{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 8.952899961074348, "eval_steps": 3450, "global_step": 69000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00324380433372259, "grad_norm": 0.05141296982765198, "learning_rate": 1.7391304347826088e-07, "loss": 0.0025813066959381103, "step": 25 }, { "epoch": 0.00648760866744518, "grad_norm": 0.0974268689751625, "learning_rate": 3.5507246376811595e-07, "loss": 0.002331161051988602, "step": 50 }, { "epoch": 0.00973141300116777, "grad_norm": 0.060197193175554276, "learning_rate": 5.36231884057971e-07, "loss": 0.002056766003370285, "step": 75 }, { "epoch": 0.01297521733489036, "grad_norm": 0.05937616154551506, "learning_rate": 7.17391304347826e-07, "loss": 0.0017064353823661805, "step": 100 }, { "epoch": 0.01621902166861295, "grad_norm": 0.12638454139232635, "learning_rate": 8.985507246376812e-07, "loss": 0.0015323017537593841, "step": 125 }, { "epoch": 0.01946282600233554, "grad_norm": 0.018911661580204964, "learning_rate": 1.0797101449275362e-06, "loss": 0.0011247570812702179, "step": 150 }, { "epoch": 0.022706630336058128, "grad_norm": 0.02503705769777298, "learning_rate": 1.2608695652173913e-06, "loss": 0.0010170405358076095, "step": 175 }, { "epoch": 0.02595043466978072, "grad_norm": 0.020587332546710968, "learning_rate": 1.4420289855072464e-06, "loss": 0.0008276050537824631, "step": 200 }, { "epoch": 0.02919423900350331, "grad_norm": 0.012301432900130749, "learning_rate": 1.6231884057971016e-06, "loss": 0.0008731838315725327, "step": 225 }, { "epoch": 0.0324380433372259, "grad_norm": 0.006783554796129465, "learning_rate": 1.8043478260869565e-06, "loss": 0.000760069489479065, "step": 250 }, { "epoch": 0.03568184767094849, "grad_norm": 0.004715466406196356, "learning_rate": 1.9855072463768116e-06, "loss": 0.0006436597555875778, "step": 275 }, { "epoch": 0.03892565200467108, "grad_norm": 0.004261302296072245, "learning_rate": 2.166666666666667e-06, "loss": 0.0007200171053409576, "step": 300 }, { "epoch": 0.04216945633839367, "grad_norm": 0.002361537190154195, "learning_rate": 2.347826086956522e-06, "loss": 0.0006688187271356583, "step": 325 }, { "epoch": 0.045413260672116255, "grad_norm": 0.004880121909081936, "learning_rate": 2.5289855072463768e-06, "loss": 0.0006225276738405228, "step": 350 }, { "epoch": 0.04865706500583885, "grad_norm": 0.0020660394802689552, "learning_rate": 2.710144927536232e-06, "loss": 0.0006154324859380722, "step": 375 }, { "epoch": 0.05190086933956144, "grad_norm": 0.0032158500980585814, "learning_rate": 2.8913043478260875e-06, "loss": 0.0005973343551158905, "step": 400 }, { "epoch": 0.05514467367328403, "grad_norm": 0.001472849864512682, "learning_rate": 3.072463768115942e-06, "loss": 0.0005997012555599212, "step": 425 }, { "epoch": 0.05838847800700662, "grad_norm": 0.0012334056664258242, "learning_rate": 3.2536231884057973e-06, "loss": 0.0005134398490190506, "step": 450 }, { "epoch": 0.061632282340729205, "grad_norm": 0.0011471605394035578, "learning_rate": 3.4347826086956526e-06, "loss": 0.0005609684810042381, "step": 475 }, { "epoch": 0.0648760866744518, "grad_norm": 0.003634745953604579, "learning_rate": 3.6159420289855076e-06, "loss": 0.0005645314604043961, "step": 500 }, { "epoch": 0.0681198910081744, "grad_norm": 0.00293130986392498, "learning_rate": 3.797101449275362e-06, "loss": 0.0005989821627736091, "step": 525 }, { "epoch": 0.07136369534189697, "grad_norm": 0.004184110090136528, "learning_rate": 3.978260869565217e-06, "loss": 0.0005207720771431923, "step": 550 }, { "epoch": 0.07460749967561957, "grad_norm": 0.0025407953653484583, "learning_rate": 4.159420289855073e-06, "loss": 0.0005049428343772888, "step": 575 }, { "epoch": 0.07785130400934216, "grad_norm": 0.0026248216163367033, "learning_rate": 4.340579710144928e-06, "loss": 0.0005791663005948066, "step": 600 }, { "epoch": 0.08109510834306474, "grad_norm": 0.004407739732414484, "learning_rate": 4.5217391304347826e-06, "loss": 0.0005084014311432838, "step": 625 }, { "epoch": 0.08433891267678734, "grad_norm": 0.0014522788114845753, "learning_rate": 4.702898550724638e-06, "loss": 0.0004914506897330284, "step": 650 }, { "epoch": 0.08758271701050993, "grad_norm": 0.0014807373518124223, "learning_rate": 4.884057971014493e-06, "loss": 0.00047999877482652665, "step": 675 }, { "epoch": 0.09082652134423251, "grad_norm": 0.0020373279694467783, "learning_rate": 5.065217391304348e-06, "loss": 0.0005152805894613266, "step": 700 }, { "epoch": 0.0940703256779551, "grad_norm": 0.003168275346979499, "learning_rate": 5.246376811594203e-06, "loss": 0.00048413489013910294, "step": 725 }, { "epoch": 0.0973141300116777, "grad_norm": 0.004898744635283947, "learning_rate": 5.427536231884058e-06, "loss": 0.0005498705059289932, "step": 750 }, { "epoch": 0.10055793434540028, "grad_norm": 0.004435047972947359, "learning_rate": 5.608695652173914e-06, "loss": 0.0004970967397093773, "step": 775 }, { "epoch": 0.10380173867912287, "grad_norm": 0.0015721892705187201, "learning_rate": 5.789855072463768e-06, "loss": 0.00044149864464998245, "step": 800 }, { "epoch": 0.10704554301284547, "grad_norm": 0.002494214801117778, "learning_rate": 5.9710144927536236e-06, "loss": 0.0005083100870251656, "step": 825 }, { "epoch": 0.11028934734656806, "grad_norm": 0.00390894478186965, "learning_rate": 6.152173913043478e-06, "loss": 0.0005286858975887299, "step": 850 }, { "epoch": 0.11353315168029064, "grad_norm": 0.0022070640698075294, "learning_rate": 6.333333333333334e-06, "loss": 0.0004761030524969101, "step": 875 }, { "epoch": 0.11677695601401324, "grad_norm": 0.0014910978497937322, "learning_rate": 6.514492753623189e-06, "loss": 0.0005094735696911811, "step": 900 }, { "epoch": 0.12002076034773583, "grad_norm": 0.001773303491063416, "learning_rate": 6.695652173913043e-06, "loss": 0.0004921802505850792, "step": 925 }, { "epoch": 0.12326456468145841, "grad_norm": 0.003881123149767518, "learning_rate": 6.876811594202899e-06, "loss": 0.0005153115466237069, "step": 950 }, { "epoch": 0.126508369015181, "grad_norm": 0.001636817934922874, "learning_rate": 7.057971014492754e-06, "loss": 0.00047637633979320527, "step": 975 }, { "epoch": 0.1297521733489036, "grad_norm": 0.005107464734464884, "learning_rate": 7.239130434782609e-06, "loss": 0.00046688809990882876, "step": 1000 }, { "epoch": 0.1329959776826262, "grad_norm": 0.0030217007733881474, "learning_rate": 7.420289855072464e-06, "loss": 0.0004785720258951187, "step": 1025 }, { "epoch": 0.1362397820163488, "grad_norm": 0.006263422779738903, "learning_rate": 7.60144927536232e-06, "loss": 0.0004970680177211761, "step": 1050 }, { "epoch": 0.13948358635007135, "grad_norm": 0.0033930917270481586, "learning_rate": 7.782608695652174e-06, "loss": 0.0004636504501104355, "step": 1075 }, { "epoch": 0.14272739068379395, "grad_norm": 0.0035221802536398172, "learning_rate": 7.963768115942028e-06, "loss": 0.0004412958770990372, "step": 1100 }, { "epoch": 0.14597119501751654, "grad_norm": 0.0014686498325318098, "learning_rate": 8.144927536231884e-06, "loss": 0.0004344014450907707, "step": 1125 }, { "epoch": 0.14921499935123914, "grad_norm": 0.0019228701712563634, "learning_rate": 8.326086956521739e-06, "loss": 0.0004539357125759125, "step": 1150 }, { "epoch": 0.15245880368496173, "grad_norm": 0.004714014939963818, "learning_rate": 8.507246376811595e-06, "loss": 0.0004735227301716804, "step": 1175 }, { "epoch": 0.15570260801868432, "grad_norm": 0.004593547433614731, "learning_rate": 8.68840579710145e-06, "loss": 0.00042663853615522386, "step": 1200 }, { "epoch": 0.1589464123524069, "grad_norm": 0.002020610496401787, "learning_rate": 8.869565217391304e-06, "loss": 0.00046691443771123886, "step": 1225 }, { "epoch": 0.16219021668612948, "grad_norm": 0.0032152580097317696, "learning_rate": 9.05072463768116e-06, "loss": 0.00043172620236873625, "step": 1250 }, { "epoch": 0.16543402101985208, "grad_norm": 0.0020857735071331263, "learning_rate": 9.231884057971015e-06, "loss": 0.0003932983800768852, "step": 1275 }, { "epoch": 0.16867782535357467, "grad_norm": 0.0008437855285592377, "learning_rate": 9.41304347826087e-06, "loss": 0.00037540558725595474, "step": 1300 }, { "epoch": 0.17192162968729727, "grad_norm": 0.0027162490878254175, "learning_rate": 9.594202898550725e-06, "loss": 0.0004056233912706375, "step": 1325 }, { "epoch": 0.17516543402101986, "grad_norm": 0.0031992075964808464, "learning_rate": 9.775362318840581e-06, "loss": 0.0004178621247410774, "step": 1350 }, { "epoch": 0.17840923835474246, "grad_norm": 0.006124439183622599, "learning_rate": 9.956521739130436e-06, "loss": 0.0004422289878129959, "step": 1375 }, { "epoch": 0.18165304268846502, "grad_norm": 0.004308260977268219, "learning_rate": 1.013768115942029e-05, "loss": 0.00043031245470046995, "step": 1400 }, { "epoch": 0.18489684702218762, "grad_norm": 0.0035516340285539627, "learning_rate": 1.0318840579710145e-05, "loss": 0.00038556307554244996, "step": 1425 }, { "epoch": 0.1881406513559102, "grad_norm": 0.0009919556323438883, "learning_rate": 1.05e-05, "loss": 0.0003632174804806709, "step": 1450 }, { "epoch": 0.1913844556896328, "grad_norm": 0.0016671878984197974, "learning_rate": 1.0681159420289856e-05, "loss": 0.0003770742192864418, "step": 1475 }, { "epoch": 0.1946282600233554, "grad_norm": 0.0020221315789967775, "learning_rate": 1.086231884057971e-05, "loss": 0.0003879324346780777, "step": 1500 }, { "epoch": 0.197872064357078, "grad_norm": 0.0025490059051662683, "learning_rate": 1.1043478260869566e-05, "loss": 0.0004146729782223701, "step": 1525 }, { "epoch": 0.20111586869080056, "grad_norm": 0.0035585095174610615, "learning_rate": 1.122463768115942e-05, "loss": 0.0004313819482922554, "step": 1550 }, { "epoch": 0.20435967302452315, "grad_norm": 0.0038785876240581274, "learning_rate": 1.1405797101449275e-05, "loss": 0.0004499450325965881, "step": 1575 }, { "epoch": 0.20760347735824575, "grad_norm": 0.0020563036669045687, "learning_rate": 1.1586956521739131e-05, "loss": 0.0003872146084904671, "step": 1600 }, { "epoch": 0.21084728169196834, "grad_norm": 0.0019040399929508567, "learning_rate": 1.1768115942028986e-05, "loss": 0.0003796825930476189, "step": 1625 }, { "epoch": 0.21409108602569094, "grad_norm": 0.0018062678864225745, "learning_rate": 1.1949275362318842e-05, "loss": 0.00039195753633975984, "step": 1650 }, { "epoch": 0.21733489035941353, "grad_norm": 0.004211977124214172, "learning_rate": 1.2130434782608697e-05, "loss": 0.000403401181101799, "step": 1675 }, { "epoch": 0.22057869469313612, "grad_norm": 0.006946008652448654, "learning_rate": 1.2311594202898551e-05, "loss": 0.00037332557141780856, "step": 1700 }, { "epoch": 0.2238224990268587, "grad_norm": 0.004914805758744478, "learning_rate": 1.2492753623188407e-05, "loss": 0.0003810044005513191, "step": 1725 }, { "epoch": 0.22706630336058128, "grad_norm": 0.0032014637254178524, "learning_rate": 1.2673913043478262e-05, "loss": 0.00039044342935085297, "step": 1750 }, { "epoch": 0.23031010769430388, "grad_norm": 0.0028719014953821898, "learning_rate": 1.2855072463768116e-05, "loss": 0.0003721149638295174, "step": 1775 }, { "epoch": 0.23355391202802647, "grad_norm": 0.0008643835899420083, "learning_rate": 1.3036231884057972e-05, "loss": 0.00032976143062114717, "step": 1800 }, { "epoch": 0.23679771636174907, "grad_norm": 0.0010783921461552382, "learning_rate": 1.3217391304347825e-05, "loss": 0.00035968132317066193, "step": 1825 }, { "epoch": 0.24004152069547166, "grad_norm": 0.0017553772777318954, "learning_rate": 1.3398550724637681e-05, "loss": 0.00039101600646972655, "step": 1850 }, { "epoch": 0.24328532502919423, "grad_norm": 0.0041997432708740234, "learning_rate": 1.3579710144927538e-05, "loss": 0.0003649348020553589, "step": 1875 }, { "epoch": 0.24652912936291682, "grad_norm": 0.004162288736552, "learning_rate": 1.376086956521739e-05, "loss": 0.0003690994158387184, "step": 1900 }, { "epoch": 0.24977293369663942, "grad_norm": 0.002320722211152315, "learning_rate": 1.3942028985507247e-05, "loss": 0.00033781368285417556, "step": 1925 }, { "epoch": 0.253016738030362, "grad_norm": 0.002002321183681488, "learning_rate": 1.4123188405797103e-05, "loss": 0.0003259081020951271, "step": 1950 }, { "epoch": 0.2562605423640846, "grad_norm": 0.007351795677095652, "learning_rate": 1.4304347826086959e-05, "loss": 0.00040906108915805817, "step": 1975 }, { "epoch": 0.2595043466978072, "grad_norm": 0.0050153727643191814, "learning_rate": 1.4485507246376812e-05, "loss": 0.00035730652511119844, "step": 2000 }, { "epoch": 0.26274815103152976, "grad_norm": 0.0022896933369338512, "learning_rate": 1.4666666666666668e-05, "loss": 0.0003491346910595894, "step": 2025 }, { "epoch": 0.2659919553652524, "grad_norm": 0.00516933761537075, "learning_rate": 1.4847826086956524e-05, "loss": 0.0003353773057460785, "step": 2050 }, { "epoch": 0.26923575969897495, "grad_norm": 0.0021054656244814396, "learning_rate": 1.5028985507246377e-05, "loss": 0.00033435128629207613, "step": 2075 }, { "epoch": 0.2724795640326976, "grad_norm": 0.002660833764821291, "learning_rate": 1.5210144927536233e-05, "loss": 0.00037069734185934066, "step": 2100 }, { "epoch": 0.27572336836642014, "grad_norm": 0.0026016009505838156, "learning_rate": 1.5391304347826088e-05, "loss": 0.00033382851630449296, "step": 2125 }, { "epoch": 0.2789671727001427, "grad_norm": 0.0009149262332357466, "learning_rate": 1.5572463768115944e-05, "loss": 0.0003106331266462803, "step": 2150 }, { "epoch": 0.28221097703386533, "grad_norm": 0.007814195938408375, "learning_rate": 1.5753623188405797e-05, "loss": 0.00036452498286962507, "step": 2175 }, { "epoch": 0.2854547813675879, "grad_norm": 0.00225284555926919, "learning_rate": 1.5934782608695653e-05, "loss": 0.00031114665791392326, "step": 2200 }, { "epoch": 0.2886985857013105, "grad_norm": 0.0025431253015995026, "learning_rate": 1.611594202898551e-05, "loss": 0.0003396584466099739, "step": 2225 }, { "epoch": 0.2919423900350331, "grad_norm": 0.0012874618405476213, "learning_rate": 1.6297101449275362e-05, "loss": 0.0003272939845919609, "step": 2250 }, { "epoch": 0.29518619436875565, "grad_norm": 0.0013607218861579895, "learning_rate": 1.6478260869565218e-05, "loss": 0.0003025977872312069, "step": 2275 }, { "epoch": 0.29842999870247827, "grad_norm": 0.0010656745871528983, "learning_rate": 1.6659420289855074e-05, "loss": 0.000327068567276001, "step": 2300 }, { "epoch": 0.30167380303620084, "grad_norm": 0.002661523874849081, "learning_rate": 1.6840579710144927e-05, "loss": 0.0003286315873265266, "step": 2325 }, { "epoch": 0.30491760736992346, "grad_norm": 0.001880124444141984, "learning_rate": 1.7021739130434783e-05, "loss": 0.00032299920916557313, "step": 2350 }, { "epoch": 0.308161411703646, "grad_norm": 0.0012912207748740911, "learning_rate": 1.720289855072464e-05, "loss": 0.0003041683696210384, "step": 2375 }, { "epoch": 0.31140521603736865, "grad_norm": 0.0020215825643390417, "learning_rate": 1.7384057971014496e-05, "loss": 0.00031235629692673685, "step": 2400 }, { "epoch": 0.3146490203710912, "grad_norm": 0.005775712430477142, "learning_rate": 1.756521739130435e-05, "loss": 0.00034006834030151365, "step": 2425 }, { "epoch": 0.3178928247048138, "grad_norm": 0.0010357714490965009, "learning_rate": 1.7746376811594205e-05, "loss": 0.0003295731171965599, "step": 2450 }, { "epoch": 0.3211366290385364, "grad_norm": 0.0033022656571120024, "learning_rate": 1.792753623188406e-05, "loss": 0.00034855425357818606, "step": 2475 }, { "epoch": 0.32438043337225897, "grad_norm": 0.0015834731748327613, "learning_rate": 1.8108695652173913e-05, "loss": 0.0003152826800942421, "step": 2500 }, { "epoch": 0.3276242377059816, "grad_norm": 0.0018712675664573908, "learning_rate": 1.828985507246377e-05, "loss": 0.0003270114213228226, "step": 2525 }, { "epoch": 0.33086804203970416, "grad_norm": 0.005989242345094681, "learning_rate": 1.8471014492753626e-05, "loss": 0.00033349290490150454, "step": 2550 }, { "epoch": 0.3341118463734268, "grad_norm": 0.0038143901620060205, "learning_rate": 1.865217391304348e-05, "loss": 0.0003201218694448471, "step": 2575 }, { "epoch": 0.33735565070714935, "grad_norm": 0.0021272441372275352, "learning_rate": 1.8833333333333335e-05, "loss": 0.0003001604229211807, "step": 2600 }, { "epoch": 0.3405994550408719, "grad_norm": 0.0028670968022197485, "learning_rate": 1.9014492753623188e-05, "loss": 0.0003079028241336346, "step": 2625 }, { "epoch": 0.34384325937459453, "grad_norm": 0.004222553223371506, "learning_rate": 1.9195652173913044e-05, "loss": 0.0003144506365060806, "step": 2650 }, { "epoch": 0.3470870637083171, "grad_norm": 0.0027283774688839912, "learning_rate": 1.9376811594202897e-05, "loss": 0.00028602026402950285, "step": 2675 }, { "epoch": 0.3503308680420397, "grad_norm": 0.0015533980913460255, "learning_rate": 1.9557971014492753e-05, "loss": 0.0003138355165719986, "step": 2700 }, { "epoch": 0.3535746723757623, "grad_norm": 0.0010180763201788068, "learning_rate": 1.973913043478261e-05, "loss": 0.00028626693412661555, "step": 2725 }, { "epoch": 0.3568184767094849, "grad_norm": 0.0007715803803876042, "learning_rate": 1.9920289855072465e-05, "loss": 0.00027470897883176805, "step": 2750 }, { "epoch": 0.3600622810432075, "grad_norm": 0.003344092285260558, "learning_rate": 2.0101449275362318e-05, "loss": 0.00031014284119009974, "step": 2775 }, { "epoch": 0.36330608537693004, "grad_norm": 0.0019453978165984154, "learning_rate": 2.0282608695652174e-05, "loss": 0.000265815407037735, "step": 2800 }, { "epoch": 0.36654988971065267, "grad_norm": 0.0013099545612931252, "learning_rate": 2.046376811594203e-05, "loss": 0.000287438053637743, "step": 2825 }, { "epoch": 0.36979369404437523, "grad_norm": 0.0012435506796464324, "learning_rate": 2.0644927536231883e-05, "loss": 0.0002766303904354572, "step": 2850 }, { "epoch": 0.37303749837809785, "grad_norm": 