      "epoch": 1.8607384193516796,
      "grad_norm": 0.15392401814460754,
      "learning_rate": 1.379917082884471e-05,
      "loss": 0.0049,
      "step": 19000
    },
    {
      "epoch": 1.9097052198609343,
      "grad_norm": 0.053341180086135864,
      "learning_rate": 1.3635948160480528e-05,
      "loss": 0.0052,
      "step": 19500
    },
    {
      "epoch": 1.958672020370189,
      "grad_norm": 0.14263851940631866,
      "learning_rate": 1.3472725492116345e-05,
      "loss": 0.005,
      "step": 20000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8507007076453448,
      "eval_f1": 0.8938003106905804,
      "eval_loss": 0.00466541014611721,
      "eval_roc_auc": 0.9387280731428467,
      "eval_runtime": 55.7959,
      "eval_samples_per_second": 129.167,
      "eval_steps_per_second": 16.148,
      "step": 20422
    },
    {
      "epoch": 2.0076388208794436,
      "grad_norm": 0.16177518665790558,
      "learning_rate": 1.3309502823752163e-05,
      "loss": 0.0048,
      "step": 20500
    },
    {
      "epoch": 2.0566056213886985,
      "grad_norm": 0.13520753383636475,
      "learning_rate": 1.314628015538798e-05,
      "loss": 0.0045,
      "step": 21000
    },
    {
      "epoch": 2.105572421897953,
      "grad_norm": 0.09872843325138092,
      "learning_rate": 1.2983057487023797e-05,
      "loss": 0.0043,
      "step": 21500
    },
    {
      "epoch": 2.154539222407208,
      "grad_norm": 0.07923103123903275,
      "learning_rate": 1.2819834818659615e-05,
      "loss": 0.0042,
      "step": 22000
    },
    {
      "epoch": 2.2035060229164625,
      "grad_norm": 0.01526894886046648,
      "learning_rate": 1.2656612150295434e-05,
      "loss": 0.0041,
      "step": 22500
    },
    {
      "epoch": 2.2524728234257174,
      "grad_norm": 0.09783605486154556,
      "learning_rate": 1.249338948193125e-05,
      "loss": 0.0042,
      "step": 23000
    },
    {
      "epoch": 2.301439623934972,
      "grad_norm": 0.12495558708906174,
      "learning_rate": 1.2330819704240527e-05,
      "loss": 0.0042,
      "step": 23500
    },
    {
      "epoch": 2.350406424444227,
      "grad_norm": 0.09078874439001083,
      "learning_rate": 1.2167597035876343e-05,
      "loss": 0.0045,
      "step": 24000
    },
    {
      "epoch": 2.3993732249534814,
      "grad_norm": 0.0656205415725708,
      "learning_rate": 1.2004374367512162e-05,
      "loss": 0.0039,
      "step": 24500
    },
    {
      "epoch": 2.4483400254627363,
      "grad_norm": 0.22209672629833221,
      "learning_rate": 1.184115169914798e-05,
      "loss": 0.0043,
      "step": 25000
    },
    {
      "epoch": 2.497306825971991,
      "grad_norm": 0.4231460988521576,
      "learning_rate": 1.1677929030783796e-05,
      "loss": 0.0042,
      "step": 25500
    },
    {
      "epoch": 2.5462736264812458,
      "grad_norm": 0.0051184347830712795,
      "learning_rate": 1.1514706362419614e-05,
      "loss": 0.0039,
      "step": 26000
    },
    {
      "epoch": 2.5952404269905003,
      "grad_norm": 0.15397199988365173,
      "learning_rate": 1.1351483694055432e-05,
      "loss": 0.0037,
      "step": 26500
    },
    {
      "epoch": 2.6442072274997552,
      "grad_norm": 0.03935805708169937,
      "learning_rate": 1.1188261025691249e-05,
      "loss": 0.0035,
      "step": 27000
    },
    {
      "epoch": 2.6931740280090097,
