{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 30.0,
  "eval_steps": 500,
  "global_step": 9390,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 39.49564743041992,
      "eval_mse_0": 40.492305755615234,
      "eval_mse_1": 48.72726058959961,
      "eval_mse_2": 32.83665084838867,
      "eval_mse_3": 35.926387786865234,
      "eval_pcc_0": -0.12333937476931386,
      "eval_pcc_1": -0.0037658507363324697,
      "eval_pcc_2": -0.08078735179830722,
      "eval_pcc_3": -0.22151305114830036,
      "eval_runtime": 106.854,
      "eval_samples_per_second": 23.396,
      "eval_steps_per_second": 2.929,
      "step": 313
    },
    {
      "epoch": 1.6,
      "learning_rate": 9.467518636847711e-06,
      "loss": 44.9568,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 27.73326301574707,
      "eval_mse_0": 26.188446044921875,
      "eval_mse_1": 37.98932647705078,
      "eval_mse_2": 20.299489974975586,
      "eval_mse_3": 26.45578384399414,
      "eval_pcc_0": -0.024441240323735954,
      "eval_pcc_1": 0.06973867343262147,
      "eval_pcc_2": 0.05592424331941597,
      "eval_pcc_3": -0.06854458904064749,
      "eval_runtime": 111.5771,
      "eval_samples_per_second": 22.406,
      "eval_steps_per_second": 2.805,
      "step": 626
    },
    {
      "epoch": 3.0,
      "eval_loss": 17.860057830810547,
      "eval_mse_0": 15.312986373901367,
      "eval_mse_1": 27.042709350585938,
      "eval_mse_2": 11.203091621398926,
      "eval_mse_3": 17.881418228149414,
      "eval_pcc_0": -0.0020156129433556054,
      "eval_pcc_1": 0.031014662405861624,
      "eval_pcc_2": 0.09980265496563742,
      "eval_pcc_3": -0.02815625568041995,
      "eval_runtime": 112.317,
      "eval_samples_per_second": 22.258,
      "eval_steps_per_second": 2.787,
      "step": 939
    },
    {
      "epoch": 3.19,
      "learning_rate": 8.935037273695422e-06,
      "loss": 24.0771,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_loss": 10.101034164428711,
      "eval_mse_0": 8.210121154785156,
      "eval_mse_1": 16.358339309692383,
      "eval_mse_2": 5.4965500831604,
      "eval_mse_3": 10.339128494262695,
      "eval_pcc_0": -1.9981024957522913e-05,
      "eval_pcc_1": 0.006653179397567406,
      "eval_pcc_2": 0.14176204796693667,
      "eval_pcc_3": 0.006243591638875637,
      "eval_runtime": 112.2879,
      "eval_samples_per_second": 22.264,
      "eval_steps_per_second": 2.787,
      "step": 1252
    },
    {
      "epoch": 4.79,
      "learning_rate": 8.402555910543132e-06,
      "loss": 10.7151,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_loss": 4.899745941162109,
      "eval_mse_0": 4.175392150878906,
      "eval_mse_1": 7.554749011993408,
      "eval_mse_2": 2.8561670780181885,
      "eval_mse_3": 5.01268196105957,
      "eval_pcc_0": 0.05106216294321992,
      "eval_pcc_1": 0.016529166362045093,
      "eval_pcc_2": 0.20000270663347938,
      "eval_pcc_3": 0.08366799317350487,
      "eval_runtime": 102.909,
      "eval_samples_per_second": 24.293,
      "eval_steps_per_second": 3.042,
      "step": 1565
    },
    {
      "epoch": 6.0,
      "eval_loss": 2.573153495788574,
      "eval_mse_0": 2.609571695327759,
      "eval_mse_1": 2.766584873199463,
      "eval_mse_2": 2.1557888984680176,
      "eval_mse_3": 2.7606797218322754,
      "eval_pcc_0": 0.1814858356455445,
      "eval_pcc_1": 0.09641154093221717,
      "eval_pcc_2": 0.28429109119381946,
      "eval_pcc_3": 0.22880177541231922,
      "eval_runtime": 109.1697,
      "eval_samples_per_second": 22.9,
      "eval_steps_per_second": 2.867,
      "step": 1878
    },
    {
      "epoch": 6.39,
      "learning_rate": 7.870074547390843e-06,
