{
  "best_metric": 0.6820038701354548,
  "best_model_checkpoint": "/content/drive/Shareddrives/Data Science Team folder-open/datasets/Lesam/BOL/combined dataset AD-656 + AD-580 /model/Bol1.0/checkpoint-8500",
  "epoch": 12.676056338028168,
  "eval_steps": 100,
  "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14084507042253522,
      "eval_accuracy": 0.9531156222418359,
      "eval_f1": 0.09613869188337273,
      "eval_loss": 0.42083606123924255,
      "eval_precision": 0.5083333333333333,
      "eval_recall": 0.05308964316797215,
      "eval_runtime": 7.3353,
      "eval_samples_per_second": 32.718,
      "eval_steps_per_second": 16.359,
      "step": 100
    },
    {
      "epoch": 0.28169014084507044,
      "eval_accuracy": 0.9531391585760518,
      "eval_f1": 0.09598741148701809,
      "eval_loss": 0.31483981013298035,
      "eval_precision": 0.5,
      "eval_recall": 0.05308964316797215,
      "eval_runtime": 7.317,
      "eval_samples_per_second": 32.801,
      "eval_steps_per_second": 16.4,
      "step": 200
    },
    {
      "epoch": 0.4225352112676056,
      "eval_accuracy": 0.9565754633715798,
      "eval_f1": 0.12402044293015331,
      "eval_loss": 0.28479117155075073,
      "eval_precision": 0.2857142857142857,
      "eval_recall": 0.07919930374238468,
      "eval_runtime": 7.3928,
      "eval_samples_per_second": 32.464,
      "eval_steps_per_second": 16.232,
      "step": 300
    },
    {
      "epoch": 0.5633802816901409,
      "eval_accuracy": 0.9590820829655781,
      "eval_f1": 0.15186615186615188,
      "eval_loss": 0.2616308927536011,
      "eval_precision": 0.291358024691358,
      "eval_recall": 0.10269799825935597,
      "eval_runtime": 7.21,
      "eval_samples_per_second": 33.287,
      "eval_steps_per_second": 16.643,
      "step": 400
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 3.1437392234802246,
      "learning_rate": 9.444444444444445e-06,
      "loss": 0.4533,
      "step": 500
    },
    {
      "epoch": 0.704225352112676,
      "eval_accuracy": 0.9585525154457193,
      "eval_f1": 0.1576517150395778,
      "eval_loss": 0.24514709413051605,
      "eval_precision": 0.32561307901907355,
      "eval_recall": 0.10400348128807659,
      "eval_runtime": 7.3357,
      "eval_samples_per_second": 32.717,
      "eval_steps_per_second": 16.358,
      "step": 500
    },
    {
      "epoch": 0.8450704225352113,
      "eval_accuracy": 0.9594586643130333,
      "eval_f1": 0.15076717811874582,
      "eval_loss": 0.23794828355312347,
      "eval_precision": 0.32285714285714284,
      "eval_recall": 0.09834638816362054,
      "eval_runtime": 7.345,
      "eval_samples_per_second": 32.675,
      "eval_steps_per_second": 16.338,
      "step": 600
    },
    {
      "epoch": 0.9859154929577465,
      "eval_accuracy": 0.9603059723448073,
      "eval_f1": 0.17906683480453975,
      "eval_loss": 0.21762977540493011,
      "eval_precision": 0.32494279176201374,
      "eval_recall": 0.12358572671888599,
      "eval_runtime": 7.3679,
      "eval_samples_per_second": 32.574,
      "eval_steps_per_second": 16.287,
      "step": 700
    },
    {
      "epoch": 1.1267605633802817,
      "eval_accuracy": 0.9655663430420712,
      "eval_f1": 0.2692101020956475,
      "eval_loss": 0.20588882267475128,
      "eval_precision": 0.3518258426966292,
      "eval_recall": 0.21801566579634465,
      "eval_runtime": 7.173,
      "eval_samples_per_second": 33.459,
      "eval_steps_per_second": 16.729,
      "step": 800
    },
    {
      "epoch": 1.267605633802817,
      "eval_accuracy": 0.9650956163577523,
      "eval_f1": 0.2747485442032822,
      "eval_loss": 0.20205169916152954,
      "eval_precision": 0.3506756756756757,
      "eval_recall": 0.2258485639686684,
      "eval_runtime": 7.327,
      "eval_samples_per_second": 32.755,
      "eval_steps_per_second": 16.378,
      "step": 900
    },
    {
      "epoch": 1.408450704225352,
      "grad_norm": 0.12497588992118835,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.2053,
      "step": 1000
    },
    {
      "epoch": 1.408450704225352,
      "eval_accuracy": 0.9687437481612239,
      "eval_f1": 0.29104679469840417,
      "eval_loss": 0.17978309094905853,
      "eval_precision": 0.38456040028591854,
      "eval_recall": 0.23411662315056572,
      "eval_runtime": 7.3218,
      "eval_samples_per_second": 32.779,
      "eval_steps_per_second": 16.389,
      "step": 1000
    },
    {
      "epoch": 1.5492957746478875,
      "eval_accuracy": 0.9712621359223301,
      "eval_f1": 0.34724021767297225,
      "eval_loss": 0.16675764322280884,
      "eval_precision": 0.42921204356181936,
      "eval_recall": 0.2915578764142733,
      "eval_runtime": 7.3153,