      "grad_norm": 0.011553222313523293,
      "learning_rate": 1.1025364802663794e-05,
      "loss": 0.0038,
      "step": 27500
    },
    {
      "epoch": 2.7421408285182647,
      "grad_norm": 0.06817249953746796,
      "learning_rate": 1.0862142134299612e-05,
      "loss": 0.0035,
      "step": 28000
    },
    {
      "epoch": 2.791107629027519,
      "grad_norm": 0.003078105626627803,
      "learning_rate": 1.0699245911272159e-05,
      "loss": 0.0036,
      "step": 28500
    },
    {
      "epoch": 2.840074429536774,
      "grad_norm": 0.11958350241184235,
      "learning_rate": 1.0536023242907975e-05,
      "loss": 0.0037,
      "step": 29000
    },
    {
      "epoch": 2.8890412300460286,
      "grad_norm": 0.17206184566020966,
      "learning_rate": 1.0372800574543793e-05,
      "loss": 0.0036,
      "step": 29500
    },
    {
      "epoch": 2.9380080305552836,
      "grad_norm": 0.018106259405612946,
      "learning_rate": 1.0209577906179611e-05,
      "loss": 0.0035,
      "step": 30000
    },
    {
      "epoch": 2.986974831064538,
      "grad_norm": 0.14708341658115387,
      "learning_rate": 1.0046355237815428e-05,
      "loss": 0.0035,
      "step": 30500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8998196198140697,
      "eval_f1": 0.9224077451943314,
      "eval_loss": 0.0033930453937500715,
      "eval_roc_auc": 0.9558131614465735,
      "eval_runtime": 55.6722,
      "eval_samples_per_second": 129.454,
      "eval_steps_per_second": 16.184,
      "step": 30633
    },
    {
      "epoch": 3.035941631573793,
      "grad_norm": 0.03020176850259304,
      "learning_rate": 9.883132569451246e-06,
      "loss": 0.0033,
      "step": 31000
    },
    {
      "epoch": 3.0849084320830475,
      "grad_norm": 0.1869770586490631,
      "learning_rate": 9.720236346423793e-06,
      "loss": 0.0029,
      "step": 31500
    },
    {
      "epoch": 3.1338752325923025,
      "grad_norm": 0.02884034253656864,
      "learning_rate": 9.55701367805961e-06,
      "loss": 0.0033,
      "step": 32000
    },
    {
      "epoch": 3.182842033101557,
      "grad_norm": 0.003137261839583516,
      "learning_rate": 9.393791009695427e-06,
      "loss": 0.0031,
      "step": 32500
    },
    {
      "epoch": 3.231808833610812,
      "grad_norm": 0.007661271840333939,
      "learning_rate": 9.230568341331245e-06,
      "loss": 0.0028,
      "step": 33000
    },
    {
      "epoch": 3.2807756341200665,
      "grad_norm": 0.006506490521132946,
      "learning_rate": 9.06767211830379e-06,
      "loss": 0.0029,
      "step": 33500
    },
    {
      "epoch": 3.3297424346293214,
      "grad_norm": 0.03698953613638878,
      "learning_rate": 8.904449449939609e-06,
      "loss": 0.003,
      "step": 34000
    },
    {
      "epoch": 3.378709235138576,
      "grad_norm": 0.1853983998298645,
      "learning_rate": 8.741226781575427e-06,
      "loss": 0.0029,
      "step": 34500
    },
    {
      "epoch": 3.427676035647831,
      "grad_norm": 0.053507931530475616,
      "learning_rate": 8.578004113211243e-06,
      "loss": 0.0029,
      "step": 35000
    },
    {
      "epoch": 3.4766428361570854,
      "grad_norm": 0.10720884054899216,
      "learning_rate": 8.414781444847061e-06,
      "loss": 0.003,
      "step": 35500
    },
    {
      "epoch": 3.5256096366663403,