      "loss": 3.739,
      "step": 2000
    },
    {
      "epoch": 7.0,
      "eval_loss": 2.8847122192382812,
      "eval_mse_0": 3.114128828048706,
      "eval_mse_1": 2.8679463863372803,
      "eval_mse_2": 2.5041022300720215,
      "eval_mse_3": 3.0526669025421143,
      "eval_pcc_0": 0.2014005597766828,
      "eval_pcc_1": 0.2752976749163899,
      "eval_pcc_2": 0.2578336245727464,
      "eval_pcc_3": 0.20622195975263777,
      "eval_runtime": 110.8767,
      "eval_samples_per_second": 22.548,
      "eval_steps_per_second": 2.823,
      "step": 2191
    },
    {
      "epoch": 7.99,
      "learning_rate": 7.337593184238552e-06,
      "loss": 1.9886,
      "step": 2500
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.4488474130630493,
      "eval_mse_0": 1.6018657684326172,
      "eval_mse_1": 1.287447452545166,
      "eval_mse_2": 1.2784101963043213,
      "eval_mse_3": 1.6276663541793823,
      "eval_pcc_0": 0.5789133492912951,
      "eval_pcc_1": 0.6361586077528624,
      "eval_pcc_2": 0.632331228735609,
      "eval_pcc_3": 0.586059811494472,
      "eval_runtime": 111.6479,
      "eval_samples_per_second": 22.392,
      "eval_steps_per_second": 2.803,
      "step": 2504
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.4175043106079102,
      "eval_mse_0": 1.5901267528533936,
      "eval_mse_1": 1.236507534980774,
      "eval_mse_2": 1.2799756526947021,
      "eval_mse_3": 1.563408613204956,
      "eval_pcc_0": 0.5951684008732291,
      "eval_pcc_1": 0.6345177392482514,
      "eval_pcc_2": 0.6324820584136368,
      "eval_pcc_3": 0.599416701403403,
      "eval_runtime": 111.1053,
      "eval_samples_per_second": 22.501,
      "eval_steps_per_second": 2.817,
      "step": 2817
    },
    {
      "epoch": 9.58,
      "learning_rate": 6.805111821086262e-06,
      "loss": 1.2345,
      "step": 3000
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.326810598373413,
      "eval_mse_0": 1.4957528114318848,
      "eval_mse_1": 1.1522624492645264,
      "eval_mse_2": 1.1763553619384766,
      "eval_mse_3": 1.4828717708587646,
      "eval_pcc_0": 0.6211318661373398,
      "eval_pcc_1": 0.6635137390370865,
      "eval_pcc_2": 0.6612453289580579,
      "eval_pcc_3": 0.6282267414748871,
      "eval_runtime": 114.1222,
      "eval_samples_per_second": 21.906,
      "eval_steps_per_second": 2.743,
      "step": 3130
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.2131879329681396,
      "eval_mse_0": 1.414042592048645,
      "eval_mse_1": 1.0205397605895996,
      "eval_mse_2": 1.0485761165618896,
      "eval_mse_3": 1.3695930242538452,
      "eval_pcc_0": 0.644350906789295,
      "eval_pcc_1": 0.7112895237456786,
      "eval_pcc_2": 0.7048267987221325,
      "eval_pcc_3": 0.6585447340367024,
      "eval_runtime": 113.4335,
      "eval_samples_per_second": 22.039,
      "eval_steps_per_second": 2.759,
      "step": 3443
    },
    {
      "epoch": 11.18,
      "learning_rate": 6.272630457933972e-06,
      "loss": 1.0408,
      "step": 3500
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.224244475364685,
      "eval_mse_0": 1.41946280002594,
      "eval_mse_1": 1.0433218479156494,
      "eval_mse_2": 1.0688689947128296,
      "eval_mse_3": 1.3653244972229004,
      "eval_pcc_0": 0.654669210296219,
      "eval_pcc_1": 0.7077277102518871,
      "eval_pcc_2": 0.7071506583861986,
      "eval_pcc_3": 0.6680765403073837,
      "eval_runtime": 113.1793,
      "eval_samples_per_second": 22.089,
      "eval_steps_per_second": 2.766,
      "step": 3756
    },
    {
      "epoch": 12.78,
      "learning_rate": 5.7401490947816826e-06,
      "loss": 0.9475,
