{
  "best_global_step": 2000,
  "best_metric": 0.9834426741643236,
  "best_model_checkpoint": "/kaggle/working/outputs/codebert_rd_keystrokes_v3_1/checkpoint-2000",
  "epoch": 1.8927444794952681,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006309148264984228,
      "grad_norm": 2.571892738342285,
      "learning_rate": 0.0,
      "loss": 0.6932622194290161,
      "step": 1
    },
    {
      "epoch": 0.015772870662460567,
      "grad_norm": 2.436145544052124,
      "learning_rate": 7.570977917981073e-07,
      "loss": 0.7295282681783041,
      "step": 25
    },
    {
      "epoch": 0.031545741324921134,
      "grad_norm": 5.32429838180542,
      "learning_rate": 1.545741324921136e-06,
      "loss": 0.7090779113769531,
      "step": 50
    },
    {
      "epoch": 0.0473186119873817,
      "grad_norm": 5.425052165985107,
      "learning_rate": 2.3343848580441643e-06,
      "loss": 0.6694438171386718,
      "step": 75
    },
    {
      "epoch": 0.06309148264984227,
      "grad_norm": 5.74971866607666,
      "learning_rate": 3.1230283911671926e-06,
      "loss": 0.6196812057495117,
      "step": 100
    },
    {
      "epoch": 0.07886435331230283,
      "grad_norm": 4.759191989898682,
      "learning_rate": 3.911671924290221e-06,
      "loss": 0.43090095520019533,
      "step": 125
    },
    {
      "epoch": 0.0946372239747634,
      "grad_norm": 5.838165283203125,
      "learning_rate": 4.70031545741325e-06,
      "loss": 0.29434648513793943,
      "step": 150
    },
    {
      "epoch": 0.11041009463722397,
      "grad_norm": 6.797428131103516,
      "learning_rate": 5.4889589905362786e-06,
      "loss": 0.1876709747314453,
      "step": 175
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": 3.7547245025634766,
      "learning_rate": 6.2776025236593065e-06,
      "loss": 0.20350841522216798,
      "step": 200
    },
    {
      "epoch": 0.14195583596214512,
      "grad_norm": 11.165263175964355,
      "learning_rate": 7.066246056782335e-06,
      "loss": 0.1446442985534668,
      "step": 225
    },
    {
      "epoch": 0.15772870662460567,
      "grad_norm": 4.109164237976074,
      "learning_rate": 7.854889589905364e-06,
      "loss": 0.17608392715454102,
      "step": 250
    },
    {
      "epoch": 0.17350157728706625,
      "grad_norm": 0.37571197748184204,
      "learning_rate": 8.643533123028391e-06,
      "loss": 0.08311139106750488,
      "step": 275
    },
    {
      "epoch": 0.1892744479495268,
      "grad_norm": 0.21334795653820038,
      "learning_rate": 9.43217665615142e-06,
      "loss": 0.10653317451477051,
      "step": 300
    },
    {
      "epoch": 0.20504731861198738,
      "grad_norm": 0.21560309827327728,
      "learning_rate": 1.022082018927445e-05,
      "loss": 0.12078428268432617,
      "step": 325
    },
    {
      "epoch": 0.22082018927444794,
      "grad_norm": 0.07722581177949905,
      "learning_rate": 1.1009463722397478e-05,
      "loss": 0.10522660255432129,
      "step": 350
    },
    {
      "epoch": 0.23659305993690852,
      "grad_norm": 13.963035583496094,
      "learning_rate": 1.1798107255520506e-05,
      "loss": 0.10268622398376465,
      "step": 375
    },
    {
      "epoch": 0.25236593059936907,
      "grad_norm": 1.7228655815124512,
      "learning_rate": 1.2586750788643533e-05,
      "loss": 0.1168508243560791,
      "step": 400
    },
    {
      "epoch": 0.26813880126182965,
      "grad_norm": 4.807567596435547,
      "learning_rate": 1.3375394321766562e-05,
      "loss": 0.1246561050415039,
      "step": 425
    },
    {
      "epoch": 0.28391167192429023,
      "grad_norm": 0.10336830466985703,