      "eval_samples_per_second": 32.808,
      "eval_steps_per_second": 16.404,
      "step": 1100
    },
    {
      "epoch": 1.6901408450704225,
      "eval_accuracy": 0.9708973227419829,
      "eval_f1": 0.33114668066124375,
      "eval_loss": 0.1615074723958969,
      "eval_precision": 0.4170522141440846,
      "eval_recall": 0.27458659704090516,
      "eval_runtime": 7.4019,
      "eval_samples_per_second": 32.424,
      "eval_steps_per_second": 16.212,
      "step": 1200
    },
    {
      "epoch": 1.8309859154929577,
      "eval_accuracy": 0.9715563401000294,
      "eval_f1": 0.37593984962406013,
      "eval_loss": 0.1544044315814972,
      "eval_precision": 0.4246575342465753,
      "eval_recall": 0.3372497824194952,
      "eval_runtime": 7.2284,
      "eval_samples_per_second": 33.202,
      "eval_steps_per_second": 16.601,
      "step": 1300
    },
    {
      "epoch": 1.971830985915493,
      "eval_accuracy": 0.9729685201529862,
      "eval_f1": 0.354788877445932,
      "eval_loss": 0.14469194412231445,
      "eval_precision": 0.4344262295081967,
      "eval_recall": 0.2998259355961706,
      "eval_runtime": 7.2572,
      "eval_samples_per_second": 33.07,
      "eval_steps_per_second": 16.535,
      "step": 1400
    },
    {
      "epoch": 2.112676056338028,
      "grad_norm": 3.3000364303588867,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.1633,
      "step": 1500
    },
    {
      "epoch": 2.112676056338028,
      "eval_accuracy": 0.9744866137099146,
      "eval_f1": 0.4306997742663657,
      "eval_loss": 0.14256681501865387,
      "eval_precision": 0.4474671669793621,
      "eval_recall": 0.4151436031331593,
      "eval_runtime": 7.3087,
      "eval_samples_per_second": 32.838,
      "eval_steps_per_second": 16.419,
      "step": 1500
    },
    {
      "epoch": 2.2535211267605635,
      "eval_accuracy": 0.9750632538982054,
      "eval_f1": 0.41274369947693773,
      "eval_loss": 0.13538698852062225,
      "eval_precision": 0.4549266247379455,
      "eval_recall": 0.3777197563098346,
      "eval_runtime": 7.3667,
      "eval_samples_per_second": 32.579,
      "eval_steps_per_second": 16.29,
      "step": 1600
    },
    {
      "epoch": 2.3943661971830985,
      "eval_accuracy": 0.9748631950573698,
      "eval_f1": 0.4427480916030535,
      "eval_loss": 0.1301625669002533,
      "eval_precision": 0.45732838589981445,
      "eval_recall": 0.4290687554395126,
      "eval_runtime": 7.3457,
      "eval_samples_per_second": 32.672,
      "eval_steps_per_second": 16.336,
      "step": 1700
    },
    {
      "epoch": 2.535211267605634,
      "eval_accuracy": 0.9771226831421006,
      "eval_f1": 0.4529600734281781,
      "eval_loss": 0.12118236720561981,
      "eval_precision": 0.479126213592233,
      "eval_recall": 0.42950391644908614,
      "eval_runtime": 7.3572,
      "eval_samples_per_second": 32.621,
      "eval_steps_per_second": 16.311,
      "step": 1800
    },
    {
      "epoch": 2.676056338028169,
      "eval_accuracy": 0.9772285966460724,
      "eval_f1": 0.4805283534502391,
      "eval_loss": 0.12013120204210281,
      "eval_precision": 0.5040611562350693,
      "eval_recall": 0.459094865100087,
      "eval_runtime": 7.2756,
      "eval_samples_per_second": 32.987,
      "eval_steps_per_second": 16.494,
      "step": 1900
    },
    {
      "epoch": 2.816901408450704,
      "grad_norm": 4.632040500640869,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.116,
      "step": 2000
    },
    {
      "epoch": 2.816901408450704,
      "eval_accuracy": 0.9765695792880259,
      "eval_f1": 0.46877098723975824,
      "eval_loss": 0.12145345658063889,
      "eval_precision": 0.4827109266943292,
      "eval_recall": 0.4556135770234987,
      "eval_runtime": 7.3168,
      "eval_samples_per_second": 32.801,
      "eval_steps_per_second": 16.401,
      "step": 2000
    },
    {
      "epoch": 2.9577464788732395,
      "eval_accuracy": 0.9755104442483084,
      "eval_f1": 0.4675658317276814,
      "eval_loss": 0.12608888745307922,
      "eval_precision": 0.46017699115044247,
      "eval_recall": 0.4751958224543081,
      "eval_runtime": 7.3583,
      "eval_samples_per_second": 32.616,
      "eval_steps_per_second": 16.308,
      "step": 2100
    },
    {
      "epoch": 3.0985915492957745,
      "eval_accuracy": 0.9789938217122683,
      "eval_f1": 0.4885803851321093,
      "eval_loss": 0.11443355679512024,
      "eval_precision": 0.5032287822878229,
      "eval_recall": 0.47476066144473456,
      "eval_runtime": 7.3495,
      "eval_samples_per_second": 32.655,
      "eval_steps_per_second": 16.328,
      "step": 2200
    },
    {
      "epoch": 3.23943661971831,
      "eval_accuracy": 0.9794880847308032,
      "eval_f1": 0.501056586053064,