      "step": 4000
    },
    {
      "epoch": 13.0,
      "eval_loss": 1.2053687572479248,
      "eval_mse_0": 1.4129148721694946,
      "eval_mse_1": 1.016390085220337,
      "eval_mse_2": 1.037606120109558,
      "eval_mse_3": 1.354564905166626,
      "eval_pcc_0": 0.6587589554474398,
      "eval_pcc_1": 0.7213830926282636,
      "eval_pcc_2": 0.7173455116943062,
      "eval_pcc_3": 0.673571849988213,
      "eval_runtime": 113.7791,
      "eval_samples_per_second": 21.972,
      "eval_steps_per_second": 2.751,
      "step": 4069
    },
    {
      "epoch": 14.0,
      "eval_loss": 1.128787875175476,
      "eval_mse_0": 1.3153932094573975,
      "eval_mse_1": 0.9470821022987366,
      "eval_mse_2": 0.9719104766845703,
      "eval_mse_3": 1.2807679176330566,
      "eval_pcc_0": 0.6705563948956171,
      "eval_pcc_1": 0.733933193964773,
      "eval_pcc_2": 0.7284221721151036,
      "eval_pcc_3": 0.6844569928653923,
      "eval_runtime": 111.7499,
      "eval_samples_per_second": 22.371,
      "eval_steps_per_second": 2.801,
      "step": 4382
    },
    {
      "epoch": 14.38,
      "learning_rate": 5.207667731629393e-06,
      "loss": 0.8501,
      "step": 4500
    },
    {
      "epoch": 15.0,
      "eval_loss": 1.2822062969207764,
      "eval_mse_0": 1.4862970113754272,
      "eval_mse_1": 1.0724018812179565,
      "eval_mse_2": 1.1084386110305786,
      "eval_mse_3": 1.461689829826355,
      "eval_pcc_0": 0.6635918629322863,
      "eval_pcc_1": 0.7210589341739497,
      "eval_pcc_2": 0.722953278888009,
      "eval_pcc_3": 0.6799461661555959,
      "eval_runtime": 109.4927,
      "eval_samples_per_second": 22.833,
      "eval_steps_per_second": 2.859,
      "step": 4695
    },
    {
      "epoch": 15.97,
      "learning_rate": 4.675186368477103e-06,
      "loss": 0.8033,
      "step": 5000
    },
    {
      "epoch": 16.0,
      "eval_loss": 1.1208453178405762,
      "eval_mse_0": 1.3246564865112305,
      "eval_mse_1": 0.9278814196586609,
      "eval_mse_2": 0.9459223747253418,
      "eval_mse_3": 1.2849211692810059,
      "eval_pcc_0": 0.6705910338352359,
      "eval_pcc_1": 0.7386330251922931,
      "eval_pcc_2": 0.7353766544984371,
      "eval_pcc_3": 0.6855463026259689,
      "eval_runtime": 107.3448,
      "eval_samples_per_second": 23.289,
      "eval_steps_per_second": 2.916,
      "step": 5008
    },
    {
      "epoch": 17.0,
      "eval_loss": 1.165283441543579,
      "eval_mse_0": 1.3421541452407837,
      "eval_mse_1": 0.9892371296882629,
      "eval_mse_2": 1.0137618780136108,
      "eval_mse_3": 1.315979242324829,
      "eval_pcc_0": 0.6838553668596663,
      "eval_pcc_1": 0.7489439409997345,
      "eval_pcc_2": 0.7417229452295838,
      "eval_pcc_3": 0.6974170602560198,
      "eval_runtime": 112.9906,
      "eval_samples_per_second": 22.126,
      "eval_steps_per_second": 2.77,
      "step": 5321
    },
    {
      "epoch": 17.57,
      "learning_rate": 4.142705005324814e-06,
      "loss": 0.7446,
      "step": 5500
    },
    {
      "epoch": 18.0,
      "eval_loss": 1.1435565948486328,
      "eval_mse_0": 1.346588134765625,
      "eval_mse_1": 0.9554901123046875,
      "eval_mse_2": 0.9721121788024902,
      "eval_mse_3": 1.300032377243042,
      "eval_pcc_0": 0.6824018700531469,
      "eval_pcc_1": 0.7410752833267896,
      "eval_pcc_2": 0.7400547744800529,
      "eval_pcc_3": 0.6971319324640849,
      "eval_runtime": 108.927,
      "eval_samples_per_second": 22.951,
      "eval_steps_per_second": 2.873,
      "step": 5634
    },
    {
      "epoch": 19.0,
      "eval_loss": 1.10788893699646,
      "eval_mse_0": 1.3004429340362549,
      "eval_mse_1": 0.9238829016685486,