      "learning_rate": 1.4164037854889591e-05,
      "loss": 0.06862223625183106,
      "step": 450
    },
    {
      "epoch": 0.2996845425867508,
      "grad_norm": 0.18726640939712524,
      "learning_rate": 1.495268138801262e-05,
      "loss": 0.10785533905029297,
      "step": 475
    },
    {
      "epoch": 0.31545741324921134,
      "grad_norm": 7.849733829498291,
      "learning_rate": 1.574132492113565e-05,
      "loss": 0.08045989990234376,
      "step": 500
    },
    {
      "epoch": 0.31545741324921134,
      "eval_accuracy": 0.9766561514195583,
      "eval_f1": 0.976932668329177,
      "eval_loss": 0.11268972605466843,
      "eval_precision": 0.9654959950708565,
      "eval_recall": 0.9886435331230284,
      "eval_runtime": 56.1856,
      "eval_samples_per_second": 56.42,
      "eval_steps_per_second": 3.542,
      "step": 500
    },
    {
      "epoch": 0.3312302839116719,
      "grad_norm": 7.707481861114502,
      "learning_rate": 1.6529968454258676e-05,
      "loss": 0.12939174652099608,
      "step": 525
    },
    {
      "epoch": 0.3470031545741325,
      "grad_norm": 1.8563039302825928,
      "learning_rate": 1.7318611987381703e-05,
      "loss": 0.14456929206848146,
      "step": 550
    },
    {
      "epoch": 0.3627760252365931,
      "grad_norm": 9.819541931152344,
      "learning_rate": 1.8107255520504733e-05,
      "loss": 0.09543749809265137,
      "step": 575
    },
    {
      "epoch": 0.3785488958990536,
      "grad_norm": 2.0916662216186523,
      "learning_rate": 1.889589905362776e-05,
      "loss": 0.11727660179138183,
      "step": 600
    },
    {
      "epoch": 0.3943217665615142,
      "grad_norm": 4.153768539428711,
      "learning_rate": 1.968454258675079e-05,
      "loss": 0.1419176959991455,
      "step": 625
    },
    {
      "epoch": 0.41009463722397477,
      "grad_norm": 0.3790145814418793,
      "learning_rate": 1.999965897496297e-05,
      "loss": 0.0911902904510498,
      "step": 650
    },
    {
      "epoch": 0.42586750788643535,
      "grad_norm": 5.445947170257568,
      "learning_rate": 1.9997575017301754e-05,
      "loss": 0.14416172981262207,
      "step": 675
    },
    {
      "epoch": 0.4416403785488959,
      "grad_norm": 0.33051055669784546,
      "learning_rate": 1.999359695467383e-05,
      "loss": 0.14161142349243164,
      "step": 700
    },
    {
      "epoch": 0.45741324921135645,
      "grad_norm": 1.2220453023910522,
      "learning_rate": 1.998772554074878e-05,
      "loss": 0.13508522033691406,
      "step": 725
    },
    {
      "epoch": 0.47318611987381703,
      "grad_norm": 16.0678768157959,
      "learning_rate": 1.9979961887903783e-05,
      "loss": 0.14012475967407226,
      "step": 750
    },
    {
      "epoch": 0.4889589905362776,
      "grad_norm": 9.829991340637207,
      "learning_rate": 1.9970307467012862e-05,
      "loss": 0.08824824333190918,
      "step": 775
    },
    {
      "epoch": 0.5047318611987381,
      "grad_norm": 0.48923227190971375,
      "learning_rate": 1.9958764107168226e-05,
      "loss": 0.14100438117980957,
      "step": 800
    },
    {
      "epoch": 0.5205047318611987,
      "grad_norm": 10.579341888427734,
      "learning_rate": 1.994533399533373e-05,
      "loss": 0.09922822952270507,
      "step": 825
    },
    {
      "epoch": 0.5362776025236593,
      "grad_norm": 0.25369012355804443,
      "learning_rate": 1.9930019675930546e-05,
      "loss": 0.09808570861816407,
      "step": 850
    },
    {
      "epoch": 0.5520504731861199,
      "grad_norm": 0.5847018361091614,
      "learning_rate": 1.99128240503551e-05,