      "eval_loss": 0.10821868479251862,
      "eval_precision": 0.5441101478837328,
      "eval_recall": 0.46431679721496955,
      "eval_runtime": 7.3804,
      "eval_samples_per_second": 32.519,
      "eval_steps_per_second": 16.259,
      "step": 2300
    },
    {
      "epoch": 3.380281690140845,
      "eval_accuracy": 0.9779935275080907,
      "eval_f1": 0.49851360621998636,
      "eval_loss": 0.11080476641654968,
      "eval_precision": 0.5253012048192771,
      "eval_recall": 0.47432550043516103,
      "eval_runtime": 7.2629,
      "eval_samples_per_second": 33.045,
      "eval_steps_per_second": 16.522,
      "step": 2400
    },
    {
      "epoch": 3.52112676056338,
      "grad_norm": 0.7869037985801697,
      "learning_rate": 7.222222222222223e-06,
      "loss": 0.0909,
      "step": 2500
    },
    {
      "epoch": 3.52112676056338,
      "eval_accuracy": 0.9786525448661371,
      "eval_f1": 0.5188613746817866,
      "eval_loss": 0.11673837155103683,
      "eval_precision": 0.5541275333662877,
      "eval_recall": 0.48781549173194083,
      "eval_runtime": 7.2497,
      "eval_samples_per_second": 33.105,
      "eval_steps_per_second": 16.552,
      "step": 2500
    },
    {
      "epoch": 3.6619718309859155,
      "eval_accuracy": 0.979982347749338,
      "eval_f1": 0.5242311276794035,
      "eval_loss": 0.11096884310245514,
      "eval_precision": 0.5641925777331996,
      "eval_recall": 0.489556135770235,
      "eval_runtime": 7.3912,
      "eval_samples_per_second": 32.471,
      "eval_steps_per_second": 16.236,
      "step": 2600
    },
    {
      "epoch": 3.802816901408451,
      "eval_accuracy": 0.9792644895557517,
      "eval_f1": 0.5294117647058825,
      "eval_loss": 0.10684900730848312,
      "eval_precision": 0.5382194244604317,
      "eval_recall": 0.52088772845953,
      "eval_runtime": 7.4198,
      "eval_samples_per_second": 32.346,
      "eval_steps_per_second": 16.173,
      "step": 2700
    },
    {
      "epoch": 3.943661971830986,
      "eval_accuracy": 0.9792527213886437,
      "eval_f1": 0.5260178532549532,
      "eval_loss": 0.10498978942632675,
      "eval_precision": 0.5263616557734205,
      "eval_recall": 0.525674499564839,
      "eval_runtime": 7.3935,
      "eval_samples_per_second": 32.461,
      "eval_steps_per_second": 16.23,
      "step": 2800
    },
    {
      "epoch": 4.084507042253521,
      "eval_accuracy": 0.9806178287731686,
      "eval_f1": 0.537687318273317,
      "eval_loss": 0.10101501643657684,
      "eval_precision": 0.55315232397607,
      "eval_recall": 0.5230635335073978,
      "eval_runtime": 7.3652,
      "eval_samples_per_second": 32.586,
      "eval_steps_per_second": 16.293,
      "step": 2900
    },
    {
      "epoch": 4.225352112676056,
      "grad_norm": 3.056248426437378,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.08,
      "step": 3000
    },
    {
      "epoch": 4.225352112676056,
      "eval_accuracy": 0.9793350985583995,
      "eval_f1": 0.534056399132321,
      "eval_loss": 0.1095050647854805,
      "eval_precision": 0.532439446366782,
      "eval_recall": 0.5356832027850305,
      "eval_runtime": 7.3022,
      "eval_samples_per_second": 32.867,
      "eval_steps_per_second": 16.433,
      "step": 3000
    },
    {
      "epoch": 4.366197183098592,
      "eval_accuracy": 0.9807355104442483,
      "eval_f1": 0.5566556655665567,
      "eval_loss": 0.10490421205759048,
      "eval_precision": 0.5629728526924789,
      "eval_recall": 0.5504786771105309,
      "eval_runtime": 7.3941,
      "eval_samples_per_second": 32.458,
      "eval_steps_per_second": 16.229,
      "step": 3100
    },
    {
      "epoch": 4.507042253521127,
      "eval_accuracy": 0.9806884377758164,
      "eval_f1": 0.5487348734873487,
      "eval_loss": 0.0985017642378807,
      "eval_precision": 0.5549621717846017,
      "eval_recall": 0.5426457789382071,
      "eval_runtime": 7.3897,
      "eval_samples_per_second": 32.478,
      "eval_steps_per_second": 16.239,
      "step": 3200
    },
    {
      "epoch": 4.647887323943662,
      "eval_accuracy": 0.9803118564283613,
      "eval_f1": 0.5325077399380805,
      "eval_loss": 0.10188236087560654,
      "eval_precision": 0.5413669064748201,
      "eval_recall": 0.5239338555265448,
      "eval_runtime": 7.3669,
      "eval_samples_per_second": 32.578,
      "eval_steps_per_second": 16.289,
      "step": 3300
    },
    {
      "epoch": 4.788732394366197,
      "eval_accuracy": 0.9811591644601353,
      "eval_f1": 0.5600684053014109,
      "eval_loss": 0.09488189220428467,
      "eval_precision": 0.5504201680672269,
      "eval_recall": 0.5700609225413403,
      "eval_runtime": 7.3775,
      "eval_samples_per_second": 32.531,