0.0012460686266422272, "learning_rate": 2.082608695652174e-05, "loss": 0.00026510348543524743, "step": 2875 }, { "epoch": 0.3762813027118204, "grad_norm": 0.0013910437701269984, "learning_rate": 2.1007246376811596e-05, "loss": 0.0002775667794048786, "step": 2900 }, { "epoch": 0.379525107045543, "grad_norm": 0.001601441646926105, "learning_rate": 2.1188405797101452e-05, "loss": 0.00025709955021739004, "step": 2925 }, { "epoch": 0.3827689113792656, "grad_norm": 0.0027849336620420218, "learning_rate": 2.1369565217391305e-05, "loss": 0.00026089539751410483, "step": 2950 }, { "epoch": 0.3860127157129882, "grad_norm": 0.002183673670515418, "learning_rate": 2.155072463768116e-05, "loss": 0.00029057132080197336, "step": 2975 }, { "epoch": 0.3892565200467108, "grad_norm": 0.001551933935843408, "learning_rate": 2.1731884057971017e-05, "loss": 0.00028264543041586873, "step": 3000 }, { "epoch": 0.39250032438043336, "grad_norm": 0.001333625870756805, "learning_rate": 2.191304347826087e-05, "loss": 0.00025324754416942595, "step": 3025 }, { "epoch": 0.395744128714156, "grad_norm": 0.0012974956771358848, "learning_rate": 2.2094202898550726e-05, "loss": 0.0003120040334761143, "step": 3050 }, { "epoch": 0.39898793304787855, "grad_norm": 0.0012331365142017603, "learning_rate": 2.2275362318840582e-05, "loss": 0.0002363399416208267, "step": 3075 }, { "epoch": 0.4022317373816011, "grad_norm": 0.0021629715338349342, "learning_rate": 2.2456521739130438e-05, "loss": 0.0002747434750199318, "step": 3100 }, { "epoch": 0.40547554171532374, "grad_norm": 0.0011742196511477232, "learning_rate": 2.263768115942029e-05, "loss": 0.00027804631739854815, "step": 3125 }, { "epoch": 0.4087193460490463, "grad_norm": 0.0020424944814294577, "learning_rate": 2.2818840579710147e-05, "loss": 0.000241420678794384, "step": 3150 }, { "epoch": 0.41196315038276893, "grad_norm": 0.0013211927143856883, "learning_rate": 2.3000000000000003e-05, "loss": 0.0002495998702943325, "step": 3175 }, { "epoch": 0.4152069547164915, "grad_norm": 0.0023100627586245537, "learning_rate": 2.3181159420289856e-05, "loss": 0.0002582721784710884, "step": 3200 }, { "epoch": 0.4184507590502141, "grad_norm": 0.00144074740819633, "learning_rate": 2.3362318840579712e-05, "loss": 0.00019795937463641168, "step": 3225 }, { "epoch": 0.4216945633839367, "grad_norm": 0.0027384154964238405, "learning_rate": 2.354347826086957e-05, "loss": 0.0002338896505534649, "step": 3250 }, { "epoch": 0.42493836771765925, "grad_norm": 0.0036048695910722017, "learning_rate": 2.372463768115942e-05, "loss": 0.0002533886767923832, "step": 3275 }, { "epoch": 0.42818217205138187, "grad_norm": 0.001342841307632625, "learning_rate": 2.3905797101449278e-05, "loss": 0.0002493559755384922, "step": 3300 }, { "epoch": 0.43142597638510444, "grad_norm": 0.003612659638747573, "learning_rate": 2.408695652173913e-05, "loss": 0.00024466965347528456, "step": 3325 }, { "epoch": 0.43466978071882706, "grad_norm": 0.0011443404946476221, "learning_rate": 2.4268115942028987e-05, "loss": 0.0002748650684952736, "step": 3350 }, { "epoch": 0.4379135850525496, "grad_norm": 0.00458540441468358, "learning_rate": 2.444927536231884e-05, "loss": 0.00026181619614362717, "step": 3375 }, { "epoch": 0.44115738938627225, "grad_norm": 0.0029179833363741636, "learning_rate": 2.4630434782608696e-05, "loss": 0.000244431272149086, "step": 3400 }, { "epoch": 0.4444011937199948, "grad_norm": 0.00635079201310873, "learning_rate": 2.4811594202898552e-05, "loss": 0.00022637033835053443, "step": 3425 }, { "epoch": 0.4476449980537174, "grad_norm": 0.0035649770870804787, "learning_rate": 2.4992753623188405e-05, "loss": 0.00027761900797486307, "step": 3450 }, { "epoch": 0.4476449980537174, "eval_loss": 0.0009446408948861063, "eval_runtime": 6.9558, "eval_samples_per_second": 718.826, "eval_steps_per_second": 5.751, "step": 3450 }, { "epoch": 0.4476449980537174, "eval_holdout_avg_strict_f1": 0.059912871850441786, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.16649377593360995, "eval_holdout_nemotron_pii_strict_f1": 0.17257582229816315, "eval_holdout_open_pii_masking_500k_strict_f1": 0.17720997321244591, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.14276201891064058, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 3450 }, { "epoch": 0.45088880238744, "grad_norm": 0.00151688267942518, "learning_rate": 2.5173913043478264e-05, "loss": 0.00025619452819228175, "step": 3475 }, { "epoch": 0.45413260672116257, "grad_norm": 0.002041513565927744, "learning_rate": 2.5355072463768113e-05, "loss": 0.0002359335869550705, "step": 3500 }, { "epoch": 0.4573764110548852, "grad_norm": 0.0032760086469352245, "learning_rate": 2.553623188405797e-05, "loss": 0.00025438517332077026, "step": 3525 }, { "epoch": 0.46062021538860776, "grad_norm": 0.0013569766888394952, "learning_rate": 2.5717391304347826e-05, "loss": 0.00026200929656624796, "step": 3550 }, { "epoch": 0.4638640197223303, "grad_norm": 0.0037377094849944115, "learning_rate": 2.5898550724637682e-05, "loss": 0.00022965669631958008, "step": 3575 }, { "epoch": 0.46710782405605294, "grad_norm": 0.003020873758941889, "learning_rate": 2.6079710144927538e-05, "loss": 0.0002460460364818573, "step": 3600 }, { "epoch": 0.4703516283897755, "grad_norm": 0.0010568414581939578, "learning_rate": 2.6260869565217394e-05, "loss": 0.00025120627135038375, "step": 3625 }, { "epoch": 0.47359543272349813, "grad_norm": 0.001937977853231132, "learning_rate": 2.644202898550725e-05, "loss": 0.000245085284113884, "step": 3650 }, { "epoch": 0.4768392370572207, "grad_norm": 0.0035292659886181355, "learning_rate": 2.66231884057971e-05, "loss": 0.00025614166632294657, "step": 3675 }, { "epoch": 0.4800830413909433, "grad_norm": 0.0020657123532146215, "learning_rate": 2.6804347826086956e-05, "loss": 0.000256416704505682, "step": 3700 }, { "epoch": 0.4833268457246659, "grad_norm": 0.0014694425044581294, "learning_rate": 2.6985507246376812e-05, "loss": 0.000231179129332304, "step": 3725 }, { "epoch": 0.48657065005838845, "grad_norm": 0.0056540281511843204, "learning_rate": 2.716666666666667e-05, "loss": 0.00022526036947965623, "step": 3750 }, { "epoch": 0.4898144543921111, "grad_norm": 0.0037987108808010817, "learning_rate": 2.7347826086956525e-05, "loss": 0.00024000352248549462, "step": 3775 }, { "epoch": 0.49305825872583364, "grad_norm": 0.0008594191749580204, "learning_rate": 2.752898550724638e-05, "loss": 0.00022664297372102738, "step": 3800 }, { "epoch": 0.49630206305955626, "grad_norm": 0.0015906551852822304, "learning_rate": 2.7710144927536237e-05, "loss": 0.0002471371740102768, "step": 3825 }, { "epoch": 0.49954586739327883, "grad_norm": 0.0015811180928722024, "learning_rate": 2.7891304347826087e-05, "loss": 0.00025458842515945434, "step": 3850 }, { "epoch": 0.5027896717270014, "grad_norm": 0.0016268145991489291, "learning_rate": 2.8072463768115943e-05, "loss": 0.00021841734647750854, "step": 3875 }, { "epoch": 0.506033476060724, "grad_norm": 0.0016667566960677505, "learning_rate": 2.82536231884058e-05, "loss": 0.00022410720586776733, "step": 3900 }, { "epoch": 0.5092772803944466, "grad_norm": 0.003140269313007593, "learning_rate": 2.8434782608695655e-05, "loss": 0.0002521145902574062, "step": 3925 }, { "epoch": 0.5125210847281692, "grad_norm": 0.0034551764838397503, "learning_rate": 2.8615942028985508e-05, "loss": 0.0002486487291753292, "step": 3950 }, { "epoch": 0.5157648890618918, "grad_norm": 0.002202315954491496, "learning_rate": 2.8797101449275364e-05, "loss": 0.00027934327721595764, "step": 3975 }, { "epoch": 0.5190086933956144, "grad_norm": 0.0035245579201728106, "learning_rate": 2.897826086956522e-05, "loss": 0.0002535081282258034, "step": 4000 }, { "epoch": 0.522252497729337, "grad_norm": 0.00205890741199255, "learning_rate": 2.9159420289855073e-05, "loss": 0.0002338763140141964, "step": 4025 }, { "epoch": 0.5254963020630595, "grad_norm": 0.002497496549040079, "learning_rate": 2.934057971014493e-05, "loss": 0.00021947348490357398, "step": 4050 }, { "epoch": 0.5287401063967822, "grad_norm": 0.002008829964324832, "learning_rate": 2.9521739130434782e-05, "loss": 0.0002608939260244369, "step": 4075 }, { "epoch": 0.5319839107305048, "grad_norm": 0.004509293008595705, "learning_rate": 2.9702898550724638e-05, "loss": 0.0002249791845679283, "step": 4100 }, { "epoch": 0.5352277150642273, "grad_norm": 0.0020177809055894613, "learning_rate": 2.9884057971014494e-05, "loss": 0.00029328135773539545, "step": 4125 }, { "epoch": 0.5384715193979499, "grad_norm": 0.005398276261985302, "learning_rate": 3.006521739130435e-05, "loss": 0.0002957523800432682, "step": 4150 }, { "epoch": 0.5417153237316725, "grad_norm": 0.0017286442453041673, "learning_rate": 3.0246376811594207e-05, "loss": 0.00026549072936177254, "step": 4175 }, { "epoch": 0.5449591280653951, "grad_norm": 0.0022595671471208334, "learning_rate": 3.0427536231884056e-05, "loss": 0.0002745557017624378, "step": 4200 }, { "epoch": 0.5482029323991177, "grad_norm": 0.002726940205320716, "learning_rate": 3.0608695652173916e-05, "loss": 0.00031262960284948347, "step": 4225 }, { "epoch": 0.5514467367328403, "grad_norm": 0.004314524121582508, "learning_rate": 3.078985507246377e-05, "loss": 0.0003048792481422424, "step": 4250 }, { "epoch": 0.5546905410665629, "grad_norm": 0.0024133736733347178, "learning_rate": 3.097101449275363e-05, "loss": 0.00024383837357163429, "step": 4275 }, { "epoch": 0.5579343454002854, "grad_norm": 0.008594175800681114, "learning_rate": 3.115217391304348e-05, "loss": 0.00027449142187833784, "step": 4300 }, { "epoch": 0.561178149734008, "grad_norm": 0.00900676567107439, "learning_rate": 3.1333333333333334e-05, "loss": 0.00025187190622091296, "step": 4325 }, { "epoch": 0.5644219540677307, "grad_norm": 0.003260792000219226, "learning_rate": 3.151449275362319e-05, "loss": 0.000244941096752882, "step": 4350 }, { "epoch": 0.5676657584014533, "grad_norm": 0.002487393096089363, "learning_rate": 3.1695652173913046e-05, "loss": 0.00024327408522367477, "step": 4375 }, { "epoch": 0.5709095627351758, "grad_norm": 0.0009622393408790231, "learning_rate": 3.18768115942029e-05, "loss": 0.00022421037778258323, "step": 4400 }, { "epoch": 0.5741533670688984, "grad_norm": 0.0019102595979347825, "learning_rate": 3.205797101449275e-05, "loss": 0.00021603509783744813, "step": 4425 }, { "epoch": 0.577397171402621, "grad_norm": 0.0030640624463558197, "learning_rate": 3.223913043478261e-05, "loss": 0.0002439466118812561, "step": 4450 }, { "epoch": 0.5806409757363435, "grad_norm": 0.003552738344296813, "learning_rate": 3.2420289855072464e-05, "loss": 0.0002462785877287388, "step": 4475 }, { "epoch": 0.5838847800700662, "grad_norm": 0.0019611355382949114, "learning_rate": 3.2601449275362324e-05, "loss": 0.00024384066462516786, "step": 4500 }, { "epoch": 0.5871285844037888, "grad_norm": 0.005117570981383324, "learning_rate": 3.278260869565217e-05, "loss": 0.00024965759366750716, "step": 4525 }, { "epoch": 0.5903723887375113, "grad_norm": 0.0030395137146115303, "learning_rate": 3.296376811594203e-05, "loss": 0.00022754574194550515, "step": 4550 }, { "epoch": 0.5936161930712339, "grad_norm": 0.004327160771936178, "learning_rate": 3.314492753623188e-05, "loss": 0.000255475752055645, "step": 4575 }, { "epoch": 0.5968599974049565, "grad_norm": 0.004168620333075523, "learning_rate": 3.332608695652174e-05, "loss": 0.0002240983210504055, "step": 4600 }, { "epoch": 0.6001038017386792, "grad_norm": 0.004194910638034344, "learning_rate": 3.3507246376811594e-05, "loss": 0.00025067068636417387, "step": 4625 }, { "epoch": 0.6033476060724017, "grad_norm": 0.0019860249012708664, "learning_rate": 3.3688405797101454e-05, "loss": 0.00022861765697598457, "step": 4650 }, { "epoch": 0.6065914104061243, "grad_norm": 0.004031823482364416, "learning_rate": 3.386956521739131e-05, "loss": 0.00023715760558843613, "step": 4675 }, { "epoch": 0.6098352147398469, "grad_norm": 0.004918450489640236, "learning_rate": 3.405072463768116e-05, "loss": 0.0002508457750082016, "step": 4700 }, { "epoch": 0.6130790190735694, "grad_norm": 0.0017530858749523759, "learning_rate": 3.423188405797101e-05, "loss": 0.00025858551263809206, "step": 4725 }, { "epoch": 0.616322823407292, "grad_norm": 0.0018709145952016115, "learning_rate": 3.441304347826087e-05, "loss": 0.00019270025193691254, "step": 4750 }, { "epoch": 0.6195666277410147, "grad_norm": 0.003533998504281044, "learning_rate": 3.4594202898550725e-05, "loss": 0.00024344077333807946, "step": 4775 }, { "epoch": 0.6228104320747373, "grad_norm": 0.003203415544703603, "learning_rate": 3.4775362318840584e-05, "loss": 0.00024244219064712525, "step": 4800 }, { "epoch": 0.6260542364084598, "grad_norm": 0.0072675542905926704, "learning_rate": 3.495652173913044e-05, "loss": 0.0002350596711039543, "step": 4825 }, { "epoch": 0.6292980407421824, "grad_norm": 0.004326831549406052, "learning_rate": 3.51376811594203e-05, "loss": 0.00022363213822245597, "step": 4850 }, { "epoch": 0.632541845075905, "grad_norm": 0.004417204763740301, "learning_rate": 3.531884057971014e-05, "loss": 0.00021585172042250632, "step": 4875 }, { "epoch": 0.6357856494096276, "grad_norm": 0.006182452663779259, "learning_rate": 3.55e-05, "loss": 0.000234098881483078, "step": 4900 }, { "epoch": 0.6390294537433502, "grad_norm": 0.00463095074519515, "learning_rate": 3.5681159420289855e-05, "loss": 0.00022355495020747184, "step": 4925 }, { "epoch": 0.6422732580770728, "grad_norm": 0.0028512924909591675, "learning_rate": 3.5862318840579715e-05, "loss": 0.00019916178658604622, "step": 4950 }, { "epoch": 0.6455170624107954, "grad_norm": 0.002945493208244443, "learning_rate": 3.604347826086957e-05, "loss": 0.0002274290844798088, "step": 4975 }, { "epoch": 0.6487608667445179, "grad_norm": 0.0018658636836335063, "learning_rate": 3.622463768115942e-05, "loss": 0.00022229474037885666, "step": 5000 }, { "epoch": 0.6520046710782406, "grad_norm": 0.00426577078178525, "learning_rate": 3.640579710144928e-05, "loss": 0.00020990844815969468, "step": 5025 }, { "epoch": 0.6552484754119632, "grad_norm": 0.002925116801634431, "learning_rate": 3.658695652173913e-05, "loss": 0.00022558726370334626, "step": 5050 }, { "epoch": 0.6584922797456857, "grad_norm": 0.003036529989913106, "learning_rate": 3.6768115942028985e-05, "loss": 0.000221334733068943, "step": 5075 }, { "epoch": 0.6617360840794083, "grad_norm": 0.0035229979548603296, "learning_rate": 3.694927536231884e-05, "loss": 0.00021997846662998198, "step": 5100 }, { "epoch": 0.6649798884131309, "grad_norm": 0.0035209222696721554, "learning_rate": 3.71304347826087e-05, "loss": 0.000210938211530447, "step": 5125 }, { "epoch": 0.6682236927468536, "grad_norm": 0.004434060305356979, "learning_rate": 3.731159420289855e-05, "loss": 0.00020338913425803186, "step": 5150 }, { "epoch": 0.6714674970805761, "grad_norm": 0.001884850556962192, "learning_rate": 3.749275362318841e-05, "loss": 0.00018231350928545, "step": 5175 }, { "epoch": 0.6747113014142987, "grad_norm": 0.004408473148941994, "learning_rate": 3.767391304347826e-05, "loss": 0.00021461354568600655, "step": 5200 }, { "epoch": 0.6779551057480213, "grad_norm": 0.002847679192200303, "learning_rate": 3.7855072463768116e-05, "loss": 0.00022815093398094178, "step": 5225 }, { "epoch": 0.6811989100817438, "grad_norm": 0.0036400463432073593, "learning_rate": 3.803623188405797e-05, "loss": 0.0002146151475608349, "step": 5250 }, { "epoch": 0.6844427144154664, "grad_norm": 0.003353703999891877, "learning_rate": 3.821739130434783e-05, "loss": 0.00019537748768925668, "step": 5275 }, { "epoch": 0.6876865187491891, "grad_norm": 0.0013628709129989147, "learning_rate": 3.839855072463768e-05, "loss": 0.0001990382932126522, "step": 5300 }, { "epoch": 0.6909303230829117, "grad_norm": 0.0038274775724858046, "learning_rate": 3.857971014492754e-05, "loss": 0.0002229778841137886, "step": 5325 }, { "epoch": 0.6941741274166342, "grad_norm": 0.0020599684212356806, "learning_rate": 3.876086956521739e-05, "loss": 0.0002234082669019699, "step": 5350 }, { "epoch": 0.6974179317503568, "grad_norm": 0.0030746429692953825, "learning_rate": 3.894202898550725e-05, "loss": 0.00021490886807441713, "step": 5375 }, { "epoch": 0.7006617360840794, "grad_norm": 0.002775353379547596, "learning_rate": 3.91231884057971e-05, "loss": 0.0001823117583990097, "step": 5400 }, { "epoch": 0.703905540417802, "grad_norm": 0.001965877367183566, "learning_rate": 3.930434782608696e-05, "loss": 0.0002158530429005623, "step": 5425 }, { "epoch": 0.7071493447515246, "grad_norm": 0.0010480332421138883, "learning_rate": 3.948550724637681e-05, "loss": 0.00021332442760467528, "step": 5450 }, { "epoch": 0.7103931490852472, "grad_norm": 0.002962821861729026, "learning_rate": 3.966666666666667e-05, "loss": 0.00019782638177275657, "step": 5475 }, { "epoch": 0.7136369534189698, "grad_norm": 0.002222544513642788, "learning_rate": 3.9847826086956524e-05, "loss": 0.00019951345399022103, "step": 5500 }, { "epoch": 0.7168807577526923, "grad_norm": 0.001600714516825974, "learning_rate": 4.002898550724638e-05, "loss": 0.00017245739698410034, "step": 5525 }, { "epoch": 0.720124562086415, "grad_norm": 0.004020948428660631, "learning_rate": 4.0210144927536236e-05, "loss": 0.00017714429646730422, "step": 5550 }, { "epoch": 0.7233683664201376, "grad_norm": 0.003957361914217472, "learning_rate": 4.039130434782609e-05, "loss": 0.00020558210089802743, "step": 5575 }, { "epoch": 0.7266121707538601, "grad_norm": 0.003327451180666685, "learning_rate": 4.057246376811594e-05, "loss": 0.00017934435978531838, "step": 5600 }, { "epoch": 0.7298559750875827, "grad_norm": 0.0022696941159665585, "learning_rate": 4.07536231884058e-05, "loss": 0.00019934432581067085, "step": 5625 }, { "epoch": 0.7330997794213053, "grad_norm": 0.0028204373084008694, "learning_rate": 4.0934782608695654e-05, "loss": 0.00017393844202160836, "step": 5650 }, { "epoch": 0.7363435837550278, "grad_norm": 0.004516483750194311, "learning_rate": 4.111594202898551e-05, "loss": 0.00016263214871287346, "step": 5675 }, { "epoch": 0.7395873880887505, "grad_norm": 0.004805281292647123, "learning_rate": 4.1297101449275366e-05, "loss": 0.00022644722834229468, "step": 5700 }, { "epoch": 0.7428311924224731, "grad_norm": 0.00221401103772223, "learning_rate": 4.147826086956522e-05, "loss": 0.0002424389310181141, "step": 5725 }, { "epoch": 0.7460749967561957, "grad_norm": 0.001982293091714382, "learning_rate": 4.165942028985507e-05, "loss": 0.00021334733814001083, "step": 5750 }, { "epoch": 0.7493188010899182, "grad_norm": 0.0023351716808974743, "learning_rate": 4.184057971014493e-05, "loss": 0.00022599229589104653, "step": 5775 }, { "epoch": 0.7525626054236408, "grad_norm": 0.0028545025270432234, "learning_rate": 4.2021739130434784e-05, "loss": 0.00020909762009978293, "step": 5800 }, { "epoch": 0.7558064097573635, "grad_norm": 0.002392112510278821, "learning_rate": 4.220289855072464e-05, "loss": 0.00020703429356217385, "step": 5825 }, { "epoch": 0.759050214091086, "grad_norm": 0.0014208235079422593, "learning_rate": 4.23840579710145e-05, "loss": 0.00019431706517934798, "step": 5850 }, { "epoch": 0.7622940184248086, "grad_norm": 0.0023823974188417196, "learning_rate": 4.256521739130435e-05, "loss": 0.0001819189079105854, "step": 5875 }, { "epoch": 0.7655378227585312, "grad_norm": 0.009989273734390736, "learning_rate": 4.274637681159421e-05, "loss": 0.0002344750054180622, "step": 5900 }, { "epoch": 0.7687816270922538, "grad_norm": 0.0036170801613479853, "learning_rate": 4.2927536231884055e-05, "loss": 0.00033482879400253295, "step": 5925 }, { "epoch": 0.7720254314259763, "grad_norm": 0.0020551919005811214, "learning_rate": 4.3108695652173915e-05, "loss": 0.0002414354123175144, "step": 5950 }, { "epoch": 0.775269235759699, "grad_norm": 0.012613258324563503, "learning_rate": 4.328985507246377e-05, "loss": 0.00024966510012745856, "step": 5975 }, { "epoch": 0.7785130400934216, "grad_norm": 0.0009294510819017887, "learning_rate": 4.347101449275363e-05, "loss": 0.00021418372169137, "step": 6000 }, { "epoch": 0.7817568444271441, "grad_norm": 0.0013295958051458001, "learning_rate": 4.365217391304348e-05, "loss": 0.00019037067890167236, "step": 6025 }, { "epoch": 0.7850006487608667, "grad_norm": 0.0014377341140061617, "learning_rate": 4.383333333333334e-05, "loss": 0.00019392110407352449, "step": 6050 }, { "epoch": 0.7882444530945893, "grad_norm": 0.0018915479304268956, "learning_rate": 4.401449275362319e-05, "loss": 0.00019365718588232995, "step": 6075 }, { "epoch": 0.791488257428312, "grad_norm": 0.0018191246781498194, "learning_rate": 4.4195652173913045e-05, "loss": 0.0002038688212633133, "step": 6100 }, { "epoch": 0.7947320617620345, "grad_norm": 0.0014808818232268095, "learning_rate": 4.43768115942029e-05, "loss": 0.00020283084362745284, "step": 6125 }, { "epoch": 0.7979758660957571, "grad_norm": 0.0018717666389420629, "learning_rate": 4.455797101449276e-05, "loss": 0.00016797048971056938, "step": 6150 }, { "epoch": 0.8012196704294797, "grad_norm": 0.0055938116274774075, "learning_rate": 4.473913043478261e-05, "loss": 0.0001979537308216095, "step": 6175 }, { "epoch": 0.8044634747632022, "grad_norm": 0.0020138737745583057, "learning_rate": 4.492028985507247e-05, "loss": 0.00029468344524502754, "step": 6200 }, { "epoch": 0.8077072790969249, "grad_norm": 0.002322674263268709, "learning_rate": 4.510144927536232e-05, "loss": 0.00021765265613794328, "step": 6225 }, { "epoch": 0.8109510834306475, "grad_norm": 0.002045984612777829, "learning_rate": 4.5282608695652175e-05, "loss": 0.0001950218714773655, "step": 6250 }, { "epoch": 0.8141948877643701, "grad_norm": 0.0014243008336052299, "learning_rate": 4.546376811594203e-05, "loss": 0.0002464310824871063, "step": 6275 }, { "epoch": 0.8174386920980926, "grad_norm": 0.017629515379667282, "learning_rate": 4.564492753623189e-05, "loss": 0.00023321276530623435, "step": 6300 }, { "epoch": 0.8206824964318152, "grad_norm": 0.003386995056644082, "learning_rate": 4.582608695652174e-05, "loss": 0.00023059941828250884, "step": 6325 }, { "epoch": 0.8239263007655379, "grad_norm": 0.0027107829228043556, "learning_rate": 4.60072463768116e-05, "loss": 0.00021067384630441666, "step": 6350 }, { "epoch": 0.8271701050992604, "grad_norm": 0.002271743491292, "learning_rate": 4.618840579710145e-05, "loss": 0.00018905309960246086, "step": 6375 }, { "epoch": 0.830413909432983, "grad_norm": 0.0032643533777445555, "learning_rate": 4.6369565217391306e-05, "loss": 0.0001740962453186512, "step": 6400 }, { "epoch": 0.8336577137667056, "grad_norm": 0.0025098773185163736, "learning_rate": 4.655072463768116e-05, "loss": 0.00022290918976068498, "step": 6425 }, { "epoch": 0.8369015181004282, "grad_norm": 0.0026529550086706877, "learning_rate": 4.673188405797102e-05, "loss": 0.00020979499444365502, "step": 6450 }, { "epoch": 0.8401453224341507, "grad_norm": 0.002523129340261221, "learning_rate": 4.691304347826087e-05, "loss": 0.00019479457288980483, "step": 6475 }, { "epoch": 0.8433891267678734, "grad_norm": 0.0030212148558348417, "learning_rate": 4.7094202898550724e-05, "loss": 0.00018869085237383843, "step": 6500 }, { "epoch": 0.846632931101596, "grad_norm": 0.0025767721235752106, "learning_rate": 4.727536231884058e-05, "loss": 0.000213950015604496, "step": 6525 }, { "epoch": 0.8498767354353185, "grad_norm": 0.0025016246363520622, "learning_rate": 4.7456521739130436e-05, "loss": 0.00020605113357305527, "step": 6550 }, { "epoch": 0.8531205397690411, "grad_norm": 0.002447175793349743, "learning_rate": 4.7637681159420296e-05, "loss": 0.0001927393674850464, "step": 6575 }, { "epoch": 0.8563643441027637, "grad_norm": 0.0029913748148828745, "learning_rate": 4.781884057971014e-05, "loss": 0.00016582824289798737, "step": 6600 }, { "epoch": 0.8596081484364864, "grad_norm": 0.001952774589881301, "learning_rate": 4.8e-05, "loss": 0.0001703508011996746, "step": 6625 }, { "epoch": 0.8628519527702089, "grad_norm": 0.0025448803789913654, "learning_rate": 4.8181159420289854e-05, "loss": 0.00019666917622089387, "step": 6650 }, { "epoch": 0.8660957571039315, "grad_norm": 0.0021315179765224457, "learning_rate": 4.8362318840579714e-05, "loss": 0.00018799265846610068, "step": 6675 }, { "epoch": 0.8693395614376541, "grad_norm": 0.0027003567665815353, "learning_rate": 4.8543478260869566e-05, "loss": 0.00016903730109333993, "step": 6700 }, { "epoch": 0.8725833657713766, "grad_norm": 0.005967850796878338, "learning_rate": 4.8724637681159426e-05, "loss": 0.00017813367769122123, "step": 6725 }, { "epoch": 0.8758271701050993, "grad_norm": 0.0021605235524475574, "learning_rate": 4.890579710144928e-05, "loss": 0.00017642628401517868, "step": 6750 }, { "epoch": 0.8790709744388219, "grad_norm": 0.002725504105910659, "learning_rate": 4.908695652173913e-05, "loss": 0.0001931869238615036, "step": 6775 }, { "epoch": 0.8823147787725445, "grad_norm": 0.021711423993110657, "learning_rate": 4.9268115942028984e-05, "loss": 0.00019259713590145112, "step": 6800 }, { "epoch": 0.885558583106267, "grad_norm": 0.0017559337429702282, "learning_rate": 4.9449275362318844e-05, "loss": 0.00017829030752182008, "step": 6825 }, { "epoch": 0.8888023874399896, "grad_norm": 0.0038578715175390244, "learning_rate": 4.96304347826087e-05, "loss": 0.00017510134726762773, "step": 6850 }, { "epoch": 0.8920461917737122, "grad_norm": 0.0023117198143154383, "learning_rate": 4.9811594202898556e-05, "loss": 0.00017724182456731796, "step": 6875 }, { "epoch": 0.8952899961074348, "grad_norm": 0.0011301643680781126, "learning_rate": 4.999275362318841e-05, "loss": 0.00017107401043176652, "step": 6900 }, { "epoch": 0.8952899961074348, "eval_loss": 0.0006006526527926326, "eval_runtime": 7.1019, "eval_samples_per_second": 704.04, "eval_steps_per_second": 5.632, "step": 6900 }, { "epoch": 0.8952899961074348, "eval_holdout_avg_strict_f1": 0.09215432804669149, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.29119732999582815, "eval_holdout_nemotron_pii_strict_f1": 0.2839112927459583, "eval_holdout_open_pii_masking_500k_strict_f1": 0.21069692058346842, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.2278920651883516, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 6900 }, { "epoch": 0.8985338004411574, "grad_norm": 0.015673916786909103, "learning_rate": 4.999998157323963e-05, "loss": 0.00018291639164090158, "step": 6925 }, { "epoch": 0.90177760477488, "grad_norm": 0.0016315768007189035, "learning_rate": 4.999992318987079e-05, "loss": 0.0001521785743534565, "step": 6950 }, { "epoch": 0.9050214091086025, "grad_norm": 0.0013345008483156562, "learning_rate": 4.999982481799595e-05, "loss": 0.00018255805596709252, "step": 6975 }, { "epoch": 0.9082652134423251, "grad_norm": 0.0038595208898186684, "learning_rate": 4.999968645777246e-05, "loss": 0.000168593879789114, "step": 7000 }, { "epoch": 0.9115090177760478, "grad_norm": 0.0043378048576414585, "learning_rate": 4.999950810942164e-05, "loss": 0.0001859547197818756, "step": 7025 }, { "epoch": 0.9147528221097704, "grad_norm": 0.0010240592528134584, "learning_rate": 4.999928977322876e-05, "loss": 0.000164824016392231, "step": 7050 }, { "epoch": 0.9179966264434929, "grad_norm": 0.002753506414592266, "learning_rate": 4.999903144954307e-05, "loss": 0.0001716824807226658, "step": 7075 }, { "epoch": 0.9212404307772155, "grad_norm": 0.005273887887597084, "learning_rate": 4.9998733138777766e-05, "loss": 0.00016859551891684532, "step": 7100 }, { "epoch": 0.9244842351109381, "grad_norm": 0.0018862936412915587, "learning_rate": 4.999839484140999e-05, "loss": 0.00016978152096271514, "step": 7125 }, { "epoch": 0.9277280394446606, "grad_norm": 0.0035417568869888783, "learning_rate": 4.9998016557980896e-05, "loss": 0.0001531672291457653, "step": 7150 }, { "epoch": 0.9309718437783833, "grad_norm": 0.0038210584316402674, "learning_rate": 4.999759828909555e-05, "loss": 0.00015187058597803115, "step": 7175 }, { "epoch": 0.9342156481121059, "grad_norm": 0.0023782167118042707, "learning_rate": 4.9997140035422984e-05, "loss": 0.0001556043792515993, "step": 7200 }, { "epoch": 0.9374594524458285, "grad_norm": 0.0023622815497219563, "learning_rate": 4.9996641797696206e-05, "loss": 0.0001532218884676695, "step": 7225 }, { "epoch": 0.940703256779551, "grad_norm": 0.0023075479548424482, "learning_rate": 4.999610357671217e-05, "loss": 0.00015801338478922843, "step": 7250 }, { "epoch": 0.9439470611132736, "grad_norm": 0.005715147126466036, "learning_rate": 4.999552537333178e-05, "loss": 0.00016315924003720283, "step": 7275 }, { "epoch": 0.9471908654469963, "grad_norm": 0.0034348592162132263, "learning_rate": 4.99949071884799e-05, "loss": 0.00014993258751928808, "step": 7300 }, { "epoch": 0.9504346697807188, "grad_norm": 0.002919167745858431, "learning_rate": 4.999424902314534e-05, "loss": 0.00018292259424924852, "step": 7325 }, { "epoch": 0.9536784741144414, "grad_norm": 0.003980020526796579, "learning_rate": 4.9993550878380876e-05, "loss": 0.00015747614204883576, "step": 7350 }, { "epoch": 0.956922278448164, "grad_norm": 0.002548377262428403, "learning_rate": 4.999281275530321e-05, "loss": 0.0001456683222204447, "step": 7375 }, { "epoch": 0.9601660827818866, "grad_norm": 0.0028948804829269648, "learning_rate": 4.9992034655093016e-05, "loss": 0.0001584981568157673, "step": 7400 }, { "epoch": 0.9634098871156092, "grad_norm": 0.0035979722160845995, "learning_rate": 4.9991216578994894e-05, "loss": 0.00014901037327945234, "step": 7425 }, { "epoch": 0.9666536914493318, "grad_norm": 0.001858632662333548, "learning_rate": 4.999035852831739e-05, "loss": 0.00015681823715567588, "step": 7450 }, { "epoch": 0.9698974957830544, "grad_norm": 0.004013970959931612, "learning_rate": 4.998946050443299e-05, "loss": 0.00015553273260593414, "step": 7475 }, { "epoch": 0.9731413001167769, "grad_norm": 0.0011248707305639982, "learning_rate": 4.9988522508778144e-05, "loss": 0.00016224171966314316, "step": 7500 }, { "epoch": 0.9763851044504995, "grad_norm": 0.0009896703995764256, "learning_rate": 4.9987544542853207e-05, "loss": 0.00015947932377457618, "step": 7525 }, { "epoch": 0.9796289087842222, "grad_norm": 0.003069917671382427, "learning_rate": 4.9986526608222475e-05, "loss": 0.00016054844483733176, "step": 7550 }, { "epoch": 0.9828727131179448, "grad_norm": 0.0023832935839891434, "learning_rate": 4.998546870651418e-05, "loss": 0.0001697651669383049, "step": 7575 }, { "epoch": 0.9861165174516673, "grad_norm": 0.0022508532274514437, "learning_rate": 4.998437083942049e-05, "loss": 0.0001507189404219389, "step": 7600 }, { "epoch": 0.9893603217853899, "grad_norm": 0.0021999150048941374, "learning_rate": 4.998323300869749e-05, "loss": 0.00014187345281243324, "step": 7625 }, { "epoch": 0.9926041261191125, "grad_norm": 0.00226745568215847, "learning_rate": 4.99820552161652e-05, "loss": 0.0001691332459449768, "step": 7650 }, { "epoch": 0.995847930452835, "grad_norm": 0.009134442545473576, "learning_rate": 4.998083746370754e-05, "loss": 0.00016232814639806746, "step": 7675 }, { "epoch": 0.9990917347865577, "grad_norm": 0.0020079261157661676, "learning_rate": 4.9979579753272364e-05, "loss": 0.0001484760455787182, "step": 7700 }, { "epoch": 1.0023355391202802, "grad_norm": 0.0020443268585950136, "learning_rate": 4.997828208687144e-05, "loss": 0.00013864344917237758, "step": 7725 }, { "epoch": 1.0055793434540028, "grad_norm": 0.0026121840346604586, "learning_rate": 4.997694446658044e-05, "loss": 0.00016659105196595192, "step": 7750 }, { "epoch": 1.0088231477877254, "grad_norm": 0.0014524577418342233, "learning_rate": 4.997556689453895e-05, "loss": 0.00014846097677946092, "step": 7775 }, { "epoch": 1.012066952121448, "grad_norm": 0.00338915828615427, "learning_rate": 4.997414937295046e-05, "loss": 0.0001345509197562933, "step": 7800 }, { "epoch": 1.0153107564551707, "grad_norm": 0.003794846124947071, "learning_rate": 4.997269190408235e-05, "loss": 0.00013902314938604832, "step": 7825 }, { "epoch": 1.0185545607888933, "grad_norm": 0.0010545526165515184, "learning_rate": 4.997119449026592e-05, "loss": 0.00014245563186705113, "step": 7850 }, { "epoch": 1.021798365122616, "grad_norm": 0.0010901517234742641, "learning_rate": 4.996965713389635e-05, "loss": 0.00013218452222645282, "step": 7875 }, { "epoch": 1.0250421694563383, "grad_norm": 0.0017376106698065996, "learning_rate": 4.99680798374327e-05, "loss": 0.00013152682222425938, "step": 7900 }, { "epoch": 1.028285973790061, "grad_norm": 0.001922004739753902, "learning_rate": 4.9966462603397946e-05, "loss": 0.00013386822305619717, "step": 7925 }, { "epoch": 1.0315297781237835, "grad_norm": 0.005177031271159649, "learning_rate": 4.9964805434378906e-05, "loss": 0.0001455233059823513, "step": 7950 }, { "epoch": 1.0347735824575062, "grad_norm": 0.003239276586100459, "learning_rate": 4.996310833302631e-05, "loss": 0.0001521645113825798, "step": 7975 }, { "epoch": 1.0380173867912288, "grad_norm": 0.0031741841230541468, "learning_rate": 4.996137130205474e-05, "loss": 0.00014716981910169126, "step": 8000 }, { "epoch": 1.0412611911249514, "grad_norm": 0.0014962584245949984, "learning_rate": 4.995959434424265e-05, "loss": 0.00012373518198728563, "step": 8025 }, { "epoch": 1.044504995458674, "grad_norm": 0.0012364909052848816, "learning_rate": 4.9957777462432394e-05, "loss": 0.00014000100083649158, "step": 8050 }, { "epoch": 1.0477487997923964, "grad_norm": 0.00302161555737257, "learning_rate": 4.9955920659530124e-05, "loss": 0.00014702915214002133, "step": 8075 }, { "epoch": 1.050992604126119, "grad_norm": 0.001989648211747408, "learning_rate": 4.99540239385059e-05, "loss": 0.00014782276935875415, "step": 8100 }, { "epoch": 1.0542364084598417, "grad_norm": 0.0025752668734639883, "learning_rate": 4.99520873023936e-05, "loss": 0.00013168673031032084, "step": 8125 }, { "epoch": 1.0574802127935643, "grad_norm": 0.002262827241793275, "learning_rate": 4.9950110754290966e-05, "loss": 0.00013846089132130146, "step": 8150 }, { "epoch": 1.060724017127287, "grad_norm": 0.004509272985160351, "learning_rate": 4.994809429735957e-05, "loss": 0.00012317084707319737, "step": 8175 }, { "epoch": 1.0639678214610095, "grad_norm": 0.004157810006290674, "learning_rate": 4.994603793482484e-05, "loss": 0.00015636086463928224, "step": 8200 }, { "epoch": 1.067211625794732, "grad_norm": 0.0022848660591989756, "learning_rate": 4.994394166997601e-05, "loss": 0.00014418723061680792, "step": 8225 }, { "epoch": 1.0704554301284546, "grad_norm": 0.0027578691951930523, "learning_rate": 4.994180550616615e-05, "loss": 0.0001505685970187187, "step": 8250 }, { "epoch": 1.0736992344621772, "grad_norm": 0.0032979706302285194, "learning_rate": 4.993962944681216e-05, "loss": 0.00013892202638089658, "step": 8275 }, { "epoch": 1.0769430387958998, "grad_norm": 0.003953599836677313, "learning_rate": 4.993741349539474e-05, "loss": 0.00015112876892089844, "step": 8300 }, { "epoch": 1.0801868431296224, "grad_norm": 0.004613295663148165, "learning_rate": 4.99351576554584e-05, "loss": 0.000127301886677742, "step": 8325 }, { "epoch": 1.083430647463345, "grad_norm": 0.0030234316363930702, "learning_rate": 4.9932861930611454e-05, "loss": 0.00014280307106673718, "step": 8350 }, { "epoch": 1.0866744517970677, "grad_norm": 0.0013406832003965974, "learning_rate": 4.993052632452603e-05, "loss": 0.00013854522258043288, "step": 8375 }, { "epoch": 1.0899182561307903, "grad_norm": 0.003002692712470889, "learning_rate": 4.9928150840938034e-05, "loss": 0.00013456257060170173, "step": 8400 }, { "epoch": 1.0931620604645127, "grad_norm": 0.0013413458364084363, "learning_rate": 4.9925735483647144e-05, "loss": 0.0001445169933140278, "step": 8425 }, { "epoch": 1.0964058647982353, "grad_norm": 0.0008674738928675652, "learning_rate": 4.9923280256516856e-05, "loss": 