      "loss": 0.08875894546508789,
      "step": 875
    },
    {
      "epoch": 0.5678233438485805,
      "grad_norm": 0.4339558482170105,
      "learning_rate": 1.9893750376429396e-05,
      "loss": 0.11056282043457032,
      "step": 900
    },
    {
      "epoch": 0.583596214511041,
      "grad_norm": 2.8855783939361572,
      "learning_rate": 1.9872802267783777e-05,
      "loss": 0.09730767250061036,
      "step": 925
    },
    {
      "epoch": 0.5993690851735016,
      "grad_norm": 6.300772666931152,
      "learning_rate": 1.9849983693172324e-05,
      "loss": 0.10335501670837402,
      "step": 950
    },
    {
      "epoch": 0.6151419558359621,
      "grad_norm": 0.1946100890636444,
      "learning_rate": 1.9825298975720938e-05,
      "loss": 0.06983193874359131,
      "step": 975
    },
    {
      "epoch": 0.6309148264984227,
      "grad_norm": 0.05659753456711769,
      "learning_rate": 1.97987527921083e-05,
      "loss": 0.06307486057281494,
      "step": 1000
    },
    {
      "epoch": 0.6309148264984227,
      "eval_accuracy": 0.9788643533123028,
      "eval_f1": 0.9791860826343585,
      "eval_loss": 0.10372021794319153,
      "eval_precision": 0.9645042839657283,
      "eval_recall": 0.9943217665615142,
      "eval_runtime": 56.2004,
      "eval_samples_per_second": 56.405,
      "eval_steps_per_second": 3.541,
      "step": 1000
    },
    {
      "epoch": 0.6466876971608833,
      "grad_norm": 0.0960870087146759,
      "learning_rate": 1.977035017167984e-05,
      "loss": 0.07478074073791503,
      "step": 1025
    },
    {
      "epoch": 0.6624605678233438,
      "grad_norm": 2.863891124725342,
      "learning_rate": 1.974009649549489e-05,
      "loss": 0.07338234424591064,
      "step": 1050
    },
    {
      "epoch": 0.6782334384858044,
      "grad_norm": 0.3583734631538391,
      "learning_rate": 1.9707997495307232e-05,
      "loss": 0.10608007431030274,
      "step": 1075
    },
    {
      "epoch": 0.694006309148265,
      "grad_norm": 0.8535360097885132,
      "learning_rate": 1.9674059252479156e-05,
      "loss": 0.07668295860290528,
      "step": 1100
    },
    {
      "epoch": 0.7097791798107256,
      "grad_norm": 0.4096319377422333,
      "learning_rate": 1.9638288196829303e-05,
      "loss": 0.07370511531829833,
      "step": 1125
    },
    {
      "epoch": 0.7255520504731862,
      "grad_norm": 0.10992075502872467,
      "learning_rate": 1.9600691105414523e-05,
      "loss": 0.04484860897064209,
      "step": 1150
    },
    {
      "epoch": 0.7413249211356467,
      "grad_norm": 4.087841510772705,
      "learning_rate": 1.9561275101245886e-05,
      "loss": 0.15258366584777833,
      "step": 1175
    },
    {
      "epoch": 0.7570977917981072,
      "grad_norm": 2.7859838008880615,
      "learning_rate": 1.95200476519392e-05,
      "loss": 0.12657273292541504,
      "step": 1200
    },
    {
      "epoch": 0.7728706624605678,
      "grad_norm": 0.08890348672866821,
      "learning_rate": 1.9477016568300233e-05,
      "loss": 0.058558349609375,
      "step": 1225
    },
    {
      "epoch": 0.7886435331230284,
      "grad_norm": 2.4231088161468506,
      "learning_rate": 1.9432190002844868e-05,
      "loss": 0.08944664001464844,
      "step": 1250
    },
    {
      "epoch": 0.804416403785489,
      "grad_norm": 0.15423132479190826,
      "learning_rate": 1.93855764482546e-05,
      "loss": 0.07989122390747071,
      "step": 1275
    },
    {
      "epoch": 0.8201892744479495,
      "grad_norm": 0.1543116569519043,
      "learning_rate": 1.933718473576751e-05,
      "loss": 0.0904345703125,
      "step": 1300
    },
    {