      "grad_norm": 0.015493680723011494,
      "learning_rate": 8.25155877648288e-06,
      "loss": 0.0031,
      "step": 36000
    },
    {
      "epoch": 3.574576437175595,
      "grad_norm": 0.07669718563556671,
      "learning_rate": 8.088336108118696e-06,
      "loss": 0.0029,
      "step": 36500
    },
    {
      "epoch": 3.6235432376848498,
      "grad_norm": 0.16198168694972992,
      "learning_rate": 7.925439885091243e-06,
      "loss": 0.003,
      "step": 37000
    },
    {
      "epoch": 3.6725100381941043,
      "grad_norm": 0.00896318256855011,
      "learning_rate": 7.76254366206379e-06,
      "loss": 0.0029,
      "step": 37500
    },
    {
      "epoch": 3.721476838703359,
      "grad_norm": 0.12104916572570801,
      "learning_rate": 7.599320993699606e-06,
      "loss": 0.0028,
      "step": 38000
    },
    {
      "epoch": 3.7704436392126137,
      "grad_norm": 0.10880939662456512,
      "learning_rate": 7.436098325335424e-06,
      "loss": 0.0029,
      "step": 38500
    },
    {
      "epoch": 3.8194104397218687,
      "grad_norm": 0.030039768666028976,
      "learning_rate": 7.272875656971241e-06,
      "loss": 0.0027,
      "step": 39000
    },
    {
      "epoch": 3.868377240231123,
      "grad_norm": 0.09756383299827576,
      "learning_rate": 7.109652988607058e-06,
      "loss": 0.0029,
      "step": 39500
    },
    {
      "epoch": 3.917344040740378,
      "grad_norm": 0.002539890818297863,
      "learning_rate": 6.9464303202428765e-06,
      "loss": 0.0027,
      "step": 40000
    },
    {
      "epoch": 3.9663108412496326,
      "grad_norm": 0.08850258588790894,
      "learning_rate": 6.783207651878694e-06,
      "loss": 0.0029,
      "step": 40500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9124462328291938,
      "eval_f1": 0.9324835411122006,
      "eval_loss": 0.0029195661190897226,
      "eval_roc_auc": 0.9616052804493336,
      "eval_runtime": 55.6822,
      "eval_samples_per_second": 129.431,
      "eval_steps_per_second": 16.181,
      "step": 40844
    },
    {
      "epoch": 4.015277641758887,
      "grad_norm": 0.1031348779797554,
      "learning_rate": 6.619984983514511e-06,
      "loss": 0.0027,
      "step": 41000
    },
    {
      "epoch": 4.0642444422681425,
      "grad_norm": 0.07331918925046921,
      "learning_rate": 6.456762315150329e-06,
      "loss": 0.0025,
      "step": 41500
    },
    {
      "epoch": 4.113211242777397,
      "grad_norm": 0.10652918368577957,
      "learning_rate": 6.2935396467861465e-06,
      "loss": 0.0025,
      "step": 42000
    },
    {
      "epoch": 4.1621780432866515,
      "grad_norm": 0.11473935097455978,
      "learning_rate": 6.130316978421964e-06,
      "loss": 0.0026,
      "step": 42500
    },
    {
      "epoch": 4.211144843795906,
      "grad_norm": 0.0035420297645032406,
      "learning_rate": 5.967094310057782e-06,
      "loss": 0.0025,
      "step": 43000
    },
    {
      "epoch": 4.260111644305161,
      "grad_norm": 0.01006217859685421,
      "learning_rate": 5.8045245323670555e-06,
      "loss": 0.0025,
      "step": 43500
    },
    {
      "epoch": 4.309078444814416,
      "grad_norm": 0.09146247059106827,
      "learning_rate": 5.641301864002873e-06,
      "loss": 0.0022,
      "step": 44000
    },
    {
      "epoch": 4.35804524532367,
      "grad_norm": 0.05604245886206627,