0.00014560348354279994, "step": 8450 }, { "epoch": 1.099649669131958, "grad_norm": 0.001296030473895371, "learning_rate": 4.99207851634744e-05, "loss": 0.0001388644240796566, "step": 8475 }, { "epoch": 1.1028934734656806, "grad_norm": 0.0029618185944855213, "learning_rate": 4.991825020851079e-05, "loss": 0.00012045403942465782, "step": 8500 }, { "epoch": 1.1061372777994032, "grad_norm": 0.0015589740360155702, "learning_rate": 4.991567539568081e-05, "loss": 0.00013180667534470558, "step": 8525 }, { "epoch": 1.1093810821331258, "grad_norm": 0.004680166020989418, "learning_rate": 4.991306072910299e-05, "loss": 0.00012142084538936615, "step": 8550 }, { "epoch": 1.1126248864668482, "grad_norm": 0.008011570200324059, "learning_rate": 4.991040621295959e-05, "loss": 0.0001287257019430399, "step": 8575 }, { "epoch": 1.1158686908005708, "grad_norm": 0.00628697220236063, "learning_rate": 4.9907711851496655e-05, "loss": 0.00015852615237236023, "step": 8600 }, { "epoch": 1.1191124951342935, "grad_norm": 0.002723196754232049, "learning_rate": 4.9904977649023906e-05, "loss": 0.000133550763130188, "step": 8625 }, { "epoch": 1.122356299468016, "grad_norm": 0.0026552604977041483, "learning_rate": 4.9902203609914855e-05, "loss": 0.00013043675571680068, "step": 8650 }, { "epoch": 1.1256001038017387, "grad_norm": 0.0027350012678653, "learning_rate": 4.989938973860668e-05, "loss": 0.00013432277366518975, "step": 8675 }, { "epoch": 1.1288439081354613, "grad_norm": 0.001737050013616681, "learning_rate": 4.989653603960032e-05, "loss": 0.00011701254174113273, "step": 8700 }, { "epoch": 1.132087712469184, "grad_norm": 0.003207565052434802, "learning_rate": 4.989364251746036e-05, "loss": 0.0001503424160182476, "step": 8725 }, { "epoch": 1.1353315168029066, "grad_norm": 0.005733543075621128, "learning_rate": 4.989070917681515e-05, "loss": 0.00012866288423538208, "step": 8750 }, { "epoch": 1.138575321136629, "grad_norm": 0.007139100693166256, "learning_rate": 4.988773602235669e-05, "loss": 0.0001536327414214611, "step": 8775 }, { "epoch": 1.1418191254703516, "grad_norm": 0.0031340215355157852, "learning_rate": 4.9884723058840665e-05, "loss": 0.0001347917690873146, "step": 8800 }, { "epoch": 1.1450629298040742, "grad_norm": 0.003754221135750413, "learning_rate": 4.988167029108646e-05, "loss": 0.00012687365524470805, "step": 8825 }, { "epoch": 1.1483067341377968, "grad_norm": 0.002546739997342229, "learning_rate": 4.9878577723977116e-05, "loss": 0.00013334625400602819, "step": 8850 }, { "epoch": 1.1515505384715194, "grad_norm": 0.0022838865406811237, "learning_rate": 4.987544536245931e-05, "loss": 0.00012206505052745343, "step": 8875 }, { "epoch": 1.154794342805242, "grad_norm": 0.0026433991733938456, "learning_rate": 4.987227321154344e-05, "loss": 0.00011950843036174774, "step": 8900 }, { "epoch": 1.1580381471389645, "grad_norm": 0.001351697021164, "learning_rate": 4.986906127630346e-05, "loss": 0.00013297591358423232, "step": 8925 }, { "epoch": 1.161281951472687, "grad_norm": 0.002192141953855753, "learning_rate": 4.986580956187703e-05, "loss": 0.00012975909747183322, "step": 8950 }, { "epoch": 1.1645257558064097, "grad_norm": 0.003854804439470172, "learning_rate": 4.9862518073465405e-05, "loss": 0.00012384939938783646, "step": 8975 }, { "epoch": 1.1677695601401323, "grad_norm": 0.0035276729613542557, "learning_rate": 4.985918681633348e-05, "loss": 0.00012343226931989194, "step": 9000 }, { "epoch": 1.171013364473855, "grad_norm": 0.006603064481168985, "learning_rate": 4.985581579580973e-05, "loss": 0.00010922129265964031, "step": 9025 }, { "epoch": 1.1742571688075776, "grad_norm": 0.0020735692232847214, "learning_rate": 4.985240501728628e-05, "loss": 0.00011517073959112167, "step": 9050 }, { "epoch": 1.1775009731413002, "grad_norm": 0.015130588784813881, "learning_rate": 4.984895448621881e-05, "loss": 0.00014729876071214676, "step": 9075 }, { "epoch": 1.1807447774750228, "grad_norm": 0.0021695042960345745, "learning_rate": 4.98454642081266e-05, "loss": 0.00013779266737401485, "step": 9100 }, { "epoch": 1.1839885818087452, "grad_norm": 0.0008490979671478271, "learning_rate": 4.984193418859251e-05, "loss": 0.00016810553148388863, "step": 9125 }, { "epoch": 1.1872323861424678, "grad_norm": 0.0034548677504062653, "learning_rate": 4.9838364433262965e-05, "loss": 0.00012994081713259221, "step": 9150 }, { "epoch": 1.1904761904761905, "grad_norm": 0.0021760868839919567, "learning_rate": 4.983475494784795e-05, "loss": 0.00011825896799564362, "step": 9175 }, { "epoch": 1.193719994809913, "grad_norm": 0.0017299389000982046, "learning_rate": 4.9831105738120995e-05, "loss": 0.00012954682111740112, "step": 9200 }, { "epoch": 1.1969637991436357, "grad_norm": 0.0036440177354961634, "learning_rate": 4.982741680991919e-05, "loss": 0.00012295584194362162, "step": 9225 }, { "epoch": 1.2002076034773583, "grad_norm": 0.003258202923461795, "learning_rate": 4.982368816914314e-05, "loss": 0.00012140109203755855, "step": 9250 }, { "epoch": 1.2034514078110807, "grad_norm": 0.001618252252228558, "learning_rate": 4.981991982175695e-05, "loss": 0.0001145719550549984, "step": 9275 }, { "epoch": 1.2066952121448034, "grad_norm": 0.001193601405248046, "learning_rate": 4.981611177378829e-05, "loss": 0.00012420842424035072, "step": 9300 }, { "epoch": 1.209939016478526, "grad_norm": 0.0015703079989179969, "learning_rate": 4.9812264031328285e-05, "loss": 0.00010998865589499473, "step": 9325 }, { "epoch": 1.2131828208122486, "grad_norm": 0.0063532330095767975, "learning_rate": 4.980837660053159e-05, "loss": 0.00011530451476573944, "step": 9350 }, { "epoch": 1.2164266251459712, "grad_norm": 0.004595960956066847, "learning_rate": 4.980444948761631e-05, "loss": 0.0001206542644649744, "step": 9375 }, { "epoch": 1.2196704294796938, "grad_norm": 0.006558804772794247, "learning_rate": 4.980048269886406e-05, "loss": 0.00012762240134179593, "step": 9400 }, { "epoch": 1.2229142338134165, "grad_norm": 0.0015244376845657825, "learning_rate": 4.979647624061987e-05, "loss": 0.0001383919920772314, "step": 9425 }, { "epoch": 1.226158038147139, "grad_norm": 0.0024551923852413893, "learning_rate": 4.9792430119292275e-05, "loss": 0.00013064601458609104, "step": 9450 }, { "epoch": 1.2294018424808615, "grad_norm": 0.001814241404645145, "learning_rate": 4.978834434135322e-05, "loss": 0.00011826836504042149, "step": 9475 }, { "epoch": 1.232645646814584, "grad_norm": 0.0027942133601754904, "learning_rate": 4.9784218913338096e-05, "loss": 0.00013357285410165788, "step": 9500 }, { "epoch": 1.2358894511483067, "grad_norm": 0.002728573279455304, "learning_rate": 4.9780053841845697e-05, "loss": 0.00011760947294533253, "step": 9525 }, { "epoch": 1.2391332554820293, "grad_norm": 0.0033307820558547974, "learning_rate": 4.9775849133538254e-05, "loss": 0.00012242857366800308, "step": 9550 }, { "epoch": 1.242377059815752, "grad_norm": 0.0034640366211533546, "learning_rate": 4.9771604795141385e-05, "loss": 0.0001291111670434475, "step": 9575 }, { "epoch": 1.2456208641494746, "grad_norm": 0.0016641821712255478, "learning_rate": 4.976732083344411e-05, "loss": 0.00011522158049046993, "step": 9600 }, { "epoch": 1.248864668483197, "grad_norm": 0.0019255299121141434, "learning_rate": 4.97629972552988e-05, "loss": 0.00010252853855490684, "step": 9625 }, { "epoch": 1.2521084728169196, "grad_norm": 0.0015568454982712865, "learning_rate": 4.975863406762124e-05, "loss": 0.0001205254253000021, "step": 9650 }, { "epoch": 1.2553522771506422, "grad_norm": 0.001585613819770515, "learning_rate": 4.9754231277390514e-05, "loss": 0.00010102837346494198, "step": 9675 }, { "epoch": 1.2585960814843649, "grad_norm": 0.005399284418672323, "learning_rate": 4.974978889164911e-05, "loss": 0.00011075906455516815, "step": 9700 }, { "epoch": 1.2618398858180875, "grad_norm": 0.002899307757616043, "learning_rate": 4.9745306917502805e-05, "loss": 0.00012125036679208278, "step": 9725 }, { "epoch": 1.26508369015181, "grad_norm": 0.0012491963570937514, "learning_rate": 4.9740785362120736e-05, "loss": 0.00011602954007685185, "step": 9750 }, { "epoch": 1.2683274944855327, "grad_norm": 0.008506156504154205, "learning_rate": 4.973622423273533e-05, "loss": 0.00012882969342172145, "step": 9775 }, { "epoch": 1.2715712988192553, "grad_norm": 0.0030648019164800644, "learning_rate": 4.973162353664231e-05, "loss": 0.00012058447115123272, "step": 9800 }, { "epoch": 1.2748151031529777, "grad_norm": 0.002383406739681959, "learning_rate": 4.972698328120071e-05, "loss": 0.0001091123092919588, "step": 9825 }, { "epoch": 1.2780589074867004, "grad_norm": 0.002522526541724801, "learning_rate": 4.9722303473832824e-05, "loss": 0.0001045923214405775, "step": 9850 }, { "epoch": 1.281302711820423, "grad_norm": 0.0017412592424079776, "learning_rate": 4.97175841220242e-05, "loss": 0.00011019484139978885, "step": 9875 }, { "epoch": 1.2845465161541456, "grad_norm": 0.0033273082226514816, "learning_rate": 4.971282523332368e-05, "loss": 0.0001070321537554264, "step": 9900 }, { "epoch": 1.2877903204878682, "grad_norm": 0.003242602339014411, "learning_rate": 4.9708026815343314e-05, "loss": 0.00011374884285032749, "step": 9925 }, { "epoch": 1.2910341248215906, "grad_norm": 0.004430373199284077, "learning_rate": 4.970318887575837e-05, "loss": 0.00010790590196847916, "step": 9950 }, { "epoch": 1.2942779291553133, "grad_norm": 0.01073714904487133, "learning_rate": 4.969831142230737e-05, "loss": 0.00015663722530007363, "step": 9975 }, { "epoch": 1.2975217334890359, "grad_norm": 0.00393688166514039, "learning_rate": 4.969339446279202e-05, "loss": 0.00018807284533977508, "step": 10000 }, { "epoch": 1.3007655378227585, "grad_norm": 0.0025645080022513866, "learning_rate": 4.968843800507721e-05, "loss": 0.00012592429295182227, "step": 10025 }, { "epoch": 1.3040093421564811, "grad_norm": 0.001242077094502747, "learning_rate": 4.9683442057091024e-05, "loss": 0.00013033896684646606, "step": 10050 }, { "epoch": 1.3072531464902037, "grad_norm": 0.001450183684937656, "learning_rate": 4.96784066268247e-05, "loss": 0.00012390486896038055, "step": 10075 }, { "epoch": 1.3104969508239264, "grad_norm": 0.0017009455477818847, "learning_rate": 4.9673331722332644e-05, "loss": 9.529363363981246e-05, "step": 10100 }, { "epoch": 1.313740755157649, "grad_norm": 0.003401797031983733, "learning_rate": 4.9668217351732396e-05, "loss": 0.00011087918654084205, "step": 10125 }, { "epoch": 1.3169845594913716, "grad_norm": 0.001372999744489789, "learning_rate": 4.966306352320461e-05, "loss": 9.170420467853546e-05, "step": 10150 }, { "epoch": 1.320228363825094, "grad_norm": 0.0012355969520285726, "learning_rate": 4.9657870244993074e-05, "loss": 0.00010841242969036103, "step": 10175 }, { "epoch": 1.3234721681588166, "grad_norm": 0.0009882008889690042, "learning_rate": 4.965263752540468e-05, "loss": 0.00011248056776821613, "step": 10200 }, { "epoch": 1.3267159724925393, "grad_norm": 0.0013076459290459752, "learning_rate": 4.964736537280939e-05, "loss": 0.00010362941771745682, "step": 10225 }, { "epoch": 1.3299597768262619, "grad_norm": 0.006651753094047308, "learning_rate": 4.9642053795640255e-05, "loss": 0.00011371344327926636, "step": 10250 }, { "epoch": 1.3332035811599845, "grad_norm": 0.001235575182363391, "learning_rate": 4.963670280239337e-05, "loss": 0.00010600646026432515, "step": 10275 }, { "epoch": 1.336447385493707, "grad_norm": 0.0007966601406224072, "learning_rate": 4.96313124016279e-05, "loss": 9.728899225592613e-05, "step": 10300 }, { "epoch": 1.3396911898274295, "grad_norm": 0.001845808350481093, "learning_rate": 4.962588260196605e-05, "loss": 0.0001120012067258358, "step": 10325 }, { "epoch": 1.3429349941611521, "grad_norm": 0.0008214382687583566, "learning_rate": 4.9620413412093e-05, "loss": 9.760853834450244e-05, "step": 10350 }, { "epoch": 1.3429349941611521, "eval_loss": 0.00036991448723711073, "eval_runtime": 7.127, "eval_samples_per_second": 701.562, "eval_steps_per_second": 5.612, "step": 10350 }, { "epoch": 1.3429349941611521, "eval_holdout_avg_strict_f1": 0.1275853617492995, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.4188692663268935, "eval_holdout_nemotron_pii_strict_f1": 0.37427312775330396, "eval_holdout_open_pii_masking_500k_strict_f1": 0.31377415351887966, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.29652243164321745, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 10350 }, { "epoch": 1.3461787984948748, "grad_norm": 0.0019075750606134534, "learning_rate": 4.9614904840756985e-05, "loss": 0.00010152452625334263, "step": 10375 }, { "epoch": 1.3494226028285974, "grad_norm": 0.0015633883886039257, "learning_rate": 4.96093568967692e-05, "loss": 9.313571266829968e-05, "step": 10400 }, { "epoch": 1.35266640716232, "grad_norm": 0.00121040060184896, "learning_rate": 4.960376958900385e-05, "loss": 0.0001095324382185936, "step": 10425 }, { "epoch": 1.3559102114960426, "grad_norm": 0.0032971289474517107, "learning_rate": 4.9598142926398075e-05, "loss": 0.00010388997383415699, "step": 10450 }, { "epoch": 1.3591540158297652, "grad_norm": 0.0015374368522316217, "learning_rate": 4.959247691795198e-05, "loss": 0.00010369649156928062, "step": 10475 }, { "epoch": 1.3623978201634879, "grad_norm": 0.0011054335627704859, "learning_rate": 4.9586771572728597e-05, "loss": 0.00010756392031908036, "step": 10500 }, { "epoch": 1.3656416244972103, "grad_norm": 0.004493126180022955, "learning_rate": 4.958102689985388e-05, "loss": 0.00010990199632942676, "step": 10525 }, { "epoch": 1.368885428830933, "grad_norm": 0.0021133364643901587, "learning_rate": 4.9575242908516705e-05, "loss": 0.00010303172282874584, "step": 10550 }, { "epoch": 1.3721292331646555, "grad_norm": 0.0013266073074191809, "learning_rate": 4.956941960796881e-05, "loss": 0.0001211999822407961, "step": 10575 }, { "epoch": 1.3753730374983781, "grad_norm": 0.000995876151137054, "learning_rate": 4.9563557007524854e-05, "loss": 0.00011714013293385505, "step": 10600 }, { "epoch": 1.3786168418321008, "grad_norm": 0.0017720719333738089, "learning_rate": 4.95576551165623e-05, "loss": 0.0001024802029132843, "step": 10625 }, { "epoch": 1.3818606461658232, "grad_norm": 0.003122315974906087, "learning_rate": 4.955171394452151e-05, "loss": 9.46104060858488e-05, "step": 10650 }, { "epoch": 1.3851044504995458, "grad_norm": 0.0013838070444762707, "learning_rate": 4.954573350090565e-05, "loss": 0.00010967789217829705, "step": 10675 }, { "epoch": 1.3883482548332684, "grad_norm": 0.002108931541442871, "learning_rate": 4.953971379528071e-05, "loss": 0.00010044232942163945, "step": 10700 }, { "epoch": 1.391592059166991, "grad_norm": 0.0019082443322986364, "learning_rate": 4.953365483727548e-05, "loss": 0.00010785138234496116, "step": 10725 }, { "epoch": 1.3948358635007136, "grad_norm": 0.002357171382755041, "learning_rate": 4.952755663658154e-05, "loss": 9.83487069606781e-05, "step": 10750 }, { "epoch": 1.3980796678344363, "grad_norm": 0.001703948713839054, "learning_rate": 4.9521419202953236e-05, "loss": 0.00010184159502387047, "step": 10775 }, { "epoch": 1.401323472168159, "grad_norm": 0.001928914338350296, "learning_rate": 4.951524254620766e-05, "loss": 9.341860190033913e-05, "step": 10800 }, { "epoch": 1.4045672765018815, "grad_norm": 0.0026474876794964075, "learning_rate": 4.950902667622468e-05, "loss": 0.00010016300715506077, "step": 10825 }, { "epoch": 1.4078110808356041, "grad_norm": 0.005246476270258427, "learning_rate": 4.950277160294683e-05, "loss": 0.00011274341493844987, "step": 10850 }, { "epoch": 1.4110548851693265, "grad_norm": 0.0014939205721020699, "learning_rate": 4.94964773363794e-05, "loss": 9.391885250806809e-05, "step": 10875 }, { "epoch": 1.4142986895030492, "grad_norm": 0.002114594914019108, "learning_rate": 4.9490143886590355e-05, "loss": 0.00010775422677397728, "step": 10900 }, { "epoch": 1.4175424938367718, "grad_norm": 0.0011581681901589036, "learning_rate": 4.948377126371032e-05, "loss": 0.0001027341838926077, "step": 10925 }, { "epoch": 1.4207862981704944, "grad_norm": 0.002227695193141699, "learning_rate": 4.9477359477932604e-05, "loss": 9.854044765233994e-05, "step": 10950 }, { "epoch": 1.424030102504217, "grad_norm": 0.0014717110898345709, "learning_rate": 4.947090853951315e-05, "loss": 0.00010085958987474442, "step": 10975 }, { "epoch": 1.4272739068379394, "grad_norm": 0.0014428577851504087, "learning_rate": 4.9464418458770516e-05, "loss": 0.00010807996615767479, "step": 11000 }, { "epoch": 1.430517711171662, "grad_norm": 0.003823901992291212, "learning_rate": 4.945788924608589e-05, "loss": 9.293714538216591e-05, "step": 11025 }, { "epoch": 1.4337615155053847, "grad_norm": 0.0023647418711334467, "learning_rate": 4.9451320911903027e-05, "loss": 0.00010413714684545994, "step": 11050 }, { "epoch": 1.4370053198391073, "grad_norm": 0.0009704636759124696, "learning_rate": 4.9444713466728286e-05, "loss": 9.642095305025578e-05, "step": 11075 }, { "epoch": 1.44024912417283, "grad_norm": 0.0032890564762055874, "learning_rate": 4.943806692113058e-05, "loss": 0.00010314587503671646, "step": 11100 }, { "epoch": 1.4434929285065525, "grad_norm": 0.0014613616513088346, "learning_rate": 4.943138128574134e-05, "loss": 9.938787668943405e-05, "step": 11125 }, { "epoch": 1.4467367328402752, "grad_norm": 0.0036230525001883507, "learning_rate": 4.942465657125455e-05, "loss": 0.00010015349835157394, "step": 11150 }, { "epoch": 1.4499805371739978, "grad_norm": 0.0007614869973622262, "learning_rate": 4.94178927884267e-05, "loss": 0.0001063475850969553, "step": 11175 }, { "epoch": 1.4532243415077202, "grad_norm": 0.0017315896693617105, "learning_rate": 4.941108994807676e-05, "loss": 9.714725427329541e-05, "step": 11200 }, { "epoch": 1.4564681458414428, "grad_norm": 0.001370782614685595, "learning_rate": 4.940424806108619e-05, "loss": 8.16777627915144e-05, "step": 11225 }, { "epoch": 