      "eval_mse_2": 0.9461784958839417,
      "eval_mse_3": 1.2610493898391724,
      "eval_pcc_0": 0.6856875662586791,
      "eval_pcc_1": 0.7445873296604236,
      "eval_pcc_2": 0.7428637183178279,
      "eval_pcc_3": 0.6992689279405016,
      "eval_runtime": 108.4841,
      "eval_samples_per_second": 23.045,
      "eval_steps_per_second": 2.885,
      "step": 5947
    },
    {
      "epoch": 19.17,
      "learning_rate": 3.6102236421725247e-06,
      "loss": 0.7269,
      "step": 6000
    },
    {
      "epoch": 20.0,
      "eval_loss": 1.1264894008636475,
      "eval_mse_0": 1.315398931503296,
      "eval_mse_1": 0.949545681476593,
      "eval_mse_2": 0.9644765853881836,
      "eval_mse_3": 1.2765377759933472,
      "eval_pcc_0": 0.6827338635086919,
      "eval_pcc_1": 0.7438526013196459,
      "eval_pcc_2": 0.7381710855337227,
      "eval_pcc_3": 0.6954272646885774,
      "eval_runtime": 106.5826,
      "eval_samples_per_second": 23.456,
      "eval_steps_per_second": 2.937,
      "step": 6260
    },
    {
      "epoch": 20.77,
      "learning_rate": 3.0777422790202343e-06,
      "loss": 0.6996,
      "step": 6500
    },
    {
      "epoch": 21.0,
      "eval_loss": 1.1285386085510254,
      "eval_mse_0": 1.3255077600479126,
      "eval_mse_1": 0.9515641331672668,
      "eval_mse_2": 0.9579839110374451,
      "eval_mse_3": 1.2790971994400024,
      "eval_pcc_0": 0.6901945193156594,
      "eval_pcc_1": 0.7491408550002535,
      "eval_pcc_2": 0.748197743686794,
      "eval_pcc_3": 0.7056622636182329,
      "eval_runtime": 107.6133,
      "eval_samples_per_second": 23.231,
      "eval_steps_per_second": 2.909,
      "step": 6573
    },
    {
      "epoch": 22.0,
      "eval_loss": 1.0939048528671265,
      "eval_mse_0": 1.2978774309158325,
      "eval_mse_1": 0.9076089859008789,
      "eval_mse_2": 0.9236165881156921,
      "eval_mse_3": 1.2465155124664307,
      "eval_pcc_0": 0.6937146675015498,
      "eval_pcc_1": 0.753625576182672,
      "eval_pcc_2": 0.7519788247786859,
      "eval_pcc_3": 0.7086490221451743,
      "eval_runtime": 107.403,
      "eval_samples_per_second": 23.277,
      "eval_steps_per_second": 2.914,
      "step": 6886
    },
    {
      "epoch": 22.36,
      "learning_rate": 2.5452609158679447e-06,
      "loss": 0.6913,
      "step": 7000
    },
    {
      "epoch": 23.0,
      "eval_loss": 1.1205700635910034,
      "eval_mse_0": 1.3218013048171997,
      "eval_mse_1": 0.9310538172721863,
      "eval_mse_2": 0.9502773284912109,
      "eval_mse_3": 1.2791509628295898,
      "eval_pcc_0": 0.6915934885988795,
      "eval_pcc_1": 0.7504811188809472,
      "eval_pcc_2": 0.7491426176244415,
      "eval_pcc_3": 0.7059594391298436,
      "eval_runtime": 111.053,
      "eval_samples_per_second": 22.512,
      "eval_steps_per_second": 2.818,
      "step": 7199
    },
    {
      "epoch": 23.96,
      "learning_rate": 2.012779552715655e-06,
      "loss": 0.6669,
      "step": 7500
    },
    {
      "epoch": 24.0,
      "eval_loss": 1.1409060955047607,
      "eval_mse_0": 1.3514517545700073,
      "eval_mse_1": 0.949164867401123,
      "eval_mse_2": 0.9572958946228027,
      "eval_mse_3": 1.3057115077972412,
      "eval_pcc_0": 0.685360677136438,
      "eval_pcc_1": 0.7483624265851474,
      "eval_pcc_2": 0.747860167146831,
      "eval_pcc_3": 0.700980006844774,
      "eval_runtime": 111.2658,
      "eval_samples_per_second": 22.469,
      "eval_steps_per_second": 2.813,
      "step": 7512
    },
    {
      "epoch": 25.0,
      "eval_loss": 1.1353332996368408,
      "eval_mse_0": 1.3407591581344604,
      "eval_mse_1": 0.9555139541625977,
      "eval_mse_2": 0.9557929635047913,