      "learning_rate": 5.47807919563869e-06,
      "loss": 0.0025,
      "step": 44500
    },
    {
      "epoch": 4.407012045832925,
      "grad_norm": 0.017924629151821136,
      "learning_rate": 5.314856527274508e-06,
      "loss": 0.0025,
      "step": 45000
    },
    {
      "epoch": 4.45597884634218,
      "grad_norm": 0.06204945594072342,
      "learning_rate": 5.1516338589103255e-06,
      "loss": 0.0026,
      "step": 45500
    },
    {
      "epoch": 4.504945646851435,
      "grad_norm": 0.06027592718601227,
      "learning_rate": 4.988411190546144e-06,
      "loss": 0.0024,
      "step": 46000
    },
    {
      "epoch": 4.553912447360689,
      "grad_norm": 0.26520290970802307,
      "learning_rate": 4.825188522181961e-06,
      "loss": 0.0022,
      "step": 46500
    },
    {
      "epoch": 4.602879247869944,
      "grad_norm": 0.025959959253668785,
      "learning_rate": 4.661965853817778e-06,
      "loss": 0.0022,
      "step": 47000
    },
    {
      "epoch": 4.651846048379199,
      "grad_norm": 0.0017334806034341455,
      "learning_rate": 4.498743185453596e-06,
      "loss": 0.0026,
      "step": 47500
    },
    {
      "epoch": 4.700812848888454,
      "grad_norm": 0.09476437419652939,
      "learning_rate": 4.335520517089414e-06,
      "loss": 0.0024,
      "step": 48000
    },
    {
      "epoch": 4.749779649397708,
      "grad_norm": 0.011143738403916359,
      "learning_rate": 4.172297848725231e-06,
      "loss": 0.0021,
      "step": 48500
    },
    {
      "epoch": 4.798746449906963,
      "grad_norm": 0.10621017217636108,
      "learning_rate": 4.009075180361049e-06,
      "loss": 0.0023,
      "step": 49000
    },
    {
      "epoch": 4.847713250416218,
      "grad_norm": 0.004438555799424648,
      "learning_rate": 3.845852511996866e-06,
      "loss": 0.0023,
      "step": 49500
    },
    {
      "epoch": 4.896680050925473,
      "grad_norm": 0.09955357015132904,
      "learning_rate": 3.682629843632684e-06,
      "loss": 0.0022,
      "step": 50000
    },
    {
      "epoch": 4.945646851434727,
      "grad_norm": 0.14140157401561737,
      "learning_rate": 3.51973362060523e-06,
      "loss": 0.0021,
      "step": 50500
    },
    {
      "epoch": 4.994613651943982,
      "grad_norm": 0.06944791227579117,
      "learning_rate": 3.3565109522410477e-06,
      "loss": 0.0022,
      "step": 51000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9174413764395727,
      "eval_f1": 0.9352578475336324,
      "eval_loss": 0.0027621558401733637,
      "eval_roc_auc": 0.9627978767199474,
      "eval_runtime": 55.5741,
      "eval_samples_per_second": 129.683,
      "eval_steps_per_second": 16.213,
      "step": 51055
    },
    {
      "epoch": 5.043580452453237,
      "grad_norm": 0.011898011900484562,
      "learning_rate": 3.1932882838768654e-06,
      "loss": 0.0021,
      "step": 51500
    },
    {
      "epoch": 5.0925472529624916,
      "grad_norm": 0.09524281322956085,
      "learning_rate": 3.0300656155126827e-06,
      "loss": 0.002,
      "step": 52000
    },
    {
      "epoch": 5.141514053471746,
      "grad_norm": 0.08005507290363312,
      "learning_rate": 2.8668429471485004e-06,
      "loss": 0.0019,
      "step": 52500
    },
    {
      "epoch": 5.190480853981001,
      "grad_norm": 0.05041489377617836,
      "learning_rate": 2.703946724121046e-06,