1.4597119501751654, "grad_norm": 0.001145777408964932, "learning_rate": 4.939736713839889e-05, "loss": 8.568291552364826e-05, "step": 11250 }, { "epoch": 1.462955754508888, "grad_norm": 0.0011671765241771936, "learning_rate": 4.93904471910212e-05, "loss": 9.868164546787739e-05, "step": 11275 }, { "epoch": 1.4661995588426107, "grad_norm": 0.0013969693100079894, "learning_rate": 4.938348823002189e-05, "loss": 0.0001043697725981474, "step": 11300 }, { "epoch": 1.4694433631763333, "grad_norm": 0.002010302385315299, "learning_rate": 4.937649026653215e-05, "loss": 9.39489621669054e-05, "step": 11325 }, { "epoch": 1.4726871675100557, "grad_norm": 0.0007198164239525795, "learning_rate": 4.9369453311745516e-05, "loss": 7.88387656211853e-05, "step": 11350 }, { "epoch": 1.4759309718437783, "grad_norm": 0.0015702141681686044, "learning_rate": 4.9362377376917936e-05, "loss": 8.33436567336321e-05, "step": 11375 }, { "epoch": 1.479174776177501, "grad_norm": 0.0031432940158993006, "learning_rate": 4.935526247336767e-05, "loss": 0.0001007038913667202, "step": 11400 }, { "epoch": 1.4824185805112235, "grad_norm": 0.001954857027158141, "learning_rate": 4.934810861247533e-05, "loss": 8.878502994775772e-05, "step": 11425 }, { "epoch": 1.4856623848449462, "grad_norm": 0.003959836438298225, "learning_rate": 4.934091580568384e-05, "loss": 9.048283100128174e-05, "step": 11450 }, { "epoch": 1.4889061891786688, "grad_norm": 0.0012222324730828404, "learning_rate": 4.933368406449843e-05, "loss": 8.21176078170538e-05, "step": 11475 }, { "epoch": 1.4921499935123914, "grad_norm": 0.0013890629634261131, "learning_rate": 4.932641340048658e-05, "loss": 8.408771827816963e-05, "step": 11500 }, { "epoch": 1.495393797846114, "grad_norm": 0.000834476959425956, "learning_rate": 4.931910382527806e-05, "loss": 8.684156462550163e-05, "step": 11525 }, { "epoch": 1.4986376021798364, "grad_norm": 0.0011225062189623713, "learning_rate": 4.931175535056486e-05, "loss": 8.782894350588322e-05, "step": 11550 }, { "epoch": 1.501881406513559, "grad_norm": 0.0009917602874338627, "learning_rate": 4.9304367988101194e-05, "loss": 8.302676491439342e-05, "step": 11575 }, { "epoch": 1.5051252108472817, "grad_norm": 0.0016674603102728724, "learning_rate": 4.9296941749703486e-05, "loss": 9.310065768659115e-05, "step": 11600 }, { "epoch": 1.5083690151810043, "grad_norm": 0.00237331073731184, "learning_rate": 4.9289476647250344e-05, "loss": 0.00010573365725576877, "step": 11625 }, { "epoch": 1.511612819514727, "grad_norm": 0.0013624010607600212, "learning_rate": 4.928197269268252e-05, "loss": 8.472266606986523e-05, "step": 11650 }, { "epoch": 1.5148566238484493, "grad_norm": 0.0017411302542313933, "learning_rate": 4.927442989800294e-05, "loss": 8.467529900372029e-05, "step": 11675 }, { "epoch": 1.518100428182172, "grad_norm": 0.001095858053304255, "learning_rate": 4.926684827527665e-05, "loss": 8.973106741905212e-05, "step": 11700 }, { "epoch": 1.5213442325158946, "grad_norm": 0.001341550494544208, "learning_rate": 4.925922783663079e-05, "loss": 8.297733031213283e-05, "step": 11725 }, { "epoch": 1.5245880368496172, "grad_norm": 0.0012667059199884534, "learning_rate": 4.925156859425459e-05, "loss": 8.052033372223377e-05, "step": 11750 }, { "epoch": 1.5278318411833398, "grad_norm": 0.002803317504003644, "learning_rate": 4.924387056039937e-05, "loss": 8.886337280273438e-05, "step": 11775 }, { "epoch": 1.5310756455170624, "grad_norm": 0.0029707374051213264, "learning_rate": 4.9236133747378475e-05, "loss": 9.532704949378967e-05, "step": 11800 }, { "epoch": 1.534319449850785, "grad_norm": 0.002772587351500988, "learning_rate": 4.922835816756728e-05, "loss": 9.086200036108494e-05, "step": 11825 }, { "epoch": 1.5375632541845077, "grad_norm": 0.0009155553416348994, "learning_rate": 4.922054383340319e-05, "loss": 9.423841722309589e-05, "step": 11850 }, { "epoch": 1.5408070585182303, "grad_norm": 0.0017063968116417527, "learning_rate": 4.9212690757385565e-05, "loss": 8.347968570888043e-05, "step": 11875 }, { "epoch": 1.544050862851953, "grad_norm": 0.0008430125890299678, "learning_rate": 4.920479895207577e-05, "loss": 7.5639090500772e-05, "step": 11900 }, { "epoch": 1.5472946671856753, "grad_norm": 0.001868857303634286, "learning_rate": 4.919686843009711e-05, "loss": 0.00010813709348440171, "step": 11925 }, { "epoch": 1.550538471519398, "grad_norm": 0.000921098398976028, "learning_rate": 4.9188899204134794e-05, "loss": 9.023160673677921e-05, "step": 11950 }, { "epoch": 1.5537822758531206, "grad_norm": 0.0005922731361351907, "learning_rate": 4.918089128693597e-05, "loss": 8.841898292303086e-05, "step": 11975 }, { "epoch": 1.557026080186843, "grad_norm": 0.0007760357111692429, "learning_rate": 4.917284469130966e-05, "loss": 7.144877687096595e-05, "step": 12000 }, { "epoch": 1.5602698845205656, "grad_norm": 0.0015065018087625504, "learning_rate": 4.916475943012676e-05, "loss": 8.484479039907455e-05, "step": 12025 }, { "epoch": 1.5635136888542882, "grad_norm": 0.0031684760469943285, "learning_rate": 4.915663551632002e-05, "loss": 8.092996664345264e-05, "step": 12050 }, { "epoch": 1.5667574931880108, "grad_norm": 0.001071028527803719, "learning_rate": 4.914847296288398e-05, "loss": 9.153211489319801e-05, "step": 12075 }, { "epoch": 1.5700012975217335, "grad_norm": 0.0019498398760333657, "learning_rate": 4.9140271782875035e-05, "loss": 8.832218125462532e-05, "step": 12100 }, { "epoch": 1.573245101855456, "grad_norm": 0.004722662270069122, "learning_rate": 4.913203198941134e-05, "loss": 9.563307277858257e-05, "step": 12125 }, { "epoch": 1.5764889061891787, "grad_norm": 0.002092895796522498, "learning_rate": 4.912375359567281e-05, "loss": 9.133992716670036e-05, "step": 12150 }, { "epoch": 1.5797327105229013, "grad_norm": 0.0015882306033745408, "learning_rate": 4.9115436614901114e-05, "loss": 0.0001010614726692438, "step": 12175 }, { "epoch": 1.582976514856624, "grad_norm": 0.0016340278089046478, "learning_rate": 4.9107081060399627e-05, "loss": 0.00010534830391407013, "step": 12200 }, { "epoch": 1.5862203191903466, "grad_norm": 0.002504449337720871, "learning_rate": 4.909868694553346e-05, "loss": 8.788328617811204e-05, "step": 12225 }, { "epoch": 1.5894641235240692, "grad_norm": 0.0024790067691355944, "learning_rate": 4.909025428372936e-05, "loss": 8.230115287005902e-05, "step": 12250 }, { "epoch": 1.5927079278577916, "grad_norm": 0.0018999363528564572, "learning_rate": 4.908178308847575e-05, "loss": 8.052840828895569e-05, "step": 12275 }, { "epoch": 1.5959517321915142, "grad_norm": 0.0026415446773171425, "learning_rate": 4.907327337332271e-05, "loss": 8.902439847588539e-05, "step": 12300 }, { "epoch": 1.5991955365252368, "grad_norm": 0.0019862309563905, "learning_rate": 4.906472515188188e-05, "loss": 9.235011413693427e-05, "step": 12325 }, { "epoch": 1.6024393408589592, "grad_norm": 0.0019993314053863287, "learning_rate": 4.905613843782655e-05, "loss": 8.959954604506493e-05, "step": 12350 }, { "epoch": 1.6056831451926818, "grad_norm": 0.0008684620261192322, "learning_rate": 4.904751324489155e-05, "loss": 9.918049909174442e-05, "step": 12375 }, { "epoch": 1.6089269495264045, "grad_norm": 0.001378091867081821, "learning_rate": 4.903884958687327e-05, "loss": 8.719393983483314e-05, "step": 12400 }, { "epoch": 1.612170753860127, "grad_norm": 0.0015808796742931008, "learning_rate": 4.903014747762961e-05, "loss": 8.262758143246174e-05, "step": 12425 }, { "epoch": 1.6154145581938497, "grad_norm": 0.003095631254836917, "learning_rate": 4.902140693108e-05, "loss": 7.6941242441535e-05, "step": 12450 }, { "epoch": 1.6186583625275723, "grad_norm": 0.0018181019695475698, "learning_rate": 4.901262796120534e-05, "loss": 8.940341882407665e-05, "step": 12475 }, { "epoch": 1.621902166861295, "grad_norm": 0.0011836604680866003, "learning_rate": 4.900381058204798e-05, "loss": 7.99892470240593e-05, "step": 12500 }, { "epoch": 1.6251459711950176, "grad_norm": 0.002007577335461974, "learning_rate": 4.8994954807711715e-05, "loss": 7.584365084767342e-05, "step": 12525 }, { "epoch": 1.6283897755287402, "grad_norm": 0.0024333058390766382, "learning_rate": 4.898606065236176e-05, "loss": 7.386034354567528e-05, "step": 12550 }, { "epoch": 1.6316335798624628, "grad_norm": 0.002769125159829855, "learning_rate": 4.897712813022473e-05, "loss": 7.98195507377386e-05, "step": 12575 }, { "epoch": 1.6348773841961854, "grad_norm": 0.0021533065009862185, "learning_rate": 4.896815725558857e-05, "loss": 7.706476841121911e-05, "step": 12600 }, { "epoch": 1.6381211885299078, "grad_norm": 0.0015184184303507209, "learning_rate": 4.895914804280262e-05, "loss": 7.303060963749886e-05, "step": 12625 }, { "epoch": 1.6413649928636305, "grad_norm": 0.0011492094490677118, "learning_rate": 4.895010050627752e-05, "loss": 6.849856581538915e-05, "step": 12650 }, { "epoch": 1.644608797197353, "grad_norm": 0.0012416229583323002, "learning_rate": 4.8941014660485206e-05, "loss": 8.295263163745404e-05, "step": 12675 }, { "epoch": 1.6478526015310755, "grad_norm": 0.000855942431371659, "learning_rate": 4.893189051995891e-05, "loss": 9.629257023334503e-05, "step": 12700 }, { "epoch": 1.6510964058647981, "grad_norm": 0.0010177335934713483, "learning_rate": 4.892272809929309e-05, "loss": 8.950124494731426e-05, "step": 12725 }, { "epoch": 1.6543402101985207, "grad_norm": 0.0015177169116213918, "learning_rate": 4.891352741314347e-05, "loss": 7.892842404544353e-05, "step": 12750 }, { "epoch": 1.6575840145322434, "grad_norm": 0.0009625729871913791, "learning_rate": 4.8904288476226954e-05, "loss": 7.750676944851875e-05, "step": 12775 }, { "epoch": 1.660827818865966, "grad_norm": 0.0019482402130961418, "learning_rate": 4.889501130332163e-05, "loss": 7.86136370152235e-05, "step": 12800 }, { "epoch": 1.6640716231996886, "grad_norm": 0.002322196261957288, "learning_rate": 4.8885695909266774e-05, "loss": 9.151757694780827e-05, "step": 12825 }, { "epoch": 1.6673154275334112, "grad_norm": 0.0015006912872195244, "learning_rate": 4.887634230896276e-05, "loss": 8.441513404250145e-05, "step": 12850 }, { "epoch": 1.6705592318671338, "grad_norm": 0.0011894501512870193, "learning_rate": 4.886695051737112e-05, "loss": 7.292881142348051e-05, "step": 12875 }, { "epoch": 1.6738030362008565, "grad_norm": 0.0013106722617521882, "learning_rate": 4.885752054951442e-05, "loss": 8.244788274168969e-05, "step": 12900 }, { "epoch": 1.677046840534579, "grad_norm": 0.0021684474777430296, "learning_rate": 4.884805242047633e-05, "loss": 7.623545359820128e-05, "step": 12925 }, { "epoch": 1.6802906448683017, "grad_norm": 0.0007913187146186829, "learning_rate": 4.8838546145401556e-05, "loss": 7.117917761206627e-05, "step": 12950 }, { "epoch": 1.683534449202024, "grad_norm": 0.0019403360784053802, "learning_rate": 4.882900173949581e-05, "loss": 8.166171610355378e-05, "step": 12975 }, { "epoch": 1.6867782535357467, "grad_norm": 0.001734033809043467, "learning_rate": 4.88194192180258e-05, "loss": 8.204659447073937e-05, "step": 13000 }, { "epoch": 1.6900220578694694, "grad_norm": 0.0009249017457477748, "learning_rate": 4.88097985963192e-05, "loss": 7.485004607588053e-05, "step": 13025 }, { "epoch": 1.6932658622031918, "grad_norm": 0.0012221273500472307, "learning_rate": 4.8800139889764635e-05, "loss": 7.446812000125647e-05, "step": 13050 }, { "epoch": 1.6965096665369144, "grad_norm": 0.0020619439892470837, "learning_rate": 4.879044311381163e-05, "loss": 9.193746373057366e-05, "step": 13075 }, { "epoch": 1.699753470870637, "grad_norm": 0.0029657273553311825, "learning_rate": 4.8780708283970635e-05, "loss": 8.89291800558567e-05, "step": 13100 }, { "epoch": 1.7029972752043596, "grad_norm": 0.001955356216058135, "learning_rate": 4.877093541581293e-05, "loss": 7.485507987439632e-05, "step": 13125 }, { "epoch": 1.7062410795380822, "grad_norm": 0.005895772483199835, "learning_rate": 4.876112452497067e-05, "loss": 8.412405848503113e-05, "step": 13150 }, { "epoch": 1.7094848838718049, "grad_norm": 0.001371910097077489, "learning_rate": 4.875127562713682e-05, "loss": 9.229876101016998e-05, "step": 13175 }, { "epoch": 1.7127286882055275, "grad_norm": 0.0017892371397465467, "learning_rate": 4.874138873806513e-05, "loss": 8.948243223130703e-05, "step": 13200 }, { "epoch": 1.71597249253925, "grad_norm": 0.00203504110686481, "learning_rate": 4.873146387357012e-05, "loss": 8.160911500453949e-05, "step": 13225 }, { "epoch": 1.7192162968729727, "grad_norm": 0.0010578008368611336, "learning_rate": 4.8721501049527074e-05, "loss": 8.255861699581146e-05, "step": 13250 }, { "epoch": 1.7224601012066953, "grad_norm": 0.0011844673426821828, "learning_rate": 4.871150028187197e-05, "loss": 6.560753565281629e-05, "step": 13275 }, { "epoch": 1.7257039055404177, "grad_norm": 0.0008761698263697326, "learning_rate": 4.8701461586601495e-05, "loss": 8.197583258152008e-05, "step": 13300 }, { "epoch": 1.7289477098741404, "grad_norm": 0.0015370022738352418, "learning_rate": 4.869138497977298e-05, "loss": 7.208854425698519e-05, "step": 13325 }, { "epoch": 1.732191514207863, "grad_norm": 0.0028539621271193027, "learning_rate": 4.8681270477504425e-05, "loss": 7.722512818872929e-05, "step": 13350 }, { "epoch": 1.7354353185415856, "grad_norm": 0.001102591399103403, "learning_rate": 4.8671118095974435e-05, "loss": 7.685069926083088e-05, "step": 13375 }, { "epoch": 1.738679122875308, "grad_norm": 0.00244920258410275, "learning_rate": 4.86609278514222e-05, "loss": 7.899302057921886e-05, "step": 13400 }, { "epoch": 1.7419229272090306, "grad_norm": 0.0035794107243418694, "learning_rate": 4.865069976014747e-05, "loss": 7.11863161996007e-05, "step": 13425 }, { "epoch": 1.7451667315427533, "grad_norm": 0.0016711038770154119, "learning_rate": 4.864043383851054e-05, "loss": 7.937068119645118e-05, "step": 13450 }, { "epoch": 1.7484105358764759, "grad_norm": 0.0008748246473260224, "learning_rate": 4.8630130102932226e-05, "loss": 7.574514020234347e-05, "step": 13475 }, { "epoch": 1.7516543402101985, "grad_norm": 0.002120730234310031, "learning_rate": 4.86197885698938e-05, "loss": 8.051407523453236e-05, "step": 13500 }, { "epoch": 1.7548981445439211, "grad_norm": 0.0011630675289779902, "learning_rate": 4.860940925593703e-05, "loss": 7.091203704476357e-05, "step": 13525 }, { "epoch": 1.7581419488776437, "grad_norm": 0.002723243786022067, "learning_rate": 4.859899217766408e-05, "loss": 8.182130753993989e-05, "step": 13550 }, { "epoch": 1.7613857532113664, "grad_norm": 0.0016937763430178165, "learning_rate": 4.858853735173756e-05, "loss": 7.372087799012661e-05, "step": 13575 }, { "epoch": 1.764629557545089, "grad_norm": 0.001066181343048811, "learning_rate": 4.857804479488042e-05, "loss": 7.690368685871363e-05, "step": 13600 }, { "epoch": 1.7678733618788116, "grad_norm": 0.003959367983043194, "learning_rate": 4.856751452387597e-05, "loss": 7.999829947948456e-05, "step": 13625 }, { "epoch": 1.771117166212534, "grad_norm": 0.002675347262993455, "learning_rate": 4.8556946555567875e-05, "loss": 0.0001254937518388033, "step": 13650 }, { "epoch": 1.7743609705462566, "grad_norm": 0.001121043460443616, "learning_rate": 4.854634090686005e-05, "loss": 9.735020808875561e-05, "step": 13675 }, { "epoch": 1.7776047748799793, "grad_norm": 0.002578918356448412, "learning_rate": 4.853569759471674e-05, "loss": 8.859816007316113e-05, "step": 13700 }, { "epoch": 1.7808485792137019, "grad_norm": 0.0016599537339061499, "learning_rate": 4.85250166361624e-05, "loss": 8.793427608907223e-05, "step": 13725 }, { "epoch": 1.7840923835474243, "grad_norm": 0.0005664475029334426, "learning_rate": 4.851429804828168e-05, "loss": 7.855155505239963e-05, "step": 13750 }, { "epoch": 1.787336187881147, "grad_norm": 0.001409393735229969, "learning_rate": 4.8503541848219464e-05, "loss": 8.891506120562554e-05, "step": 13775 }, { "epoch": 1.7905799922148695, "grad_norm": 0.0014451773604378104, "learning_rate": 4.8492748053180776e-05, "loss": 8.817222900688649e-05, "step": 13800 }, { "epoch": 1.7905799922148695, "eval_loss": 0.00028621102683246136, "eval_runtime": 6.8691, "eval_samples_per_second": 727.895, "eval_steps_per_second": 5.823, "step": 13800 }, { "epoch": 1.7905799922148695, "eval_holdout_avg_strict_f1": 0.16289575994387603, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.5410555346621537, "eval_holdout_nemotron_pii_strict_f1": 0.46169679037756484, "eval_holdout_open_pii_masking_500k_strict_f1": 0.42060433989048873, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.3684966944524289, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 13800 }, { "epoch": 1.7938237965485921, "grad_norm": 0.0017992433859035373, "learning_rate": 4.848191668043078e-05, "loss": 7.993078790605068e-05, "step": 13825 }, { "epoch": 1.7970676008823148, "grad_norm": 0.0016151908785104752, "learning_rate": 4.847104774729474e-05, "loss": 8.325460366904735e-05, "step": 13850 }, { "epoch": 1.8003114052160374, "grad_norm": 0.0005030088359490037, "learning_rate": 4.8460141271158014e-05, "loss": 7.913115434348583e-05, "step": 13875 }, { "epoch": 1.80355520954976, "grad_norm": 0.0028371233493089676, "learning_rate": 4.8449197269466e-05, "loss": 7.86207988858223e-05, "step": 13900 }, { "epoch": 1.8067990138834826, "grad_norm": 0.0018934336258098483, "learning_rate": 4.843821575972411e-05, "loss": 7.642902433872222e-05, "step": 13925 }, { "epoch": 1.8100428182172053, "grad_norm": 0.002829365199431777, "learning_rate": 4.8427196759497796e-05, "loss": 7.457474246621132e-05, "step": 13950 }, { "epoch": 1.8132866225509279, "grad_norm": 0.0017637739656493068, "learning_rate": 4.8416140286412416e-05, "loss": 7.773185148835182e-05, "step": 13975 }, { "epoch": 1.8165304268846503, "grad_norm": 0.0008556293323636055, "learning_rate": 4.840504635815331e-05, "loss": 7.779463194310666e-05, "step": 14000 }, { "epoch": 1.819774231218373, "grad_norm": 0.0017993493238463998, "learning_rate": 