      "eval_steps_per_second": 16.266,
      "step": 3400
    },
    {
      "epoch": 4.929577464788732,
      "grad_norm": 0.00509398290887475,
      "learning_rate": 6.111111111111112e-06,
      "loss": 0.0671,
      "step": 3500
    },
    {
      "epoch": 4.929577464788732,
      "eval_accuracy": 0.9823477493380406,
      "eval_f1": 0.5749396532806671,
      "eval_loss": 0.09079114347696304,
      "eval_precision": 0.5799026117751217,
      "eval_recall": 0.5700609225413403,
      "eval_runtime": 7.2549,
      "eval_samples_per_second": 33.081,
      "eval_steps_per_second": 16.54,
      "step": 3500
    },
    {
      "epoch": 5.070422535211268,
      "eval_accuracy": 0.9842188879082083,
      "eval_f1": 0.5980850590069028,
      "eval_loss": 0.08618247509002686,
      "eval_precision": 0.6124031007751938,
      "eval_recall": 0.5844212358572672,
      "eval_runtime": 7.3833,
      "eval_samples_per_second": 32.506,
      "eval_steps_per_second": 16.253,
      "step": 3600
    },
    {
      "epoch": 5.211267605633803,
      "eval_accuracy": 0.98177110914975,
      "eval_f1": 0.5608871827681807,
      "eval_loss": 0.09391660988330841,
      "eval_precision": 0.5499790882475951,
      "eval_recall": 0.572236727589208,
      "eval_runtime": 7.376,
      "eval_samples_per_second": 32.538,
      "eval_steps_per_second": 16.269,
      "step": 3700
    },
    {
      "epoch": 5.352112676056338,
      "eval_accuracy": 0.9824889673433362,
      "eval_f1": 0.5940507436570428,
      "eval_loss": 0.09653446823358536,
      "eval_precision": 0.5971855760773966,
      "eval_recall": 0.5909486510008704,
      "eval_runtime": 7.386,
      "eval_samples_per_second": 32.494,
      "eval_steps_per_second": 16.247,
      "step": 3800
    },
    {
      "epoch": 5.492957746478873,
      "eval_accuracy": 0.9821006178287731,
      "eval_f1": 0.5902280130293159,
      "eval_loss": 0.09449278563261032,
      "eval_precision": 0.5890767230169051,
      "eval_recall": 0.5913838120104439,
      "eval_runtime": 7.3734,
      "eval_samples_per_second": 32.549,
      "eval_steps_per_second": 16.275,
      "step": 3900
    },
    {
      "epoch": 5.633802816901408,
      "grad_norm": 0.8984728455543518,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.059,
      "step": 4000
    },
    {
      "epoch": 5.633802816901408,
      "eval_accuracy": 0.982171226831421,
      "eval_f1": 0.5924487594390507,
      "eval_loss": 0.09081266820430756,
      "eval_precision": 0.5875053487376979,
      "eval_recall": 0.5974760661444735,
      "eval_runtime": 7.3677,
      "eval_samples_per_second": 32.575,
      "eval_steps_per_second": 16.287,
      "step": 4000
    },
    {
      "epoch": 5.774647887323944,
      "eval_accuracy": 0.983030303030303,
      "eval_f1": 0.5897771952817825,
      "eval_loss": 0.08924023061990738,
      "eval_precision": 0.5921052631578947,
      "eval_recall": 0.587467362924282,
      "eval_runtime": 7.278,
      "eval_samples_per_second": 32.976,
      "eval_steps_per_second": 16.488,
      "step": 4100
    },
    {
      "epoch": 5.915492957746479,
      "eval_accuracy": 0.9837010885554575,
      "eval_f1": 0.6034408602150538,
      "eval_loss": 0.0901557207107544,
      "eval_precision": 0.5965136054421769,
      "eval_recall": 0.6105308964316797,
      "eval_runtime": 7.4615,
      "eval_samples_per_second": 32.165,
      "eval_steps_per_second": 16.083,
      "step": 4200
    },
    {
      "epoch": 6.056338028169014,
      "eval_accuracy": 0.9843836422477199,
      "eval_f1": 0.6253776435045316,
      "eval_loss": 0.08598857372999191,
      "eval_precision": 0.620291095890411,
      "eval_recall": 0.6305483028720626,
      "eval_runtime": 7.367,
      "eval_samples_per_second": 32.578,
      "eval_steps_per_second": 16.289,
      "step": 4300
    },
    {
      "epoch": 6.197183098591549,
      "eval_accuracy": 0.9844307149161519,
      "eval_f1": 0.6058235549760974,
      "eval_loss": 0.08827093243598938,
      "eval_precision": 0.6050347222222222,
      "eval_recall": 0.6066144473455178,
      "eval_runtime": 7.3941,
      "eval_samples_per_second": 32.458,
      "eval_steps_per_second": 16.229,
      "step": 4400
    },
    {
      "epoch": 6.338028169014084,
      "grad_norm": 2.909140110015869,
      "learning_rate": 5e-06,
      "loss": 0.0516,
      "step": 4500
    },
    {
      "epoch": 6.338028169014084,
      "eval_accuracy": 0.9840894380700206,
      "eval_f1": 0.5963083604777416,
      "eval_loss": 0.09003057330846786,
      "eval_precision": 0.5951452102297355,
      "eval_recall": 0.5974760661444735,
      "eval_runtime": 7.3583,
      "eval_samples_per_second": 32.616,
      "eval_steps_per_second": 16.308,