      "epoch": 0.8359621451104101,
      "grad_norm": 0.2740912139415741,
      "learning_rate": 1.9287024033505156e-05,
      "loss": 0.08953811645507813,
      "step": 1325
    },
    {
      "epoch": 0.8517350157728707,
      "grad_norm": 0.06053502485156059,
      "learning_rate": 1.9235103844735587e-05,
      "loss": 0.09112126350402833,
      "step": 1350
    },
    {
      "epoch": 0.8675078864353313,
      "grad_norm": 3.397080898284912,
      "learning_rate": 1.9181434006072906e-05,
      "loss": 0.10066482543945313,
      "step": 1375
    },
    {
      "epoch": 0.8832807570977917,
      "grad_norm": 0.24578048288822174,
      "learning_rate": 1.9126024685613664e-05,
      "loss": 0.06111194610595703,
      "step": 1400
    },
    {
      "epoch": 0.8990536277602523,
      "grad_norm": 0.09262054413557053,
      "learning_rate": 1.9068886381010424e-05,
      "loss": 0.07008316040039063,
      "step": 1425
    },
    {
      "epoch": 0.9148264984227129,
      "grad_norm": 1.9535330533981323,
      "learning_rate": 1.9010029917482943e-05,
      "loss": 0.14111000061035156,
      "step": 1450
    },
    {
      "epoch": 0.9305993690851735,
      "grad_norm": 0.1983080357313156,
      "learning_rate": 1.894946644576724e-05,
      "loss": 0.07531814575195313,
      "step": 1475
    },
    {
      "epoch": 0.9463722397476341,
      "grad_norm": 0.09421352297067642,
      "learning_rate": 1.8887207440003028e-05,
      "loss": 0.09356441497802734,
      "step": 1500
    },
    {
      "epoch": 0.9463722397476341,
      "eval_accuracy": 0.9782334384858045,
      "eval_f1": 0.9782677165354331,
      "eval_loss": 0.07328534126281738,
      "eval_precision": 0.9767295597484277,
      "eval_recall": 0.9798107255520505,
      "eval_runtime": 55.7759,
      "eval_samples_per_second": 56.835,
      "eval_steps_per_second": 3.568,
      "step": 1500
    },
    {
      "epoch": 0.9621451104100947,
      "grad_norm": 0.23979413509368896,
      "learning_rate": 1.8823264695559876e-05,
      "loss": 0.04988880157470703,
      "step": 1525
    },
    {
      "epoch": 0.9779179810725552,
      "grad_norm": 0.1378251314163208,
      "learning_rate": 1.8757650326802474e-05,
      "loss": 0.03976966857910156,
      "step": 1550
    },
    {
      "epoch": 0.9936908517350158,
      "grad_norm": 0.06288843601942062,
      "learning_rate": 1.8690376764795512e-05,
      "loss": 0.08686065673828125,
      "step": 1575
    },
    {
      "epoch": 1.0094637223974763,
      "grad_norm": 5.365837097167969,
      "learning_rate": 1.8621456754948524e-05,
      "loss": 0.05250164031982422,
      "step": 1600
    },
    {
      "epoch": 1.025236593059937,
      "grad_norm": 0.18591798841953278,
      "learning_rate": 1.8550903354601182e-05,
      "loss": 0.05328141212463379,
      "step": 1625
    },
    {
      "epoch": 1.0410094637223974,
      "grad_norm": 0.14107061922550201,
      "learning_rate": 1.847872993054952e-05,
      "loss": 0.0559916353225708,
      "step": 1650
    },
    {
      "epoch": 1.0567823343848581,
      "grad_norm": 6.363674163818359,
      "learning_rate": 1.840495015651348e-05,
      "loss": 0.1134580421447754,
      "step": 1675
    },
    {
      "epoch": 1.0725552050473186,
      "grad_norm": 0.072722889482975,
      "learning_rate": 1.8329578010546364e-05,
      "loss": 0.04161137580871582,
      "step": 1700
    },
    {
      "epoch": 1.088328075709779,
      "grad_norm": 7.499703884124756,
      "learning_rate": 1.825262777238659e-05,
      "loss": 0.07552608013153077,
      "step": 1725
    },
    {
      "epoch": 1.1041009463722398,