4.8393914992465715e-05, "loss": 9.640770964324475e-05, "step": 14025 }, { "epoch": 1.8230180355520955, "grad_norm": 0.000892499927431345, "learning_rate": 4.838274620715475e-05, "loss": 6.752979941666127e-05, "step": 14050 }, { "epoch": 1.8262618398858181, "grad_norm": 0.0024511071387678385, "learning_rate": 4.8371540020085406e-05, "loss": 8.075581863522529e-05, "step": 14075 }, { "epoch": 1.8295056442195405, "grad_norm": 0.001369614154100418, "learning_rate": 4.836029644918246e-05, "loss": 7.937046699225903e-05, "step": 14100 }, { "epoch": 1.8327494485532632, "grad_norm": 0.0008991092909127474, "learning_rate": 4.834901551243054e-05, "loss": 7.099605165421962e-05, "step": 14125 }, { "epoch": 1.8359932528869858, "grad_norm": 0.0010980498045682907, "learning_rate": 4.833769722787399e-05, "loss": 7.277236320078373e-05, "step": 14150 }, { "epoch": 1.8392370572207084, "grad_norm": 0.0009406327735632658, "learning_rate": 4.832634161361693e-05, "loss": 6.790244020521641e-05, "step": 14175 }, { "epoch": 1.842480861554431, "grad_norm": 0.0006981506012380123, "learning_rate": 4.831494868782318e-05, "loss": 5.929016042500734e-05, "step": 14200 }, { "epoch": 1.8457246658881536, "grad_norm": 0.004993625916540623, "learning_rate": 4.830351846871623e-05, "loss": 7.173890713602305e-05, "step": 14225 }, { "epoch": 1.8489684702218763, "grad_norm": 0.0017329213442280889, "learning_rate": 4.829205097457923e-05, "loss": 7.702444680035114e-05, "step": 14250 }, { "epoch": 1.852212274555599, "grad_norm": 0.0009655167232267559, "learning_rate": 4.8280546223754967e-05, "loss": 6.429588422179221e-05, "step": 14275 }, { "epoch": 1.8554560788893215, "grad_norm": 0.001568168168887496, "learning_rate": 4.8269004234645805e-05, "loss": 6.835578475147485e-05, "step": 14300 }, { "epoch": 1.8586998832230441, "grad_norm": 0.0006995972944423556, "learning_rate": 4.825742502571366e-05, "loss": 7.055698893964291e-05, "step": 14325 }, { "epoch": 1.8619436875567665, "grad_norm": 0.001590573345310986, "learning_rate": 4.824580861548004e-05, "loss": 7.025405764579773e-05, "step": 14350 }, { "epoch": 1.8651874918904892, "grad_norm": 0.0014081131666898727, "learning_rate": 4.823415502252587e-05, "loss": 6.783813703805209e-05, "step": 14375 }, { "epoch": 1.8684312962242118, "grad_norm": 0.0010710358619689941, "learning_rate": 4.8222464265491624e-05, "loss": 7.427906617522239e-05, "step": 14400 }, { "epoch": 1.8716751005579342, "grad_norm": 0.0010218314127996564, "learning_rate": 4.821073636307719e-05, "loss": 6.696430034935474e-05, "step": 14425 }, { "epoch": 1.8749189048916568, "grad_norm": 0.0011292512062937021, "learning_rate": 4.819897133404189e-05, "loss": 6.755630020052194e-05, "step": 14450 }, { "epoch": 1.8781627092253794, "grad_norm": 0.0012575897853821516, "learning_rate": 4.8187169197204395e-05, "loss": 6.622707936912775e-05, "step": 14475 }, { "epoch": 1.881406513559102, "grad_norm": 0.0013158308574929833, "learning_rate": 4.8175329971442774e-05, "loss": 7.714783772826195e-05, "step": 14500 }, { "epoch": 1.8846503178928247, "grad_norm": 0.000693166337441653, "learning_rate": 4.8163453675694396e-05, "loss": 6.389220245182514e-05, "step": 14525 }, { "epoch": 1.8878941222265473, "grad_norm": 0.0005092194187454879, "learning_rate": 4.8151540328955935e-05, "loss": 6.637971848249435e-05, "step": 14550 }, { "epoch": 1.89113792656027, "grad_norm": 0.0011929867323487997, "learning_rate": 4.813958995028333e-05, "loss": 6.236397661268711e-05, "step": 14575 }, { "epoch": 1.8943817308939925, "grad_norm": 0.001532752881757915, "learning_rate": 4.812760255879175e-05, "loss": 7.077332120388746e-05, "step": 14600 }, { "epoch": 1.8976255352277152, "grad_norm": 0.0011661503231152892, "learning_rate": 4.811557817365556e-05, "loss": 7.278126198798418e-05, "step": 14625 }, { "epoch": 1.9008693395614378, "grad_norm": 0.00247553619556129, "learning_rate": 4.810351681410832e-05, "loss": 6.765744648873806e-05, "step": 14650 }, { "epoch": 1.9041131438951604, "grad_norm": 0.0011613015085458755, "learning_rate": 4.8091418499442705e-05, "loss": 6.806576158851384e-05, "step": 14675 }, { "epoch": 1.9073569482288828, "grad_norm": 0.0010280158603563905, "learning_rate": 4.8079283249010535e-05, "loss": 6.903153844177723e-05, "step": 14700 }, { "epoch": 1.9106007525626054, "grad_norm": 0.0010567547287791967, "learning_rate": 4.806711108222267e-05, "loss": 7.839513942599297e-05, "step": 14725 }, { "epoch": 1.913844556896328, "grad_norm": 0.0014772460563108325, "learning_rate": 4.805490201854905e-05, "loss": 7.287751417607069e-05, "step": 14750 }, { "epoch": 1.9170883612300504, "grad_norm": 0.0011612212983891368, "learning_rate": 4.8042656077518625e-05, "loss": 7.574753370136022e-05, "step": 14775 }, { "epoch": 1.920332165563773, "grad_norm": 0.002476678928360343, "learning_rate": 4.8030373278719335e-05, "loss": 8.059391751885414e-05, "step": 14800 }, { "epoch": 1.9235759698974957, "grad_norm": 0.0009961245814338326, "learning_rate": 4.801805364179806e-05, "loss": 7.313782349228859e-05, "step": 14825 }, { "epoch": 1.9268197742312183, "grad_norm": 0.0009172203717753291, "learning_rate": 4.800569718646062e-05, "loss": 8.575986139476299e-05, "step": 14850 }, { "epoch": 1.930063578564941, "grad_norm": 0.0007917257025837898, "learning_rate": 4.7993303932471726e-05, "loss": 6.733985617756843e-05, "step": 14875 }, { "epoch": 1.9333073828986636, "grad_norm": 0.0010068488772958517, "learning_rate": 4.798087389965495e-05, "loss": 6.0743745416402815e-05, "step": 14900 }, { "epoch": 1.9365511872323862, "grad_norm": 0.0011633482063189149, "learning_rate": 4.7968407107892684e-05, "loss": 6.796516478061675e-05, "step": 14925 }, { "epoch": 1.9397949915661088, "grad_norm": 0.0008138160337693989, "learning_rate": 4.795590357712613e-05, "loss": 6.525983568280935e-05, "step": 14950 }, { "epoch": 1.9430387958998314, "grad_norm": 0.0009562924969941378, "learning_rate": 4.794336332735524e-05, "loss": 7.225790526717902e-05, "step": 14975 }, { "epoch": 1.946282600233554, "grad_norm": 0.0008769669802859426, "learning_rate": 4.793078637863872e-05, "loss": 5.9787044301629065e-05, "step": 15000 }, { "epoch": 1.9495264045672767, "grad_norm": 0.000941862934269011, "learning_rate": 4.791817275109396e-05, "loss": 6.927200593054295e-05, "step": 15025 }, { "epoch": 1.952770208900999, "grad_norm": 0.0014511779882013798, "learning_rate": 4.790552246489703e-05, "loss": 6.241975352168083e-05, "step": 15050 }, { "epoch": 1.9560140132347217, "grad_norm": 0.0010261726565659046, "learning_rate": 4.789283554028264e-05, "loss": 6.856746040284634e-05, "step": 15075 }, { "epoch": 1.9592578175684443, "grad_norm": 0.002154337940737605, "learning_rate": 4.7880111997544094e-05, "loss": 6.816055625677108e-05, "step": 15100 }, { "epoch": 1.9625016219021667, "grad_norm": 0.0010185635183006525, "learning_rate": 4.786735185703327e-05, "loss": 5.7463934645056725e-05, "step": 15125 }, { "epoch": 1.9657454262358893, "grad_norm": 0.002066479530185461, "learning_rate": 4.785455513916059e-05, "loss": 6.038195919245482e-05, "step": 15150 }, { "epoch": 1.968989230569612, "grad_norm": 0.0009665784891694784, "learning_rate": 4.784172186439499e-05, "loss": 5.422243382781744e-05, "step": 15175 }, { "epoch": 1.9722330349033346, "grad_norm": 0.0013866373337805271, "learning_rate": 4.7828852053263865e-05, "loss": 5.931714083999395e-05, "step": 15200 }, { "epoch": 1.9754768392370572, "grad_norm": 0.0008066284353844821, "learning_rate": 4.781594572635306e-05, "loss": 5.632000043988228e-05, "step": 15225 }, { "epoch": 1.9787206435707798, "grad_norm": 0.000465130724478513, "learning_rate": 4.780300290430682e-05, "loss": 6.41647819429636e-05, "step": 15250 }, { "epoch": 1.9819644479045024, "grad_norm": 0.0022965874522924423, "learning_rate": 4.779002360782779e-05, "loss": 6.641185842454434e-05, "step": 15275 }, { "epoch": 1.985208252238225, "grad_norm": 0.002456093905493617, "learning_rate": 4.777700785767694e-05, "loss": 7.371004670858383e-05, "step": 15300 }, { "epoch": 1.9884520565719477, "grad_norm": 0.0011670672101899981, "learning_rate": 4.776395567467353e-05, "loss": 5.789134651422501e-05, "step": 15325 }, { "epoch": 1.9916958609056703, "grad_norm": 0.0011417181231081486, "learning_rate": 4.775086707969513e-05, "loss": 6.043701898306608e-05, "step": 15350 }, { "epoch": 1.994939665239393, "grad_norm": 0.002112944843247533, "learning_rate": 4.773774209367753e-05, "loss": 8.008132688701153e-05, "step": 15375 }, { "epoch": 1.9981834695731153, "grad_norm": 0.0008301316411234438, "learning_rate": 4.7724580737614755e-05, "loss": 7.78111582621932e-05, "step": 15400 }, { "epoch": 2.0014272739068377, "grad_norm": 0.001274540787562728, "learning_rate": 4.7711383032558976e-05, "loss": 6.782150827348232e-05, "step": 15425 }, { "epoch": 2.0046710782405603, "grad_norm": 0.0010873471619561315, "learning_rate": 4.769814899962052e-05, "loss": 6.420539692044258e-05, "step": 15450 }, { "epoch": 2.007914882574283, "grad_norm": 0.000750692212022841, "learning_rate": 4.7684878659967816e-05, "loss": 6.27730367705226e-05, "step": 15475 }, { "epoch": 2.0111586869080056, "grad_norm": 0.0010055204620584846, "learning_rate": 4.7671572034827375e-05, "loss": 6.0947081074118614e-05, "step": 15500 }, { "epoch": 2.014402491241728, "grad_norm": 0.0011479125823825598, "learning_rate": 4.765822914548375e-05, "loss": 6.0180709697306155e-05, "step": 15525 }, { "epoch": 2.017646295575451, "grad_norm": 0.0013083955273032188, "learning_rate": 4.764485001327949e-05, "loss": 5.9014311991631987e-05, "step": 15550 }, { "epoch": 2.0208900999091735, "grad_norm": 0.0008779132040217519, "learning_rate": 4.763143465961512e-05, "loss": 6.733686197549105e-05, "step": 15575 }, { "epoch": 2.024133904242896, "grad_norm": 0.0008410927839577198, "learning_rate": 4.761798310594911e-05, "loss": 6.902824621647596e-05, "step": 15600 }, { "epoch": 2.0273777085766187, "grad_norm": 0.0028562024235725403, "learning_rate": 4.760449537379782e-05, "loss": 6.163925863802432e-05, "step": 15625 }, { "epoch": 2.0306215129103413, "grad_norm": 0.0007592672482132912, "learning_rate": 4.7590971484735495e-05, "loss": 6.602572742849589e-05, "step": 15650 }, { "epoch": 2.033865317244064, "grad_norm": 0.0010342145105823874, "learning_rate": 4.757741146039419e-05, "loss": 7.126634940505028e-05, "step": 15675 }, { "epoch": 2.0371091215777866, "grad_norm": 0.001749491784721613, "learning_rate": 4.756381532246379e-05, "loss": 6.504145450890064e-05, "step": 15700 }, { "epoch": 2.040352925911509, "grad_norm": 0.0031394860707223415, "learning_rate": 4.755018309269194e-05, "loss": 5.117744673043489e-05, "step": 15725 }, { "epoch": 2.043596730245232, "grad_norm": 0.0009203410590998828, "learning_rate": 4.753651479288398e-05, "loss": 7.345256861299276e-05, "step": 15750 }, { "epoch": 2.046840534578954, "grad_norm": 0.002024740446358919, "learning_rate": 4.7522810444903e-05, "loss": 6.23815692961216e-05, "step": 15775 }, { "epoch": 2.0500843389126766, "grad_norm": 0.0016759359277784824, "learning_rate": 4.75090700706697e-05, "loss": 7.103788200765848e-05, "step": 15800 }, { "epoch": 2.0533281432463992, "grad_norm": 0.0005622164462693036, "learning_rate": 4.749529369216246e-05, "loss": 6.09663687646389e-05, "step": 15825 }, { "epoch": 2.056571947580122, "grad_norm": 0.0009406614699400961, "learning_rate": 4.748148133141718e-05, "loss": 6.393078248947859e-05, "step": 15850 }, { "epoch": 2.0598157519138445, "grad_norm": 0.0015304385451599956, "learning_rate": 4.746763301052739e-05, "loss": 5.871599074453116e-05, "step": 15875 }, { "epoch": 2.063059556247567, "grad_norm": 0.0009464545291848481, "learning_rate": 4.7453748751644075e-05, "loss": 6.833617575466633e-05, "step": 15900 }, { "epoch": 2.0663033605812897, "grad_norm": 0.0010370747186243534, "learning_rate": 4.7439828576975766e-05, "loss": 6.598201114684344e-05, "step": 15925 }, { "epoch": 2.0695471649150123, "grad_norm": 0.0050219022668898106, "learning_rate": 4.7425872508788384e-05, "loss": 5.822454113513231e-05, "step": 15950 }, { "epoch": 2.072790969248735, "grad_norm": 0.0011437920620664954, "learning_rate": 4.74118805694053e-05, "loss": 5.549767054617405e-05, "step": 15975 }, { "epoch": 2.0760347735824576, "grad_norm": 0.002084362553432584, "learning_rate": 4.739785278120725e-05, "loss": 6.091033574193716e-05, "step": 16000 }, { "epoch": 2.07927857791618, "grad_norm": 0.0012393668293952942, "learning_rate": 4.738378916663233e-05, "loss": 6.483460310846567e-05, "step": 16025 }, { "epoch": 2.082522382249903, "grad_norm": 0.001234677154570818, "learning_rate": 4.73696897481759e-05, "loss": 6.876432336866856e-05, "step": 16050 }, { "epoch": 2.0857661865836254, "grad_norm": 0.0019152307650074363, "learning_rate": 4.7355554548390636e-05, "loss": 7.432758808135986e-05, "step": 16075 }, { "epoch": 2.089009990917348, "grad_norm": 0.0007152243051677942, "learning_rate": 4.7341383589886423e-05, "loss": 7.619905285537243e-05, "step": 16100 }, { "epoch": 2.0922537952510702, "grad_norm": 0.006245169788599014, "learning_rate": 4.732717689533035e-05, "loss": 5.653427913784981e-05, "step": 16125 }, { "epoch": 2.095497599584793, "grad_norm": 0.0007941206567920744, "learning_rate": 4.731293448744666e-05, "loss": 5.578515585511923e-05, "step": 16150 }, { "epoch": 2.0987414039185155, "grad_norm": 0.0036797462962567806, "learning_rate": 4.7298656389016735e-05, "loss": 6.625200621783734e-05, "step": 16175 }, { "epoch": 2.101985208252238, "grad_norm": 0.00220097484998405, "learning_rate": 4.728434262287904e-05, "loss": 6.716974079608918e-05, "step": 16200 }, { "epoch": 2.1052290125859607, "grad_norm": 0.0011315939482301474, "learning_rate": 4.726999321192908e-05, "loss": 6.378018297255039e-05, "step": 16225 }, { "epoch": 2.1084728169196834, "grad_norm": 0.0014813186135143042, "learning_rate": 4.725560817911939e-05, "loss": 6.043429486453533e-05, "step": 16250 }, { "epoch": 2.111716621253406, "grad_norm": 0.0009171017445623875, "learning_rate": 4.724118754745949e-05, "loss": 5.768408067524433e-05, "step": 16275 }, { "epoch": 2.1149604255871286, "grad_norm": 0.0010123832616955042, "learning_rate": 4.7226731340015814e-05, "loss": 6.164350546896458e-05, "step": 16300 }, { "epoch": 2.1182042299208512, "grad_norm": 0.0010498963529244065, "learning_rate": 4.721223957991174e-05, "loss": 5.677357316017151e-05, "step": 16325 }, { "epoch": 2.121448034254574, "grad_norm": 0.0007775750127620995, "learning_rate": 4.7197712290327465e-05, "loss": 5.575641058385372e-05, "step": 16350 }, { "epoch": 2.1246918385882965, "grad_norm": 0.0010830371174961329, "learning_rate": 4.718314949450007e-05, "loss": 7.547513116151094e-05, "step": 16375 }, { "epoch": 2.127935642922019, "grad_norm": 0.005400130059570074, "learning_rate": 4.7168551215723395e-05, "loss": 6.671285722404718e-05, "step": 16400 }, { "epoch": 2.1311794472557417, "grad_norm": 0.0010221345582976937, "learning_rate": 4.715391747734804e-05, "loss": 6.116392090916633e-05, "step": 16425 }, { "epoch": 2.134423251589464, "grad_norm": 0.0018388223834335804, "learning_rate": 4.7139248302781335e-05, "loss": 5.557825323194265e-05, "step": 16450 }, { "epoch": 2.1376670559231865, "grad_norm": 0.0011934456415474415, "learning_rate": 4.712454371548729e-05, "loss": 6.337139755487442e-05, "step": 16475 }, { "epoch": 2.140910860256909, "grad_norm": 0.0019593157339841127, "learning_rate": 4.710980373898656e-05, "loss": 7.207899820059538e-05, "step": 16500 }, { "epoch": 2.1441546645906318, "grad_norm": 0.0006870873039588332, "learning_rate": 4.709502839685639e-05, "loss": 5.7127662003040314e-05, "step": 16525 }, { "epoch": 2.1473984689243544, "grad_norm": 0.00065016676671803, "learning_rate": 4.708021771273061e-05, "loss": 5.559897981584072e-05, "step": 16550 }, { "epoch": 2.150642273258077, "grad_norm": 0.0014222875470295548, "learning_rate": 4.706537171029959e-05, "loss": 5.7039358653128145e-05, "step": 16575 }, { "epoch": 2.1538860775917996, "grad_norm": 0.0008006573189049959, "learning_rate": 4.7050490413310166e-05, "loss": 6.028616335242987e-05, "step": 16600 }, { "epoch": 2.1571298819255222, "grad_norm": 0.0018469318747520447, "learning_rate": 4.703557384556566e-05, "loss": 6.495026405900717e-05, "step": 16625 }, { "epoch": 2.160373686259245, "grad_norm": 0.0006900982698425651, "learning_rate": 4.7020622030925785e-05, "loss": 5.94747019931674e-05, "step": 16650 }, { "epoch": 2.1636174905929675, "grad_norm": 0.0014392179436981678, "learning_rate": 4.700563499330664e-05, "loss": 5.595467984676361e-05, "step": 16675 }, { "epoch": 2.16686129492669, "grad_norm": 0.0035675407852977514, "learning_rate": 4.699061275668068e-05, "loss": 6.046608556061983e-05, "step": 16700 }, { "epoch": 2.1701050992604127, "grad_norm": 0.001082102651707828, "learning_rate": 4.6975555345076644e-05, "loss": 5.954996682703495e-05, "step": 16725 }, { "epoch": 2.1733489035941354, "grad_norm": 0.0012325086863711476, "learning_rate": 4.696046278257954e-05, "loss": 6.631665863096714e-05, "step": 16750 }, { "epoch": 2.176592707927858, "grad_norm": 0.0014705209759995341, "learning_rate": 4.694533509333061e-05, "loss": 6.277582142502069e-05, "step": 16775 }, { "epoch": 2.1798365122615806, "grad_norm": 0.002401568926870823, "learning_rate": 4.693017230152727e-05, "loss": 6.723280530422926e-05, "step": 16800 }, { "epoch": 2.1830803165953028, "grad_norm": 0.0018796154763549566, "learning_rate": 4.6914974431423095e-05, "loss": 6.516513414680958e-05, "step": 16825 }, { "epoch": 2.1863241209290254, "grad_norm": 0.002211836399510503, "learning_rate": 4.689974150732776e-05, "loss": 6.814585532993078e-05, "step": 16850 }, { "epoch": 2.189567925262748, "grad_norm": 0.000680724682752043, "learning_rate": 4.688447355360702e-05, "loss": 7.058924995362759e-05, "step": 16875 }, { "epoch": 2.1928117295964706, "grad_norm": 0.0011872730683535337, "learning_rate": 4.686917059468265e-05, "loss": 