      "step": 4500
    },
    {
      "epoch": 6.47887323943662,
      "eval_accuracy": 0.9842541924095323,
      "eval_f1": 0.5947252747252747,
      "eval_loss": 0.08872821182012558,
      "eval_precision": 0.6007992895204263,
      "eval_recall": 0.5887728459530026,
      "eval_runtime": 7.2679,
      "eval_samples_per_second": 33.022,
      "eval_steps_per_second": 16.511,
      "step": 4600
    },
    {
      "epoch": 6.619718309859155,
      "eval_accuracy": 0.9841835834068844,
      "eval_f1": 0.6222998036220816,
      "eval_loss": 0.08372443169355392,
      "eval_precision": 0.624070021881838,
      "eval_recall": 0.6205395996518712,
      "eval_runtime": 7.4046,
      "eval_samples_per_second": 32.412,
      "eval_steps_per_second": 16.206,
      "step": 4700
    },
    {
      "epoch": 6.76056338028169,
      "eval_accuracy": 0.9844777875845837,
      "eval_f1": 0.6397756686798964,
      "eval_loss": 0.08945748209953308,
      "eval_precision": 0.6343028229255774,
      "eval_recall": 0.6453437771975631,
      "eval_runtime": 7.3826,
      "eval_samples_per_second": 32.509,
      "eval_steps_per_second": 16.254,
      "step": 4800
    },
    {
      "epoch": 6.901408450704225,
      "eval_accuracy": 0.9840541335686966,
      "eval_f1": 0.6284970722186076,
      "eval_loss": 0.08736680448055267,
      "eval_precision": 0.6264591439688716,
      "eval_recall": 0.6305483028720626,
      "eval_runtime": 7.3836,
      "eval_samples_per_second": 32.505,
      "eval_steps_per_second": 16.252,
      "step": 4900
    },
    {
      "epoch": 7.042253521126761,
      "grad_norm": 0.0029603431466966867,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.0494,
      "step": 5000
    },
    {
      "epoch": 7.042253521126761,
      "eval_accuracy": 0.9837481612238894,
      "eval_f1": 0.6307495741056218,
      "eval_loss": 0.08429873734712601,
      "eval_precision": 0.6175979983319433,
      "eval_recall": 0.644473455178416,
      "eval_runtime": 7.4187,
      "eval_samples_per_second": 32.351,
      "eval_steps_per_second": 16.175,
      "step": 5000
    },
    {
      "epoch": 7.183098591549296,
      "eval_accuracy": 0.9844542512503678,
      "eval_f1": 0.6298800436205015,
      "eval_loss": 0.0860215276479721,
      "eval_precision": 0.6313948404022737,
      "eval_recall": 0.6283724978241949,
      "eval_runtime": 7.3007,
      "eval_samples_per_second": 32.874,
      "eval_steps_per_second": 16.437,
      "step": 5100
    },
    {
      "epoch": 7.323943661971831,
      "eval_accuracy": 0.9841835834068844,
      "eval_f1": 0.6415256053139062,
      "eval_loss": 0.08662400394678116,
      "eval_precision": 0.6319121992401857,
      "eval_recall": 0.6514360313315927,
      "eval_runtime": 7.2401,
      "eval_samples_per_second": 33.149,
      "eval_steps_per_second": 16.574,
      "step": 5200
    },
    {
      "epoch": 7.464788732394366,
      "eval_accuracy": 0.9846072374227715,
      "eval_f1": 0.6500537056928034,
      "eval_loss": 0.08784898370504379,
      "eval_precision": 0.6419176919813322,
      "eval_recall": 0.6583986074847694,
      "eval_runtime": 7.4104,
      "eval_samples_per_second": 32.387,
      "eval_steps_per_second": 16.193,
      "step": 5300
    },
    {
      "epoch": 7.605633802816901,
      "eval_accuracy": 0.9842541924095323,
      "eval_f1": 0.6414596614640581,
      "eval_loss": 0.09084232151508331,
      "eval_precision": 0.6481563749444691,
      "eval_recall": 0.6348999129677981,
      "eval_runtime": 7.3975,
      "eval_samples_per_second": 32.443,
      "eval_steps_per_second": 16.222,
      "step": 5400
    },
    {
      "epoch": 7.746478873239437,
      "grad_norm": 0.0023182749282568693,
      "learning_rate": 3.88888888888889e-06,
      "loss": 0.0471,
      "step": 5500
    },
    {
      "epoch": 7.746478873239437,
      "eval_accuracy": 0.9840188290673727,
      "eval_f1": 0.6452567082188886,
      "eval_loss": 0.08999249339103699,
      "eval_precision": 0.6271047227926078,
      "eval_recall": 0.664490861618799,
      "eval_runtime": 7.3891,
      "eval_samples_per_second": 32.48,
      "eval_steps_per_second": 16.24,
      "step": 5500
    },
    {
      "epoch": 7.887323943661972,
      "eval_accuracy": 0.9845601647543395,
      "eval_f1": 0.6460348162475823,
      "eval_loss": 0.08533038198947906,
      "eval_precision": 0.6382165605095541,
      "eval_recall": 0.6540469973890339,
      "eval_runtime": 7.4541,
      "eval_samples_per_second": 32.197,
      "eval_steps_per_second": 16.099,
      "step": 5600
    },
    {
      "epoch": 8.028169014084508,
      "eval_accuracy": 0.9839835245660489,
      "eval_f1": 0.6473011055712118,
      "eval_loss": 0.08411037921905518,