      "loss": 0.0022,
      "step": 53000
    },
    {
      "epoch": 5.239447654490256,
      "grad_norm": 0.001608343911357224,
      "learning_rate": 2.5407240557568635e-06,
      "loss": 0.0019,
      "step": 53500
    },
    {
      "epoch": 5.2884144549995105,
      "grad_norm": 0.11538127809762955,
      "learning_rate": 2.3775013873926812e-06,
      "loss": 0.0019,
      "step": 54000
    },
    {
      "epoch": 5.337381255508765,
      "grad_norm": 0.11458936333656311,
      "learning_rate": 2.214278719028499e-06,
      "loss": 0.002,
      "step": 54500
    },
    {
      "epoch": 5.3863480560180195,
      "grad_norm": 0.07239941507577896,
      "learning_rate": 2.051382496001045e-06,
      "loss": 0.0021,
      "step": 55000
    },
    {
      "epoch": 5.435314856527275,
      "grad_norm": 0.1313902884721756,
      "learning_rate": 1.8881598276368623e-06,
      "loss": 0.0018,
      "step": 55500
    },
    {
      "epoch": 5.484281657036529,
      "grad_norm": 0.0023473671171814203,
      "learning_rate": 1.7249371592726798e-06,
      "loss": 0.0021,
      "step": 56000
    },
    {
      "epoch": 5.533248457545784,
      "grad_norm": 0.09586118161678314,
      "learning_rate": 1.5617144909084975e-06,
      "loss": 0.0019,
      "step": 56500
    },
    {
      "epoch": 5.582215258055038,
      "grad_norm": 0.08927006274461746,
      "learning_rate": 1.398491822544315e-06,
      "loss": 0.0019,
      "step": 57000
    },
    {
      "epoch": 5.631182058564294,
      "grad_norm": 0.011845240369439125,
      "learning_rate": 1.235595599516861e-06,
      "loss": 0.002,
      "step": 57500
    },
    {
      "epoch": 5.680148859073548,
      "grad_norm": 0.041209351271390915,
      "learning_rate": 1.0723729311526786e-06,
      "loss": 0.002,
      "step": 58000
    },
    {
      "epoch": 5.729115659582803,
      "grad_norm": 0.09277820587158203,
      "learning_rate": 9.091502627884961e-07,
      "loss": 0.002,
      "step": 58500
    },
    {
      "epoch": 5.778082460092057,
      "grad_norm": 0.07851295173168182,
      "learning_rate": 7.459275944243137e-07,
      "loss": 0.002,
      "step": 59000
    },
    {
      "epoch": 5.827049260601313,
      "grad_norm": 0.046077970415353775,
      "learning_rate": 5.827049260601313e-07,
      "loss": 0.0018,
      "step": 59500
    },
    {
      "epoch": 5.876016061110567,
      "grad_norm": 0.13472139835357666,
      "learning_rate": 4.198087030326772e-07,
      "loss": 0.0019,
      "step": 60000
    },
    {
      "epoch": 5.924982861619822,
      "grad_norm": 0.05562426894903183,
      "learning_rate": 2.5658603466849477e-07,
      "loss": 0.0019,
      "step": 60500
    },
    {
      "epoch": 5.973949662129076,
      "grad_norm": 0.016598107293248177,
      "learning_rate": 9.368981164104072e-08,
      "loss": 0.0019,
      "step": 61000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.920632718190648,
      "eval_f1": 0.9361970057366729,
      "eval_loss": 0.002764922333881259,
      "eval_roc_auc": 0.9639744188099952,
      "eval_runtime": 55.7082,
      "eval_samples_per_second": 129.37,
      "eval_steps_per_second": 16.174,
      "step": 61266
    }
  ],
  "logging_steps": 500,
  "max_steps": 61266,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2909461039327232e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}