      "grad_norm": 0.034939683973789215,
      "learning_rate": 1.817411402075229e-05,
      "loss": 0.07142114162445068,
      "step": 1750
    },
    {
      "epoch": 1.1198738170347002,
      "grad_norm": 0.19647593796253204,
      "learning_rate": 1.809405163057931e-05,
      "loss": 0.09205500602722168,
      "step": 1775
    },
    {
      "epoch": 1.135646687697161,
      "grad_norm": 0.1461659073829651,
      "learning_rate": 1.8012455770203038e-05,
      "loss": 0.06862086296081543,
      "step": 1800
    },
    {
      "epoch": 1.1514195583596214,
      "grad_norm": 0.09000778943300247,
      "learning_rate": 1.7929341898484653e-05,
      "loss": 0.03869293212890625,
      "step": 1825
    },
    {
      "epoch": 1.167192429022082,
      "grad_norm": 3.4395689964294434,
      "learning_rate": 1.784472576188237e-05,
      "loss": 0.10784174919128418,
      "step": 1850
    },
    {
      "epoch": 1.1829652996845426,
      "grad_norm": 6.185035228729248,
      "learning_rate": 1.775862339146815e-05,
      "loss": 0.08741586685180663,
      "step": 1875
    },
    {
      "epoch": 1.1987381703470033,
      "grad_norm": 0.03306306153535843,
      "learning_rate": 1.7671051099890538e-05,
      "loss": 0.03821196556091309,
      "step": 1900
    },
    {
      "epoch": 1.2145110410094637,
      "grad_norm": 0.11795313656330109,
      "learning_rate": 1.758202547828409e-05,
      "loss": 0.05004812240600586,
      "step": 1925
    },
    {
      "epoch": 1.2302839116719242,
      "grad_norm": 0.27102428674697876,
      "learning_rate": 1.74915633931261e-05,
      "loss": 0.09024031639099121,
      "step": 1950
    },
    {
      "epoch": 1.2460567823343849,
      "grad_norm": 0.1362110674381256,
      "learning_rate": 1.739968198304114e-05,
      "loss": 0.0506083345413208,
      "step": 1975
    },
    {
      "epoch": 1.2618296529968454,
      "grad_norm": 0.05871753394603729,
      "learning_rate": 1.7306398655554023e-05,
      "loss": 0.12149024963378906,
      "step": 2000
    },
    {
      "epoch": 1.2618296529968454,
      "eval_accuracy": 0.9832807570977918,
      "eval_f1": 0.9834426741643236,
      "eval_loss": 0.0678657591342926,
      "eval_precision": 0.974009900990099,
      "eval_recall": 0.9930599369085173,
      "eval_runtime": 56.2139,
      "eval_samples_per_second": 56.392,
      "eval_steps_per_second": 3.54,
      "step": 2000
    },
    {
      "epoch": 1.277602523659306,
      "grad_norm": 14.435188293457031,
      "learning_rate": 1.721173108379184e-05,
      "loss": 0.09227321624755859,
      "step": 2025
    },
    {
      "epoch": 1.2933753943217665,
      "grad_norm": 0.14022010564804077,
      "learning_rate": 1.711569720313568e-05,
      "loss": 0.07053103446960449,
      "step": 2050
    },
    {
      "epoch": 1.3091482649842272,
      "grad_norm": 0.17620061337947845,
      "learning_rate": 1.701831520782264e-05,
      "loss": 0.07794711112976074,
      "step": 2075
    },
    {
      "epoch": 1.3249211356466877,
      "grad_norm": 6.461155891418457,
      "learning_rate": 1.6919603547498832e-05,
      "loss": 0.05158097267150879,
      "step": 2100
    },
    {
      "epoch": 1.3406940063091484,
      "grad_norm": 8.352033615112305,
      "learning_rate": 1.6819580923723957e-05,
      "loss": 0.04181491374969482,
      "step": 2125
    },
    {
      "epoch": 1.3564668769716088,
      "grad_norm": 0.052411582320928574,
      "learning_rate": 1.671826628642819e-05,
      "loss": 0.049018054008483886,
      "step": 2150
    },
    {
      "epoch": 1.3722397476340693,
      "grad_norm": 0.0428645983338356,