      "eval_precision": 0.6449244060475162,
      "eval_recall": 0.6496953872932986,
      "eval_runtime": 7.2873,
      "eval_samples_per_second": 32.934,
      "eval_steps_per_second": 16.467,
      "step": 5700
    },
    {
      "epoch": 8.169014084507042,
      "eval_accuracy": 0.9845837010885554,
      "eval_f1": 0.6499032882011605,
      "eval_loss": 0.08550503104925156,
      "eval_precision": 0.6420382165605095,
      "eval_recall": 0.6579634464751958,
      "eval_runtime": 7.4063,
      "eval_samples_per_second": 32.405,
      "eval_steps_per_second": 16.203,
      "step": 5800
    },
    {
      "epoch": 8.309859154929578,
      "eval_accuracy": 0.9845719329214475,
      "eval_f1": 0.6492411467116358,
      "eval_loss": 0.08611707389354706,
      "eval_precision": 0.6295993458708095,
      "eval_recall": 0.6701479547432551,
      "eval_runtime": 7.4327,
      "eval_samples_per_second": 32.29,
      "eval_steps_per_second": 16.145,
      "step": 5900
    },
    {
      "epoch": 8.450704225352112,
      "grad_norm": 1.646479606628418,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.0372,
      "step": 6000
    },
    {
      "epoch": 8.450704225352112,
      "eval_accuracy": 0.9843365695792881,
      "eval_f1": 0.6446173800259403,
      "eval_loss": 0.08737049251794815,
      "eval_precision": 0.6404639175257731,
      "eval_recall": 0.6488250652741514,
      "eval_runtime": 7.382,
      "eval_samples_per_second": 32.511,
      "eval_steps_per_second": 16.256,
      "step": 6000
    },
    {
      "epoch": 8.591549295774648,
      "eval_accuracy": 0.9844424830832598,
      "eval_f1": 0.6449305847707194,
      "eval_loss": 0.08426456153392792,
      "eval_precision": 0.624185667752443,
      "eval_recall": 0.6671018276762402,
      "eval_runtime": 7.3893,
      "eval_samples_per_second": 32.479,
      "eval_steps_per_second": 16.24,
      "step": 6100
    },
    {
      "epoch": 8.732394366197184,
      "eval_accuracy": 0.9846778464254192,
      "eval_f1": 0.6556962025316455,
      "eval_loss": 0.08480408787727356,
      "eval_precision": 0.6363636363636364,
      "eval_recall": 0.6762402088772846,
      "eval_runtime": 7.2354,
      "eval_samples_per_second": 33.17,
      "eval_steps_per_second": 16.585,
      "step": 6200
    },
    {
      "epoch": 8.873239436619718,
      "eval_accuracy": 0.9845601647543395,
      "eval_f1": 0.6470588235294118,
      "eval_loss": 0.08321469277143478,
      "eval_precision": 0.6385593220338983,
      "eval_recall": 0.6557876414273281,
      "eval_runtime": 7.4183,
      "eval_samples_per_second": 32.352,
      "eval_steps_per_second": 16.176,
      "step": 6300
    },
    {
      "epoch": 9.014084507042254,
      "eval_accuracy": 0.9850779641070904,
      "eval_f1": 0.6635009712928988,
      "eval_loss": 0.08342073112726212,
      "eval_precision": 0.6582441113490364,
      "eval_recall": 0.6688424717145344,
      "eval_runtime": 7.3864,
      "eval_samples_per_second": 32.492,
      "eval_steps_per_second": 16.246,
      "step": 6400
    },
    {
      "epoch": 9.154929577464788,
      "grad_norm": 2.369316339492798,
      "learning_rate": 2.7777777777777783e-06,
      "loss": 0.0376,
      "step": 6500
    },
    {
      "epoch": 9.154929577464788,
      "eval_accuracy": 0.9844777875845837,
      "eval_f1": 0.6438267614738203,
      "eval_loss": 0.08599114418029785,
      "eval_precision": 0.6376440460947503,
      "eval_recall": 0.6501305483028721,
      "eval_runtime": 7.4336,
      "eval_samples_per_second": 32.286,
      "eval_steps_per_second": 16.143,
      "step": 6500
    },
    {
      "epoch": 9.295774647887324,
      "eval_accuracy": 0.9851838776110621,
      "eval_f1": 0.6749455337690632,
      "eval_loss": 0.0860476940870285,
      "eval_precision": 0.6758289703315882,
      "eval_recall": 0.6740644038294169,
      "eval_runtime": 7.3997,
      "eval_samples_per_second": 32.434,
      "eval_steps_per_second": 16.217,
      "step": 6600
    },
    {
      "epoch": 9.43661971830986,
      "eval_accuracy": 0.9851132686084142,
      "eval_f1": 0.6611642050390965,
      "eval_loss": 0.08599450439214706,
      "eval_precision": 0.6600173460537727,
      "eval_recall": 0.6623150565709313,
      "eval_runtime": 7.2459,
      "eval_samples_per_second": 33.122,
      "eval_steps_per_second": 16.561,
      "step": 6700
    },
    {
      "epoch": 9.577464788732394,
      "eval_accuracy": 0.9855486907914093,
      "eval_f1": 0.661723009814613,
      "eval_loss": 0.0859636440873146,
      "eval_precision": 0.6633143856580673,
      "eval_recall": 0.6601392515230635,
      "eval_runtime": 7.2743,
      "eval_samples_per_second": 32.993,
      "eval_steps_per_second": 16.496,