6.590130738914013e-05, "step": 16900 }, { "epoch": 2.1960555339301933, "grad_norm": 0.0019986594561487436, "learning_rate": 4.685383265503243e-05, "loss": 7.342448923736811e-05, "step": 16925 }, { "epoch": 2.199299338263916, "grad_norm": 0.0013751668157055974, "learning_rate": 4.683845975919008e-05, "loss": 6.503782235085964e-05, "step": 16950 }, { "epoch": 2.2025431425976385, "grad_norm": 0.001519917044788599, "learning_rate": 4.682305193174524e-05, "loss": 6.175130140036345e-05, "step": 16975 }, { "epoch": 2.205786946931361, "grad_norm": 0.0011367384577170014, "learning_rate": 4.6807609197343444e-05, "loss": 6.641847547143698e-05, "step": 17000 }, { "epoch": 2.2090307512650837, "grad_norm": 0.0016465997323393822, "learning_rate": 4.679213158068602e-05, "loss": 5.857688374817371e-05, "step": 17025 }, { "epoch": 2.2122745555988064, "grad_norm": 0.001116060302592814, "learning_rate": 4.677661910653013e-05, "loss": 6.897761486470699e-05, "step": 17050 }, { "epoch": 2.215518359932529, "grad_norm": 0.0016632082406431437, "learning_rate": 4.676107179968867e-05, "loss": 6.391846109181643e-05, "step": 17075 }, { "epoch": 2.2187621642662516, "grad_norm": 0.0019938445184379816, "learning_rate": 4.674548968503026e-05, "loss": 7.023543119430542e-05, "step": 17100 }, { "epoch": 2.2220059685999742, "grad_norm": 0.0008942094864323735, "learning_rate": 4.672987278747919e-05, "loss": 5.692241247743368e-05, "step": 17125 }, { "epoch": 2.2252497729336964, "grad_norm": 0.0014288020320236683, "learning_rate": 4.671422113201541e-05, "loss": 6.357506383210421e-05, "step": 17150 }, { "epoch": 2.228493577267419, "grad_norm": 0.001207267283461988, "learning_rate": 4.6698534743674436e-05, "loss": 6.154441274702549e-05, "step": 17175 }, { "epoch": 2.2317373816011417, "grad_norm": 0.0014622053131461143, "learning_rate": 4.668281364754735e-05, "loss": 6.679147947579622e-05, "step": 17200 }, { "epoch": 2.2349811859348643, "grad_norm": 0.0019345682812854648, "learning_rate": 4.666705786878077e-05, "loss": 7.240661885589361e-05, "step": 17225 }, { "epoch": 2.238224990268587, "grad_norm": 0.0017180965514853597, "learning_rate": 4.665126743257677e-05, "loss": 6.113220937550068e-05, "step": 17250 }, { "epoch": 2.238224990268587, "eval_loss": 0.0002635233395267278, "eval_runtime": 6.7917, "eval_samples_per_second": 736.196, "eval_steps_per_second": 5.89, "step": 17250 }, { "epoch": 2.238224990268587, "eval_holdout_avg_strict_f1": 0.19016805326670097, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.6582696056380268, "eval_holdout_nemotron_pii_strict_f1": 0.5635226819209791, "eval_holdout_open_pii_masking_500k_strict_f1": 0.4583960438615351, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.41166025451316957, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 17250 }, { "epoch": 2.2414687946023095, "grad_norm": 0.0016182535327970982, "learning_rate": 4.663544236419286e-05, "loss": 6.702410988509655e-05, "step": 17275 }, { "epoch": 2.244712598936032, "grad_norm": 0.0013112551532685757, "learning_rate": 4.6619582688941967e-05, "loss": 5.697115790098906e-05, "step": 17300 }, { "epoch": 2.2479564032697548, "grad_norm": 0.004770216997712851, "learning_rate": 4.660368843219233e-05, "loss": 6.503615994006395e-05, "step": 17325 }, { "epoch": 2.2512002076034774, "grad_norm": 0.0015921492595225573, "learning_rate": 4.6587759619367556e-05, "loss": 5.98308676853776e-05, "step": 17350 }, { "epoch": 2.2544440119372, "grad_norm": 0.0013045334490016103, "learning_rate": 4.657179627594649e-05, "loss": 6.155623123049736e-05, "step": 17375 }, { "epoch": 2.2576878162709226, "grad_norm": 0.0014331517741084099, "learning_rate": 4.6555798427463214e-05, "loss": 5.8888327330350876e-05, "step": 17400 }, { "epoch": 2.2609316206046453, "grad_norm": 0.0008224392659030855, "learning_rate": 4.653976609950702e-05, "loss": 6.343248300254345e-05, "step": 17425 }, { "epoch": 2.264175424938368, "grad_norm": 0.0007194095524027944, "learning_rate": 4.6523699317722344e-05, "loss": 6.0496018268167976e-05, "step": 17450 }, { "epoch": 2.2674192292720905, "grad_norm": 0.001750152325257659, "learning_rate": 4.650759810780872e-05, "loss": 6.371530238538981e-05, "step": 17475 }, { "epoch": 2.270663033605813, "grad_norm": 0.0006566008669324219, "learning_rate": 4.6491462495520755e-05, "loss": 4.8616686835885045e-05, "step": 17500 }, { "epoch": 2.2739068379395353, "grad_norm": 0.0011204618494957685, "learning_rate": 4.64752925066681e-05, "loss": 5.198880098760128e-05, "step": 17525 }, { "epoch": 2.277150642273258, "grad_norm": 0.0010584210976958275, "learning_rate": 4.645908816711538e-05, "loss": 5.15294773504138e-05, "step": 17550 }, { "epoch": 2.2803944466069805, "grad_norm": 0.0009662836091592908, "learning_rate": 4.644284950278217e-05, "loss": 5.907395388931036e-05, "step": 17575 }, { "epoch": 2.283638250940703, "grad_norm": 0.001671878737397492, "learning_rate": 4.6426576539642944e-05, "loss": 5.658445879817009e-05, "step": 17600 }, { "epoch": 2.286882055274426, "grad_norm": 0.00045820677769370377, "learning_rate": 4.641026930372703e-05, "loss": 5.365137942135334e-05, "step": 17625 }, { "epoch": 2.2901258596081484, "grad_norm": 0.005284789018332958, "learning_rate": 4.639392782111861e-05, "loss": 5.764308851212263e-05, "step": 17650 }, { "epoch": 2.293369663941871, "grad_norm": 0.0005423437105491757, "learning_rate": 4.6377552117956605e-05, "loss": 6.170740816742182e-05, "step": 17675 }, { "epoch": 2.2966134682755937, "grad_norm": 0.0007329126819968224, "learning_rate": 4.636114222043471e-05, "loss": 5.656846798956394e-05, "step": 17700 }, { "epoch": 2.2998572726093163, "grad_norm": 0.0007795207784511149, "learning_rate": 4.634469815480128e-05, "loss": 5.613509099930525e-05, "step": 17725 }, { "epoch": 2.303101076943039, "grad_norm": 0.0009231014992110431, "learning_rate": 4.6328219947359345e-05, "loss": 4.774017259478569e-05, "step": 17750 }, { "epoch": 2.3063448812767615, "grad_norm": 0.0014131237985566258, "learning_rate": 4.631170762446654e-05, "loss": 5.8499393053352835e-05, "step": 17775 }, { "epoch": 2.309588685610484, "grad_norm": 0.0016996270278468728, "learning_rate": 4.6295161212535085e-05, "loss": 5.984154064208269e-05, "step": 17800 }, { "epoch": 2.3128324899442068, "grad_norm": 0.0023738713935017586, "learning_rate": 4.62785807380317e-05, "loss": 6.056112237274647e-05, "step": 17825 }, { "epoch": 2.316076294277929, "grad_norm": 0.0015172789571806788, "learning_rate": 4.62619662274776e-05, "loss": 7.487225811928511e-05, "step": 17850 }, { "epoch": 2.3193200986116516, "grad_norm": 0.001304394449107349, "learning_rate": 4.624531770744845e-05, "loss": 6.638495717197656e-05, "step": 17875 }, { "epoch": 2.322563902945374, "grad_norm": 0.0008217108552344143, "learning_rate": 4.622863520457431e-05, "loss": 5.8523928746581074e-05, "step": 17900 }, { "epoch": 2.325807707279097, "grad_norm": 0.002014805329963565, "learning_rate": 4.621191874553961e-05, "loss": 6.741347722709179e-05, "step": 17925 }, { "epoch": 2.3290515116128194, "grad_norm": 0.0012340594548732042, "learning_rate": 4.619516835708305e-05, "loss": 5.731149576604366e-05, "step": 17950 }, { "epoch": 2.332295315946542, "grad_norm": 0.0010709335329011083, "learning_rate": 4.617838406599766e-05, "loss": 5.777557846158743e-05, "step": 17975 }, { "epoch": 2.3355391202802647, "grad_norm": 0.001265083672478795, "learning_rate": 4.616156589913066e-05, "loss": 6.128018256276846e-05, "step": 18000 }, { "epoch": 2.3387829246139873, "grad_norm": 0.0018042369047179818, "learning_rate": 4.614471388338346e-05, "loss": 6.411097943782806e-05, "step": 18025 }, { "epoch": 2.34202672894771, "grad_norm": 0.0016456886660307646, "learning_rate": 4.612782804571164e-05, "loss": 5.429653450846672e-05, "step": 18050 }, { "epoch": 2.3452705332814325, "grad_norm": 0.0005386894335970283, "learning_rate": 4.6110908413124844e-05, "loss": 5.785825196653604e-05, "step": 18075 }, { "epoch": 2.348514337615155, "grad_norm": 0.0008323945803567767, "learning_rate": 4.60939550126868e-05, "loss": 6.103419698774815e-05, "step": 18100 }, { "epoch": 2.351758141948878, "grad_norm": 0.0007758743013255298, "learning_rate": 4.607696787151522e-05, "loss": 6.170956417918205e-05, "step": 18125 }, { "epoch": 2.3550019462826004, "grad_norm": 0.0006034644902683794, "learning_rate": 4.605994701678182e-05, "loss": 5.2654137834906575e-05, "step": 18150 }, { "epoch": 2.358245750616323, "grad_norm": 0.0013105672551319003, "learning_rate": 4.604289247571222e-05, "loss": 5.966693628579378e-05, "step": 18175 }, { "epoch": 2.3614895549500456, "grad_norm": 0.0021546287462115288, "learning_rate": 4.6025804275585923e-05, "loss": 5.627896636724472e-05, "step": 18200 }, { "epoch": 2.364733359283768, "grad_norm": 0.0009753959020599723, "learning_rate": 4.600868244373629e-05, "loss": 4.9737952649593354e-05, "step": 18225 }, { "epoch": 2.3679771636174904, "grad_norm": 0.0025071967393159866, "learning_rate": 4.599152700755045e-05, "loss": 6.24960521236062e-05, "step": 18250 }, { "epoch": 2.371220967951213, "grad_norm": 0.0045777419582009315, "learning_rate": 4.597433799446931e-05, "loss": 5.872861947864294e-05, "step": 18275 }, { "epoch": 2.3744647722849357, "grad_norm": 0.0017984769074246287, "learning_rate": 4.5957115431987456e-05, "loss": 6.045766174793243e-05, "step": 18300 }, { "epoch": 2.3777085766186583, "grad_norm": 0.0008955154335126281, "learning_rate": 4.593985934765317e-05, "loss": 5.428563803434372e-05, "step": 18325 }, { "epoch": 2.380952380952381, "grad_norm": 0.000718228577170521, "learning_rate": 4.5922569769068337e-05, "loss": 5.7072602212429045e-05, "step": 18350 }, { "epoch": 2.3841961852861036, "grad_norm": 0.010487344115972519, "learning_rate": 4.590524672388842e-05, "loss": 6.243649404495955e-05, "step": 18375 }, { "epoch": 2.387439989619826, "grad_norm": 0.000750688195694238, "learning_rate": 4.5887890239822394e-05, "loss": 5.303144920617342e-05, "step": 18400 }, { "epoch": 2.390683793953549, "grad_norm": 0.0008748677792027593, "learning_rate": 4.587050034463276e-05, "loss": 5.6995968334376814e-05, "step": 18425 }, { "epoch": 2.3939275982872714, "grad_norm": 0.0008842506795190275, "learning_rate": 4.5853077066135425e-05, "loss": 5.651137325912714e-05, "step": 18450 }, { "epoch": 2.397171402620994, "grad_norm": 0.0010263564763590693, "learning_rate": 4.583562043219972e-05, "loss": 5.729707889258861e-05, "step": 18475 }, { "epoch": 2.4004152069547167, "grad_norm": 0.0018930226797237992, "learning_rate": 4.5818130470748315e-05, "loss": 6.541605573147535e-05, "step": 18500 }, { "epoch": 2.403659011288439, "grad_norm": 0.0029299557209014893, "learning_rate": 4.5800607209757195e-05, "loss": 6.35345745831728e-05, "step": 18525 }, { "epoch": 2.4069028156221615, "grad_norm": 0.0011962739517912269, "learning_rate": 4.578305067725561e-05, "loss": 7.315068505704403e-05, "step": 18550 }, { "epoch": 2.410146619955884, "grad_norm": 0.0013640476390719414, "learning_rate": 4.5765460901326016e-05, "loss": 6.213285494595766e-05, "step": 18575 }, { "epoch": 2.4133904242896067, "grad_norm": 0.001347828540019691, "learning_rate": 4.574783791010407e-05, "loss": 7.453013677150011e-05, "step": 18600 }, { "epoch": 2.4166342286233293, "grad_norm": 0.0038168029859662056, "learning_rate": 4.573018173177853e-05, "loss": 7.867606356739998e-05, "step": 18625 }, { "epoch": 2.419878032957052, "grad_norm": 0.0015298950020223856, "learning_rate": 4.5712492394591245e-05, "loss": 8.978086523711681e-05, "step": 18650 }, { "epoch": 2.4231218372907746, "grad_norm": 0.001124762580730021, "learning_rate": 4.569476992683712e-05, "loss": 6.369809620082378e-05, "step": 18675 }, { "epoch": 2.426365641624497, "grad_norm": 0.001214916235767305, "learning_rate": 4.567701435686404e-05, "loss": 5.423621740192175e-05, "step": 18700 }, { "epoch": 2.42960944595822, "grad_norm": 0.0007485290407203138, "learning_rate": 4.565922571307285e-05, "loss": 5.05424477159977e-05, "step": 18725 }, { "epoch": 2.4328532502919424, "grad_norm": 0.0010098085040226579, "learning_rate": 4.5641404023917274e-05, "loss": 6.17220439016819e-05, "step": 18750 }, { "epoch": 2.436097054625665, "grad_norm": 0.0007279584533534944, "learning_rate": 4.5623549317903915e-05, "loss": 5.0616688095033166e-05, "step": 18775 }, { "epoch": 2.4393408589593877, "grad_norm": 0.0019331490620970726, "learning_rate": 4.560566162359217e-05, "loss": 6.201838608831167e-05, "step": 18800 }, { "epoch": 2.4425846632931103, "grad_norm": 0.0011670601088553667, "learning_rate": 4.558774096959423e-05, "loss": 5.5516487918794155e-05, "step": 18825 }, { "epoch": 2.445828467626833, "grad_norm": 0.0009654265595600009, "learning_rate": 4.556978738457499e-05, "loss": 5.6612351909279826e-05, "step": 18850 }, { "epoch": 2.4490722719605555, "grad_norm": 0.0024051018990576267, "learning_rate": 4.555180089725201e-05, "loss": 5.312634631991387e-05, "step": 18875 }, { "epoch": 2.452316076294278, "grad_norm": 0.0004879662301391363, "learning_rate": 4.5533781536395495e-05, "loss": 5.2810143679380416e-05, "step": 18900 }, { "epoch": 2.4555598806280003, "grad_norm": 0.001054049818776548, "learning_rate": 4.551572933082822e-05, "loss": 4.6661305241286754e-05, "step": 18925 }, { "epoch": 2.458803684961723, "grad_norm": 0.0009839426493272185, "learning_rate": 4.5497644309425516e-05, "loss": 5.369991529732943e-05, "step": 18950 }, { "epoch": 2.4620474892954456, "grad_norm": 0.0010525831021368504, "learning_rate": 4.547952650111517e-05, "loss": 5.1316693425178525e-05, "step": 18975 }, { "epoch": 2.465291293629168, "grad_norm": 0.0015101778553798795, "learning_rate": 4.546137593487746e-05, "loss": 5.9760310687124726e-05, "step": 19000 }, { "epoch": 2.468535097962891, "grad_norm": 0.0015365019207820296, "learning_rate": 4.5443192639745015e-05, "loss": 5.987817421555519e-05, "step": 19025 }, { "epoch": 2.4717789022966135, "grad_norm": 0.0008458250085823238, "learning_rate": 4.542497664480284e-05, "loss": 5.206458270549774e-05, "step": 19050 }, { "epoch": 2.475022706630336, "grad_norm": 0.0008645106572657824, "learning_rate": 4.5406727979188255e-05, "loss": 5.8201109059154984e-05, "step": 19075 }, { "epoch": 2.4782665109640587, "grad_norm": 0.001099140616133809, "learning_rate": 4.5388446672090814e-05, "loss": 6.792063359171153e-05, "step": 19100 }, { "epoch": 2.4815103152977813, "grad_norm": 0.0017211961094290018, "learning_rate": 4.5370132752752294e-05, "loss": 5.824710242450237e-05, "step": 19125 }, { "epoch": 2.484754119631504, "grad_norm": 0.0028032278642058372, "learning_rate": 4.5351786250466636e-05, "loss": 7.019483484327794e-05, "step": 19150 }, { "epoch": 2.4879979239652266, "grad_norm": 0.0012812681961804628, "learning_rate": 4.53334071945799e-05, "loss": 6.183907389640808e-05, "step": 19175 }, { "epoch": 2.491241728298949, "grad_norm": 0.001245909254066646, "learning_rate": 4.531499561449022e-05, "loss": 6.445104256272316e-05, "step": 19200 }, { "epoch": 2.4944855326326714, "grad_norm": 0.001403098227456212, "learning_rate": 4.529655153964775e-05, "loss": 6.702614016830922e-05, "step": 19225 }, { "epoch": 2.497729336966394, "grad_norm": 0.0007750423392280936, "learning_rate": 4.52780749995546e-05, "loss": 6.096431519836187e-05, "step": 19250 }, { "epoch": 2.5009731413001166, "grad_norm": 0.0008184191538020968, "learning_rate": 4.525956602376486e-05, "loss": 4.9065290950238706e-05, "step": 19275 }, { "epoch": 2.5042169456338392, "grad_norm": 0.000569896656088531, "learning_rate": 4.5241024641884456e-05, "loss": 6.08682818710804e-05, "step": 19300 }, { "epoch": 2.507460749967562, "grad_norm": 0.0007476020255126059, "learning_rate": 4.522245088357116e-05, "loss": 5.926272831857205e-05, "step": 19325 }, { "epoch": 2.5107045543012845, "grad_norm": 0.0020040806848555803, "learning_rate": 4.5203844778534554e-05, "loss": 6.065156776458025e-05, "step": 19350 }, { "epoch": 2.513948358635007, "grad_norm": 0.00035510759335011244, "learning_rate": 4.518520635653594e-05, "loss": 5.46090304851532e-05, "step": 19375 }, { "epoch": 2.5171921629687297, "grad_norm": 0.0007557239150628448, "learning_rate": 4.5166535647388296e-05, "loss": 4.524030722677708e-05, "step": 19400 }, { "epoch": 2.5204359673024523, "grad_norm": 0.0014556809328496456, "learning_rate": 4.5147832680956284e-05, "loss": 5.303089041262865e-05, "step": 19425 }, { "epoch": 2.523679771636175, "grad_norm": 0.0019299911800771952, "learning_rate": 4.512909748715613e-05, "loss": 5.232525523751974e-05, "step": 19450 }, { "epoch": 2.5269235759698976, "grad_norm": 0.0009495535050518811, "learning_rate": 4.511033009595564e-05, "loss": 5.374740343540907e-05, "step": 19475 }, { "epoch": 2.53016738030362, "grad_norm": 0.000398665782995522, "learning_rate": 4.50915305373741e-05, "loss": 4.968229681253433e-05, "step": 19500 }, { "epoch": 2.533411184637343, "grad_norm": 0.002159884897992015, "learning_rate": 4.507269884148224e-05, "loss": 5.776622798293829e-05, "step": 19525 }, { "epoch": 2.5366549889710654, "grad_norm": 0.0013120253570377827, "learning_rate": 4.505383503840221e-05, "loss": 6.393718533217907e-05, "step": 19550 }, { "epoch": 2.539898793304788, "grad_norm": 0.001998805208131671, "learning_rate": 4.503493915830753e-05, "loss": 6.56480062752962e-05, "step": 19575 }, { "epoch": 2.5431425976385107, "grad_norm": 0.0006372964708134532, "learning_rate": 4.5016011231422995e-05, "loss": 5.5217109620571135e-05, "step": 19600 }, { "epoch": 2.546386401972233, "grad_norm": 0.000993330031633377, "learning_rate": 4.4997051288024686e-05, "loss": 5.533466581255197e-05, "step": 19625 }, { "epoch": 2.5496302063059555, "grad_norm": 0.0016404540510848165, "learning_rate": 4.497805935843989e-05, "loss": 6.038051098585129e-05, "step": 19650 }, { "epoch": 2.552874010639678, "grad_norm": 0.001109354430809617, "learning_rate": 4.4959035473047054e-05, "loss": 5.629546474665403e-05, "step": 19675 }, { "epoch": 