      "learning_rate": 1.6615678830321987e-05,
      "loss": 0.06123344898223877,
      "step": 2175
    },
    {
      "epoch": 1.38801261829653,
      "grad_norm": 0.12796339392662048,
      "learning_rate": 1.651183799125952e-05,
      "loss": 0.06224549293518066,
      "step": 2200
    },
    {
      "epoch": 1.4037854889589905,
      "grad_norm": 0.3184094727039337,
      "learning_rate": 1.640676344255643e-05,
      "loss": 0.04998977661132813,
      "step": 2225
    },
    {
      "epoch": 1.4195583596214512,
      "grad_norm": 0.08195166289806366,
      "learning_rate": 1.6300475091262615e-05,
      "loss": 0.07321974277496338,
      "step": 2250
    },
    {
      "epoch": 1.4353312302839116,
      "grad_norm": 3.03761625289917,
      "learning_rate": 1.6192993074390658e-05,
      "loss": 0.08428791999816894,
      "step": 2275
    },
    {
      "epoch": 1.4511041009463723,
      "grad_norm": 0.41116461157798767,
      "learning_rate": 1.6084337755100795e-05,
      "loss": 0.06157721996307373,
      "step": 2300
    },
    {
      "epoch": 1.4668769716088328,
      "grad_norm": 4.645056247711182,
      "learning_rate": 1.597452971884296e-05,
      "loss": 0.09335646629333497,
      "step": 2325
    },
    {
      "epoch": 1.4826498422712935,
      "grad_norm": 0.07679587602615356,
      "learning_rate": 1.5863589769456725e-05,
      "loss": 0.035682902336120606,
      "step": 2350
    },
    {
      "epoch": 1.498422712933754,
      "grad_norm": 16.212730407714844,
      "learning_rate": 1.575153892522991e-05,
      "loss": 0.08860483169555664,
      "step": 2375
    },
    {
      "epoch": 1.5141955835962144,
      "grad_norm": 0.035901762545108795,
      "learning_rate": 1.5638398414916504e-05,
      "loss": 0.06739212989807129,
      "step": 2400
    },
    {
      "epoch": 1.5299684542586751,
      "grad_norm": 14.2339448928833,
      "learning_rate": 1.552418967371476e-05,
      "loss": 0.03637696027755737,
      "step": 2425
    },
    {
      "epoch": 1.5457413249211358,
      "grad_norm": 0.021874595433473587,
      "learning_rate": 1.540893433920614e-05,
      "loss": 0.03717231750488281,
      "step": 2450
    },
    {
      "epoch": 1.5615141955835963,
      "grad_norm": 0.048296067863702774,
      "learning_rate": 1.5292654247255976e-05,
      "loss": 0.02598174810409546,
      "step": 2475
    },
    {
      "epoch": 1.5772870662460567,
      "grad_norm": 9.524810791015625,
      "learning_rate": 1.5175371427876462e-05,
      "loss": 0.06133613586425781,
      "step": 2500
    },
    {
      "epoch": 1.5772870662460567,
      "eval_accuracy": 0.9826498422712934,
      "eval_f1": 0.9827963715983735,
      "eval_loss": 0.07992753386497498,
      "eval_precision": 0.9745657568238213,
      "eval_recall": 0.9911671924290221,
      "eval_runtime": 55.9735,
      "eval_samples_per_second": 56.634,
      "eval_steps_per_second": 3.555,
      "step": 2500
    },
    {
      "epoch": 1.5930599369085172,
      "grad_norm": 0.015798641368746758,
      "learning_rate": 1.5057108101052978e-05,
      "loss": 0.05316779613494873,
      "step": 2525
    },
    {
      "epoch": 1.608832807570978,
      "grad_norm": 1.9981679916381836,
      "learning_rate": 1.4937886672534355e-05,
      "loss": 0.04096637725830078,
      "step": 2550
    },
    {
      "epoch": 1.6246056782334386,
      "grad_norm": 14.948141098022461,
      "learning_rate": 1.4817729729587951e-05,
      "loss": 0.11973735809326172,
      "step": 2575
    },
    {
      "epoch": 1.640378548895899,
      "grad_norm": 10.006237030029297,
      "learning_rate": 1.4696660036720366e-05,