      "step": 6800
    },
    {
      "epoch": 9.71830985915493,
      "eval_accuracy": 0.985642836128273,
      "eval_f1": 0.6686567164179105,
      "eval_loss": 0.08458743244409561,
      "eval_precision": 0.6555183946488294,
      "eval_recall": 0.6823324630113142,
      "eval_runtime": 7.4204,
      "eval_samples_per_second": 32.343,
      "eval_steps_per_second": 16.172,
      "step": 6900
    },
    {
      "epoch": 9.859154929577464,
      "grad_norm": 0.0017794760642573237,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.0352,
      "step": 7000
    },
    {
      "epoch": 9.859154929577464,
      "eval_accuracy": 0.9853250956163577,
      "eval_f1": 0.6703601108033241,
      "eval_loss": 0.08406654000282288,
      "eval_precision": 0.6567849686847599,
      "eval_recall": 0.6845082680591819,
      "eval_runtime": 7.4608,
      "eval_samples_per_second": 32.168,
      "eval_steps_per_second": 16.084,
      "step": 7000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9856310679611651,
      "eval_f1": 0.6696619597774925,
      "eval_loss": 0.08345002681016922,
      "eval_precision": 0.6586700336700336,
      "eval_recall": 0.6810269799825935,
      "eval_runtime": 7.4149,
      "eval_samples_per_second": 32.367,
      "eval_steps_per_second": 16.184,
      "step": 7100
    },
    {
      "epoch": 10.140845070422536,
      "eval_accuracy": 0.9852427184466019,
      "eval_f1": 0.6715548846236791,
      "eval_loss": 0.0879812017083168,
      "eval_precision": 0.6656690893544249,
      "eval_recall": 0.6775456919060052,
      "eval_runtime": 7.4442,
      "eval_samples_per_second": 32.24,
      "eval_steps_per_second": 16.12,
      "step": 7200
    },
    {
      "epoch": 10.28169014084507,
      "eval_accuracy": 0.9859723448072962,
      "eval_f1": 0.6685272649205668,
      "eval_loss": 0.08136157691478729,
      "eval_precision": 0.6597457627118644,
      "eval_recall": 0.6775456919060052,
      "eval_runtime": 7.376,
      "eval_samples_per_second": 32.538,
      "eval_steps_per_second": 16.269,
      "step": 7300
    },
    {
      "epoch": 10.422535211267606,
      "eval_accuracy": 0.9856781406295969,
      "eval_f1": 0.6621363346782757,
      "eval_loss": 0.08381623774766922,
      "eval_precision": 0.646619659892161,
      "eval_recall": 0.6784160139251523,
      "eval_runtime": 7.4024,
      "eval_samples_per_second": 32.422,
      "eval_steps_per_second": 16.211,
      "step": 7400
    },
    {
      "epoch": 10.56338028169014,
      "grad_norm": 7.505336761474609,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.0316,
      "step": 7500
    },
    {
      "epoch": 10.56338028169014,
      "eval_accuracy": 0.9855722271256252,
      "eval_f1": 0.6696619597774925,
      "eval_loss": 0.08473847806453705,
      "eval_precision": 0.6586700336700336,
      "eval_recall": 0.6810269799825935,
      "eval_runtime": 7.4244,
      "eval_samples_per_second": 32.326,
      "eval_steps_per_second": 16.163,
      "step": 7500
    },
    {
      "epoch": 10.704225352112676,
      "eval_accuracy": 0.9857252132980289,
      "eval_f1": 0.6789620416041175,
      "eval_loss": 0.08409886062145233,
      "eval_precision": 0.6693446088794927,
      "eval_recall": 0.6888598781549173,
      "eval_runtime": 7.4216,
      "eval_samples_per_second": 32.338,
      "eval_steps_per_second": 16.169,
      "step": 7600
    },
    {
      "epoch": 10.845070422535212,
      "eval_accuracy": 0.9858546631362165,
      "eval_f1": 0.6777609682299546,
      "eval_loss": 0.08510851860046387,
      "eval_precision": 0.6732503220266208,
      "eval_recall": 0.6823324630113142,
      "eval_runtime": 7.4269,
      "eval_samples_per_second": 32.315,
      "eval_steps_per_second": 16.157,
      "step": 7700
    },
    {
      "epoch": 10.985915492957746,
      "eval_accuracy": 0.985219182112386,
      "eval_f1": 0.663824344489448,
      "eval_loss": 0.08504322916269302,
      "eval_precision": 0.6506477225240285,
      "eval_recall": 0.6775456919060052,
      "eval_runtime": 7.297,
      "eval_samples_per_second": 32.89,
      "eval_steps_per_second": 16.445,
      "step": 7800
    },
    {
      "epoch": 11.126760563380282,
      "eval_accuracy": 0.9855133862900853,
      "eval_f1": 0.6787174521196471,
      "eval_loss": 0.08639871329069138,
      "eval_precision": 0.6713495104299702,
      "eval_recall": 0.6862489120974761,
      "eval_runtime": 7.3134,
      "eval_samples_per_second": 32.817,
      "eval_steps_per_second": 16.408,
      "step": 7900
    },
    {
      "epoch": 11.267605633802816,
      "grad_norm": 0.0015932625392451882,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.0323,
      "step": 8000
    },
    {
      "epoch": 11.267605633802816,