      "eval_mse_3": 1.2892675399780273,
      "eval_pcc_0": 0.6901165588720602,
      "eval_pcc_1": 0.7497798135245186,
      "eval_pcc_2": 0.748800124735736,
      "eval_pcc_3": 0.7048397107362878,
      "eval_runtime": 112.4376,
      "eval_samples_per_second": 22.235,
      "eval_steps_per_second": 2.784,
      "step": 7825
    },
    {
      "epoch": 25.56,
      "learning_rate": 1.4802981895633654e-06,
      "loss": 0.6652,
      "step": 8000
    },
    {
      "epoch": 26.0,
      "eval_loss": 1.106658935546875,
      "eval_mse_0": 1.3105865716934204,
      "eval_mse_1": 0.9180678725242615,
      "eval_mse_2": 0.9328413009643555,
      "eval_mse_3": 1.265139102935791,
      "eval_pcc_0": 0.69052729682231,
      "eval_pcc_1": 0.7515881516832139,
      "eval_pcc_2": 0.7502769036586929,
      "eval_pcc_3": 0.704789098042473,
      "eval_runtime": 110.512,
      "eval_samples_per_second": 22.622,
      "eval_steps_per_second": 2.832,
      "step": 8138
    },
    {
      "epoch": 27.0,
      "eval_loss": 1.177926778793335,
      "eval_mse_0": 1.3825031518936157,
      "eval_mse_1": 0.9906836152076721,
      "eval_mse_2": 1.0017260313034058,
      "eval_mse_3": 1.3367940187454224,
      "eval_pcc_0": 0.6879140755970282,
      "eval_pcc_1": 0.745388341373506,
      "eval_pcc_2": 0.7456945121762633,
      "eval_pcc_3": 0.7026128255410367,
      "eval_runtime": 110.9542,
      "eval_samples_per_second": 22.532,
      "eval_steps_per_second": 2.821,
      "step": 8451
    },
    {
      "epoch": 27.16,
      "learning_rate": 9.478168264110757e-07,
      "loss": 0.648,
      "step": 8500
    },
    {
      "epoch": 28.0,
      "eval_loss": 1.1224308013916016,
      "eval_mse_0": 1.323011875152588,
      "eval_mse_1": 0.9357097744941711,
      "eval_mse_2": 0.9498267769813538,
      "eval_mse_3": 1.281173586845398,
      "eval_pcc_0": 0.6914016645884247,
      "eval_pcc_1": 0.7519228063802504,
      "eval_pcc_2": 0.7508387729965698,
      "eval_pcc_3": 0.7061130189116113,
      "eval_runtime": 111.5642,
      "eval_samples_per_second": 22.409,
      "eval_steps_per_second": 2.806,
      "step": 8764
    },
    {
      "epoch": 28.75,
      "learning_rate": 4.1533546325878595e-07,
      "loss": 0.6273,
      "step": 9000
    },
    {
      "epoch": 29.0,
      "eval_loss": 1.1294724941253662,
      "eval_mse_0": 1.330993890762329,
      "eval_mse_1": 0.9427235126495361,
      "eval_mse_2": 0.956869900226593,
      "eval_mse_3": 1.2873003482818604,
      "eval_pcc_0": 0.691092550190147,
      "eval_pcc_1": 0.7512359511723832,
      "eval_pcc_2": 0.7500889691212941,
      "eval_pcc_3": 0.7058747931898186,
      "eval_runtime": 110.429,
      "eval_samples_per_second": 22.639,
      "eval_steps_per_second": 2.834,
      "step": 9077
    },
    {
      "epoch": 30.0,
      "eval_loss": 1.1318851709365845,
      "eval_mse_0": 1.3352088928222656,
      "eval_mse_1": 0.9430738091468811,
      "eval_mse_2": 0.9584095478057861,
      "eval_mse_3": 1.2908461093902588,
      "eval_pcc_0": 0.6912135413860196,
      "eval_pcc_1": 0.7515995503174117,
      "eval_pcc_2": 0.7506598615839062,
      "eval_pcc_3": 0.706160269283068,
      "eval_runtime": 111.4429,
      "eval_samples_per_second": 22.433,
      "eval_steps_per_second": 2.809,
      "step": 9390
    },
    {
      "epoch": 30.0,
      "step": 9390,
      "total_flos": 0.0,
      "train_loss": 5.128481850913539,
      "train_runtime": 9991.0527,
      "train_samples_per_second": 7.507,
      "train_steps_per_second": 0.94
    }
  ],
  "logging_steps": 500,
  "max_steps": 9390,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}