      "loss": 0.07024142742156983,
      "step": 2600
    },
    {
      "epoch": 1.6561514195583595,
      "grad_norm": 2.659205436706543,
      "learning_rate": 1.4574700531364538e-05,
      "loss": 0.05831857681274414,
      "step": 2625
    },
    {
      "epoch": 1.6719242902208202,
      "grad_norm": 0.023404600098729134,
      "learning_rate": 1.445187431953413e-05,
      "loss": 0.012276544570922851,
      "step": 2650
    },
    {
      "epoch": 1.687697160883281,
      "grad_norm": 0.05033299699425697,
      "learning_rate": 1.4328204671445906e-05,
      "loss": 0.04452509880065918,
      "step": 2675
    },
    {
      "epoch": 1.7034700315457414,
      "grad_norm": 0.008091382682323456,
      "learning_rate": 1.4203715017111077e-05,
      "loss": 0.03908012628555298,
      "step": 2700
    },
    {
      "epoch": 1.7192429022082019,
      "grad_norm": 0.8330066800117493,
      "learning_rate": 1.4078428941896308e-05,
      "loss": 0.07871007442474365,
      "step": 2725
    },
    {
      "epoch": 1.7350157728706623,
      "grad_norm": 0.20014899969100952,
      "learning_rate": 1.3952370182055332e-05,
      "loss": 0.05369951725006104,
      "step": 2750
    },
    {
      "epoch": 1.750788643533123,
      "grad_norm": 5.281189918518066,
      "learning_rate": 1.3825562620231962e-05,
      "loss": 0.06861288547515869,
      "step": 2775
    },
    {
      "epoch": 1.7665615141955837,
      "grad_norm": 13.993217468261719,
      "learning_rate": 1.3698030280935365e-05,
      "loss": 0.0692290210723877,
      "step": 2800
    },
    {
      "epoch": 1.7823343848580442,
      "grad_norm": 0.19194826483726501,
      "learning_rate": 1.356979732598847e-05,
      "loss": 0.0943898868560791,
      "step": 2825
    },
    {
      "epoch": 1.7981072555205047,
      "grad_norm": 0.24530774354934692,
      "learning_rate": 1.3440888049950352e-05,
      "loss": 0.05583916664123535,
      "step": 2850
    },
    {
      "epoch": 1.8138801261829653,
      "grad_norm": 23.30782699584961,
      "learning_rate": 1.3311326875513473e-05,
      "loss": 0.06628149509429931,
      "step": 2875
    },
    {
      "epoch": 1.8296529968454258,
      "grad_norm": 5.725240230560303,
      "learning_rate": 1.3181138348876637e-05,
      "loss": 0.08753268241882324,
      "step": 2900
    },
    {
      "epoch": 1.8454258675078865,
      "grad_norm": 3.2451798915863037,
      "learning_rate": 1.305034713509457e-05,
      "loss": 0.04335375308990479,
      "step": 2925
    },
    {
      "epoch": 1.861198738170347,
      "grad_norm": 8.147355079650879,
      "learning_rate": 1.2918978013404961e-05,
      "loss": 0.08735511779785156,
      "step": 2950
    },
    {
      "epoch": 1.8769716088328074,
      "grad_norm": 0.31234487891197205,
      "learning_rate": 1.2787055872533867e-05,
      "loss": 0.04033580780029297,
      "step": 2975
    },
    {
      "epoch": 1.8927444794952681,
      "grad_norm": 2.878502368927002,
      "learning_rate": 1.2654605705980394e-05,
      "loss": 0.07418310165405273,
      "step": 3000
    },
    {
      "epoch": 1.8927444794952681,
      "eval_accuracy": 0.9823343848580441,
      "eval_f1": 0.982532751091703,
      "eval_loss": 0.09431762993335724,
      "eval_precision": 0.9716224552745218,
      "eval_recall": 0.9936908517350158,
      "eval_runtime": 55.9884,
      "eval_samples_per_second": 56.619,
      "eval_steps_per_second": 3.554,
      "step": 3000
    }
  ],
  "logging_steps": 25,
  "max_steps": 6340,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.257414311341824e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}