      "eval_accuracy": 0.9859605766401883,
      "eval_f1": 0.671434763762462,
      "eval_loss": 0.08427204191684723,
      "eval_precision": 0.668825561312608,
      "eval_recall": 0.6740644038294169,
      "eval_runtime": 7.4224,
      "eval_samples_per_second": 32.335,
      "eval_steps_per_second": 16.167,
      "step": 8000
    },
    {
      "epoch": 11.408450704225352,
      "eval_accuracy": 0.9853368637834657,
      "eval_f1": 0.6679487179487179,
      "eval_loss": 0.08620592951774597,
      "eval_precision": 0.6561712846347607,
      "eval_recall": 0.6801566579634465,
      "eval_runtime": 7.52,
      "eval_samples_per_second": 31.915,
      "eval_steps_per_second": 15.957,
      "step": 8100
    },
    {
      "epoch": 11.549295774647888,
      "eval_accuracy": 0.9859723448072962,
      "eval_f1": 0.6735661923242777,
      "eval_loss": 0.08543656021356583,
      "eval_precision": 0.6675213675213675,
      "eval_recall": 0.679721496953873,
      "eval_runtime": 7.4397,
      "eval_samples_per_second": 32.259,
      "eval_steps_per_second": 16.13,
      "step": 8200
    },
    {
      "epoch": 11.690140845070422,
      "eval_accuracy": 0.986090026478376,
      "eval_f1": 0.679860809047412,
      "eval_loss": 0.0849027931690216,
      "eval_precision": 0.6795652173913044,
      "eval_recall": 0.6801566579634465,
      "eval_runtime": 7.4695,
      "eval_samples_per_second": 32.131,
      "eval_steps_per_second": 16.065,
      "step": 8300
    },
    {
      "epoch": 11.830985915492958,
      "eval_accuracy": 0.9858899676375404,
      "eval_f1": 0.6754684838160135,
      "eval_loss": 0.08420813083648682,
      "eval_precision": 0.6613844870725605,
      "eval_recall": 0.6901653611836379,
      "eval_runtime": 7.2972,
      "eval_samples_per_second": 32.889,
      "eval_steps_per_second": 16.445,
      "step": 8400
    },
    {
      "epoch": 11.971830985915492,
      "grad_norm": 4.900869369506836,
      "learning_rate": 5.555555555555555e-07,
      "loss": 0.0307,
      "step": 8500
    },
    {
      "epoch": 11.971830985915492,
      "eval_accuracy": 0.9861488673139158,
      "eval_f1": 0.6820038701354548,
      "eval_loss": 0.08459390699863434,
      "eval_precision": 0.6740331491712708,
      "eval_recall": 0.6901653611836379,
      "eval_runtime": 7.4228,
      "eval_samples_per_second": 32.333,
      "eval_steps_per_second": 16.166,
      "step": 8500
    },
    {
      "epoch": 12.112676056338028,
      "eval_accuracy": 0.9863371579876434,
      "eval_f1": 0.6822409690677049,
      "eval_loss": 0.08515108376741409,
      "eval_precision": 0.6782795698924731,
      "eval_recall": 0.6862489120974761,
      "eval_runtime": 7.4273,
      "eval_samples_per_second": 32.313,
      "eval_steps_per_second": 16.157,
      "step": 8600
    },
    {
      "epoch": 12.253521126760564,
      "eval_accuracy": 0.9860076493086202,
      "eval_f1": 0.6782646048109965,
      "eval_loss": 0.08560565114021301,
      "eval_precision": 0.6696352841391009,
      "eval_recall": 0.6871192341166231,
      "eval_runtime": 7.5069,
      "eval_samples_per_second": 31.97,
      "eval_steps_per_second": 15.985,
      "step": 8700
    },
    {
      "epoch": 12.394366197183098,
      "eval_accuracy": 0.9859017358046485,
      "eval_f1": 0.6775580395528805,
      "eval_loss": 0.08563963323831558,
      "eval_precision": 0.6694987255734919,
      "eval_recall": 0.6858137510879025,
      "eval_runtime": 7.5078,
      "eval_samples_per_second": 31.967,
      "eval_steps_per_second": 15.983,
      "step": 8800
    },
    {
      "epoch": 12.535211267605634,
      "eval_accuracy": 0.9858546631362165,
      "eval_f1": 0.6785791173304628,
      "eval_loss": 0.08600553870201111,
      "eval_precision": 0.6714955262036643,
      "eval_recall": 0.6858137510879025,
      "eval_runtime": 7.3022,
      "eval_samples_per_second": 32.867,
      "eval_steps_per_second": 16.433,
      "step": 8900
    },
    {
      "epoch": 12.676056338028168,
      "grad_norm": 0.2440214604139328,
      "learning_rate": 0.0,
      "loss": 0.028,
      "step": 9000
    },
    {
      "epoch": 12.676056338028168,
      "eval_accuracy": 0.9859252721388644,
      "eval_f1": 0.6791559000861327,
      "eval_loss": 0.08589298278093338,
      "eval_precision": 0.6722080136402387,
      "eval_recall": 0.6862489120974761,
      "eval_runtime": 7.3893,
      "eval_samples_per_second": 32.479,
      "eval_steps_per_second": 16.24,
      "step": 9000
    }
  ],
  "logging_steps": 500,
  "max_steps": 9000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 13,
  "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": 4780487614464000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}