2.5561178149734007, "grad_norm": 0.001074078376404941, "learning_rate": 4.4939979662275745e-05, "loss": 5.534065887331963e-05, "step": 19700 }, { "epoch": 2.5593616193071234, "grad_norm": 0.0012507392093539238, "learning_rate": 4.4920891956606594e-05, "loss": 5.2110771648585796e-05, "step": 19725 }, { "epoch": 2.562605423640846, "grad_norm": 0.0012239833595231175, "learning_rate": 4.490177238657124e-05, "loss": 5.697227083146572e-05, "step": 19750 }, { "epoch": 2.5658492279745686, "grad_norm": 0.000830311153549701, "learning_rate": 4.48826209827523e-05, "loss": 4.585276357829571e-05, "step": 19775 }, { "epoch": 2.5690930323082912, "grad_norm": 0.0012085463386029005, "learning_rate": 4.4863437775783323e-05, "loss": 5.4011684842407706e-05, "step": 19800 }, { "epoch": 2.572336836642014, "grad_norm": 0.0020938822999596596, "learning_rate": 4.48442227963487e-05, "loss": 5.383182782679796e-05, "step": 19825 }, { "epoch": 2.5755806409757365, "grad_norm": 0.0008378715720027685, "learning_rate": 4.4824976075183654e-05, "loss": 5.141466856002808e-05, "step": 19850 }, { "epoch": 2.578824445309459, "grad_norm": 0.0015031305374577641, "learning_rate": 4.4805697643074206e-05, "loss": 5.038064904510975e-05, "step": 19875 }, { "epoch": 2.5820682496431813, "grad_norm": 0.0007376973517239094, "learning_rate": 4.4786387530857056e-05, "loss": 5.6049483828246596e-05, "step": 19900 }, { "epoch": 2.585312053976904, "grad_norm": 0.0011927729938179255, "learning_rate": 4.476704576941961e-05, "loss": 5.2509685046970845e-05, "step": 19925 }, { "epoch": 2.5885558583106265, "grad_norm": 0.0011331229470670223, "learning_rate": 4.47476723896999e-05, "loss": 5.485334899276495e-05, "step": 19950 }, { "epoch": 2.591799662644349, "grad_norm": 0.0005742421490140259, "learning_rate": 4.4728267422686496e-05, "loss": 5.463377572596073e-05, "step": 19975 }, { "epoch": 2.5950434669780718, "grad_norm": 0.0009788335300981998, "learning_rate": 4.4708830899418544e-05, "loss": 4.941990599036217e-05, "step": 20000 }, { "epoch": 2.5982872713117944, "grad_norm": 0.0016961732180789113, "learning_rate": 4.4689362850985625e-05, "loss": 5.894227884709835e-05, "step": 20025 }, { "epoch": 2.601531075645517, "grad_norm": 0.0019096795003861189, "learning_rate": 4.466986330852777e-05, "loss": 5.323691759258509e-05, "step": 20050 }, { "epoch": 2.6047748799792396, "grad_norm": 0.0013482776703312993, "learning_rate": 4.465033230323538e-05, "loss": 5.077918991446495e-05, "step": 20075 }, { "epoch": 2.6080186843129622, "grad_norm": 0.002127456245943904, "learning_rate": 4.463076986634916e-05, "loss": 5.419087130576372e-05, "step": 20100 }, { "epoch": 2.611262488646685, "grad_norm": 0.001370071666315198, "learning_rate": 4.461117602916014e-05, "loss": 5.953768268227577e-05, "step": 20125 }, { "epoch": 2.6145062929804075, "grad_norm": 0.0017292867414653301, "learning_rate": 4.459155082300952e-05, "loss": 6.516265217214823e-05, "step": 20150 }, { "epoch": 2.61775009731413, "grad_norm": 0.0010634456994011998, "learning_rate": 4.457189427928872e-05, "loss": 6.403960287570953e-05, "step": 20175 }, { "epoch": 2.6209939016478527, "grad_norm": 0.0013361264718696475, "learning_rate": 4.455220642943927e-05, "loss": 5.736483260989189e-05, "step": 20200 }, { "epoch": 2.6242377059815754, "grad_norm": 0.0008942830027081072, "learning_rate": 4.4532487304952764e-05, "loss": 4.6785427257418634e-05, "step": 20225 }, { "epoch": 2.627481510315298, "grad_norm": 0.0020622427109628916, "learning_rate": 4.4512736937370844e-05, "loss": 5.310042761266232e-05, "step": 20250 }, { "epoch": 2.6307253146490206, "grad_norm": 0.001173284137621522, "learning_rate": 4.4492955358285104e-05, "loss": 6.1020483262836936e-05, "step": 20275 }, { "epoch": 2.633969118982743, "grad_norm": 0.0011594835668802261, "learning_rate": 4.447314259933708e-05, "loss": 6.0584614984691144e-05, "step": 20300 }, { "epoch": 2.6372129233164654, "grad_norm": 0.002829106291756034, "learning_rate": 4.445329869221817e-05, "loss": 5.844712723046541e-05, "step": 20325 }, { "epoch": 2.640456727650188, "grad_norm": 0.0007342799799516797, "learning_rate": 4.4433423668669604e-05, "loss": 5.1371557638049126e-05, "step": 20350 }, { "epoch": 2.6437005319839106, "grad_norm": 0.007264559157192707, "learning_rate": 4.4413517560482376e-05, "loss": 5.2819596603512765e-05, "step": 20375 }, { "epoch": 2.6469443363176333, "grad_norm": 0.0005045419675298035, "learning_rate": 4.4393580399497214e-05, "loss": 4.872250836342573e-05, "step": 20400 }, { "epoch": 2.650188140651356, "grad_norm": 0.0011980625567957759, "learning_rate": 4.4373612217604496e-05, "loss": 4.7193784266710284e-05, "step": 20425 }, { "epoch": 2.6534319449850785, "grad_norm": 0.0013326279586181045, "learning_rate": 4.435361304674423e-05, "loss": 4.961750004440546e-05, "step": 20450 }, { "epoch": 2.656675749318801, "grad_norm": 0.0007897471659816802, "learning_rate": 4.4333582918906e-05, "loss": 5.1872157491743565e-05, "step": 20475 }, { "epoch": 2.6599195536525237, "grad_norm": 0.0005701633635908365, "learning_rate": 4.431352186612889e-05, "loss": 5.360012408345938e-05, "step": 20500 }, { "epoch": 2.6631633579862464, "grad_norm": 0.0005467779701575637, "learning_rate": 4.429342992050148e-05, "loss": 5.068980623036623e-05, "step": 20525 }, { "epoch": 2.666407162319969, "grad_norm": 0.0017254377016797662, "learning_rate": 4.427330711416172e-05, "loss": 4.5905155129730705e-05, "step": 20550 }, { "epoch": 2.6696509666536916, "grad_norm": 0.00041812562267296016, "learning_rate": 4.4253153479296964e-05, "loss": 4.887691233307123e-05, "step": 20575 }, { "epoch": 2.672894770987414, "grad_norm": 0.001148405484855175, "learning_rate": 4.423296904814386e-05, "loss": 5.4057524539530275e-05, "step": 20600 }, { "epoch": 2.6761385753211364, "grad_norm": 0.0006488741491921246, "learning_rate": 4.4212753852988296e-05, "loss": 5.5467113852500916e-05, "step": 20625 }, { "epoch": 2.679382379654859, "grad_norm": 0.00831567496061325, "learning_rate": 4.419250792616542e-05, "loss": 5.312738474458456e-05, "step": 20650 }, { "epoch": 2.6826261839885817, "grad_norm": 0.0021836748346686363, "learning_rate": 4.4172231300059485e-05, "loss": 5.738171748816967e-05, "step": 20675 }, { "epoch": 2.6858699883223043, "grad_norm": 0.0008395619224756956, "learning_rate": 4.415192400710388e-05, "loss": 5.409103352576494e-05, "step": 20700 }, { "epoch": 2.6858699883223043, "eval_loss": 0.0002143534948118031, "eval_runtime": 6.5403, "eval_samples_per_second": 764.486, "eval_steps_per_second": 6.116, "step": 20700 }, { "epoch": 2.6858699883223043, "eval_holdout_avg_strict_f1": 0.23122447545465796, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7816901408450704, "eval_holdout_nemotron_pii_strict_f1": 0.684904214559387, "eval_holdout_open_pii_masking_500k_strict_f1": 0.553623188405797, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.5232516861909833, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 20700 }, { "epoch": 2.689113792656027, "grad_norm": 0.0012287527788430452, "learning_rate": 4.413158607978104e-05, "loss": 5.3219501860439775e-05, "step": 20725 }, { "epoch": 2.6923575969897495, "grad_norm": 0.0012113215634599328, "learning_rate": 4.4111217550622385e-05, "loss": 6.008664146065712e-05, "step": 20750 }, { "epoch": 2.695601401323472, "grad_norm": 0.0010658798273652792, "learning_rate": 4.409081845220831e-05, "loss": 5.4371245205402375e-05, "step": 20775 }, { "epoch": 2.6988452056571948, "grad_norm": 0.0016598160145804286, "learning_rate": 4.407038881716808e-05, "loss": 5.153648089617491e-05, "step": 20800 }, { "epoch": 2.7020890099909174, "grad_norm": 0.0016598233487457037, "learning_rate": 4.404992867817983e-05, "loss": 5.094144493341446e-05, "step": 20825 }, { "epoch": 2.70533281432464, "grad_norm": 0.000884748063981533, "learning_rate": 4.402943806797048e-05, "loss": 5.7097021490335464e-05, "step": 20850 }, { "epoch": 2.7085766186583626, "grad_norm": 0.0010101109510287642, "learning_rate": 4.4008917019315676e-05, "loss": 5.28867170214653e-05, "step": 20875 }, { "epoch": 2.7118204229920853, "grad_norm": 0.0028984183445572853, "learning_rate": 4.398836556503976e-05, "loss": 5.16117038205266e-05, "step": 20900 }, { "epoch": 2.715064227325808, "grad_norm": 0.0025796068366616964, "learning_rate": 4.3967783738015724e-05, "loss": 6.322179455310106e-05, "step": 20925 }, { "epoch": 2.7183080316595305, "grad_norm": 0.0015145255019888282, "learning_rate": 4.394717157116512e-05, "loss": 6.351370830088854e-05, "step": 20950 }, { "epoch": 2.721551835993253, "grad_norm": 0.0009088438819162548, "learning_rate": 4.392652909745804e-05, "loss": 5.0907521508634094e-05, "step": 20975 }, { "epoch": 2.7247956403269757, "grad_norm": 0.001716925879009068, "learning_rate": 4.390585634991305e-05, "loss": 5.925416946411133e-05, "step": 21000 }, { "epoch": 2.728039444660698, "grad_norm": 0.0008526298333890736, "learning_rate": 4.388515336159716e-05, "loss": 5.0829751417040824e-05, "step": 21025 }, { "epoch": 2.7312832489944205, "grad_norm": 0.0007600942626595497, "learning_rate": 4.386442016562572e-05, "loss": 5.671436432749033e-05, "step": 21050 }, { "epoch": 2.734527053328143, "grad_norm": 0.0007586602005176246, "learning_rate": 4.38436567951624e-05, "loss": 6.078100297600031e-05, "step": 21075 }, { "epoch": 2.737770857661866, "grad_norm": 0.001476939651183784, "learning_rate": 4.382286328341918e-05, "loss": 4.793212283402681e-05, "step": 21100 }, { "epoch": 2.7410146619955884, "grad_norm": 0.0017539989203214645, "learning_rate": 4.38020396636562e-05, "loss": 5.2300486713647843e-05, "step": 21125 }, { "epoch": 2.744258466329311, "grad_norm": 0.000842199893668294, "learning_rate": 4.378118596918179e-05, "loss": 4.9244677647948265e-05, "step": 21150 }, { "epoch": 2.7475022706630337, "grad_norm": 0.0011546657187864184, "learning_rate": 4.376030223335237e-05, "loss": 5.392031744122505e-05, "step": 21175 }, { "epoch": 2.7507460749967563, "grad_norm": 0.0009593299473635852, "learning_rate": 4.3739388489572416e-05, "loss": 5.211362149566412e-05, "step": 21200 }, { "epoch": 2.753989879330479, "grad_norm": 0.0009008182678371668, "learning_rate": 4.371844477129441e-05, "loss": 5.315751302987337e-05, "step": 21225 }, { "epoch": 2.7572336836642015, "grad_norm": 0.001105339964851737, "learning_rate": 4.369747111201877e-05, "loss": 4.705106373876333e-05, "step": 21250 }, { "epoch": 2.7604774879979237, "grad_norm": 0.000623121508397162, "learning_rate": 4.367646754529383e-05, "loss": 5.378408823162317e-05, "step": 21275 }, { "epoch": 2.7637212923316463, "grad_norm": 0.0004830897960346192, "learning_rate": 4.365543410471571e-05, "loss": 5.0109000876545904e-05, "step": 21300 }, { "epoch": 2.766965096665369, "grad_norm": 0.0012933810940012336, "learning_rate": 4.363437082392838e-05, "loss": 5.317446775734425e-05, "step": 21325 }, { "epoch": 2.7702089009990916, "grad_norm": 0.0008854776970110834, "learning_rate": 4.361327773662349e-05, "loss": 4.7490224242210386e-05, "step": 21350 }, { "epoch": 2.773452705332814, "grad_norm": 0.0021710514556616545, "learning_rate": 4.359215487654039e-05, "loss": 5.162980407476425e-05, "step": 21375 }, { "epoch": 2.776696509666537, "grad_norm": 0.0011909108143299818, "learning_rate": 4.357100227746606e-05, "loss": 6.326674018055201e-05, "step": 21400 }, { "epoch": 2.7799403140002594, "grad_norm": 0.000816775020211935, "learning_rate": 4.354981997323501e-05, "loss": 5.598699674010277e-05, "step": 21425 }, { "epoch": 2.783184118333982, "grad_norm": 0.0016986014088615775, "learning_rate": 4.352860799772931e-05, "loss": 5.308338906615973e-05, "step": 21450 }, { "epoch": 2.7864279226677047, "grad_norm": 0.00072915741475299, "learning_rate": 4.3507366384878486e-05, "loss": 5.363121163100004e-05, "step": 21475 }, { "epoch": 2.7896717270014273, "grad_norm": 0.002178191440179944, "learning_rate": 4.3486095168659435e-05, "loss": 5.35898469388485e-05, "step": 21500 }, { "epoch": 2.79291553133515, "grad_norm": 0.0008095112279988825, "learning_rate": 4.346479438309643e-05, "loss": 4.6959342435002326e-05, "step": 21525 }, { "epoch": 2.7961593356688725, "grad_norm": 0.0036779718939214945, "learning_rate": 4.3443464062261055e-05, "loss": 6.976427510380746e-05, "step": 21550 }, { "epoch": 2.799403140002595, "grad_norm": 0.0012386500602588058, "learning_rate": 4.34221042402721e-05, "loss": 6.309887859970331e-05, "step": 21575 }, { "epoch": 2.802646944336318, "grad_norm": 0.001421452034264803, "learning_rate": 4.3400714951295586e-05, "loss": 5.671134684234858e-05, "step": 21600 }, { "epoch": 2.8058907486700404, "grad_norm": 0.00091330282157287, "learning_rate": 4.337929622954463e-05, "loss": 5.1584867760539056e-05, "step": 21625 }, { "epoch": 2.809134553003763, "grad_norm": 0.001270504668354988, "learning_rate": 4.335784810927945e-05, "loss": 6.034310441464186e-05, "step": 21650 }, { "epoch": 2.8123783573374856, "grad_norm": 0.0010795651469379663, "learning_rate": 4.3336370624807286e-05, "loss": 4.6530235558748244e-05, "step": 21675 }, { "epoch": 2.8156221616712083, "grad_norm": 0.0015777138760313392, "learning_rate": 4.3314863810482344e-05, "loss": 5.958176217973232e-05, "step": 21700 }, { "epoch": 2.8188659660049304, "grad_norm": 0.0012359591200947762, "learning_rate": 4.3293327700705744e-05, "loss": 5.8761099353432655e-05, "step": 21725 }, { "epoch": 2.822109770338653, "grad_norm": 0.0008567681070417166, "learning_rate": 4.3271762329925456e-05, "loss": 5.2143814973533156e-05, "step": 21750 }, { "epoch": 2.8253535746723757, "grad_norm": 0.0008462846162728965, "learning_rate": 4.325016773263628e-05, "loss": 4.9622287042438985e-05, "step": 21775 }, { "epoch": 2.8285973790060983, "grad_norm": 0.000488682824652642, "learning_rate": 4.322854394337974e-05, "loss": 5.202279426157475e-05, "step": 21800 }, { "epoch": 2.831841183339821, "grad_norm": 0.0008545344462618232, "learning_rate": 4.320689099674406e-05, "loss": 4.688541870564222e-05, "step": 21825 }, { "epoch": 2.8350849876735436, "grad_norm": 0.0010484014637768269, "learning_rate": 4.318520892736412e-05, "loss": 4.676192533224821e-05, "step": 21850 }, { "epoch": 2.838328792007266, "grad_norm": 0.0013194689527153969, "learning_rate": 4.316349776992136e-05, "loss": 5.0970339216291905e-05, "step": 21875 }, { "epoch": 2.841572596340989, "grad_norm": 0.0008247167570516467, "learning_rate": 4.314175755914375e-05, "loss": 5.758105311542749e-05, "step": 21900 }, { "epoch": 2.8448164006747114, "grad_norm": 0.0009647550759837031, "learning_rate": 4.311998832980576e-05, "loss": 5.274449475109577e-05, "step": 21925 }, { "epoch": 2.848060205008434, "grad_norm": 0.001830253517255187, "learning_rate": 4.309819011672823e-05, "loss": 6.614188198000192e-05, "step": 21950 }, { "epoch": 2.851304009342156, "grad_norm": 0.0020867481362074614, "learning_rate": 4.3076362954778393e-05, "loss": 5.6825424544513225e-05, "step": 21975 }, { "epoch": 2.854547813675879, "grad_norm": 0.0010637515224516392, "learning_rate": 4.3054506878869794e-05, "loss": 5.330375395715237e-05, "step": 22000 }, { "epoch": 2.8577916180096015, "grad_norm": 0.002279468812048435, "learning_rate": 4.3032621923962203e-05, "loss": 5.919148214161396e-05, "step": 22025 }, { "epoch": 2.861035422343324, "grad_norm": 0.00081172602949664, "learning_rate": 4.3010708125061596e-05, "loss": 5.5839745327830316e-05, "step": 22050 }, { "epoch": 2.8642792266770467, "grad_norm": 0.0009272390743717551, "learning_rate": 4.298876551722008e-05, "loss": 5.0461553037166596e-05, "step": 22075 }, { "epoch": 2.8675230310107693, "grad_norm": 0.0010071253636851907, "learning_rate": 4.296679413553584e-05, "loss": 4.974015988409519e-05, "step": 22100 }, { "epoch": 2.870766835344492, "grad_norm": 0.0013954933965578675, "learning_rate": 4.2944794015153114e-05, "loss": 4.817927721887827e-05, "step": 22125 }, { "epoch": 2.8740106396782146, "grad_norm": 0.001503468956798315, "learning_rate": 4.292276519126207e-05, "loss": 4.9963132478296754e-05, "step": 22150 }, { "epoch": 2.877254444011937, "grad_norm": 0.0006520295282825828, "learning_rate": 4.290070769909882e-05, "loss": 4.977383185178042e-05, "step": 22175 }, { "epoch": 2.88049824834566, "grad_norm": 0.0007242034189403057, "learning_rate": 4.287862157394531e-05, "loss": 5.053251981735229e-05, "step": 22200 }, { "epoch": 2.8837420526793824, "grad_norm": 0.0006574604194611311, "learning_rate": 4.285650685112929e-05, "loss": 5.233993288129568e-05, "step": 22225 }, { "epoch": 2.886985857013105, "grad_norm": 0.0016811463283374906, "learning_rate": 4.283436356602426e-05, "loss": 7.112233433872461e-05, "step": 22250 }, { "epoch": 2.8902296613468277, "grad_norm": 0.0024714807514101267, "learning_rate": 4.2812191754049416e-05, "loss": 5.798354744911194e-05, "step": 22275 }, { "epoch": 2.8934734656805503, "grad_norm": 0.00099657173268497, "learning_rate": 4.278999145066956e-05, "loss": 5.39609557017684e-05, "step": 22300 }, { "epoch": 2.896717270014273, "grad_norm": 0.0007382440380752087, "learning_rate": 4.27677626913951e-05, "loss": 5.3393514826893805e-05, "step": 22325 }, { "epoch": 2.8999610743479955, "grad_norm": 0.00033008208265528083, "learning_rate": 4.274550551178191e-05, "loss": 4.7118659131228925e-05, "step": 22350 }, { "epoch": 2.903204878681718, "grad_norm": 0.0007131941965781152, "learning_rate": 4.272321994743137e-05, "loss": 5.073138978332281e-05, "step": 22375 }, { "epoch": 2.9064486830154403, "grad_norm": 0.0004770196392200887, "learning_rate": 4.2700906033990246e-05, "loss": 4.705374129116535e-05, "step": 22400 }, { "epoch": 2.909692487349163, "grad_norm": 0.0008687296067364514, "learning_rate": 4.267856380715065e-05, "loss": 4.436025395989418e-05, "step": 22425 }, { "epoch": 2.9129362916828856, "grad_norm": 0.0008773301960900426, "learning_rate": 4.2656193302649975e-05, "loss": 5.2733183838427064e-05, "step": 22450 }, { "epoch": 2.916180096016608, "grad_norm": 0.000984707847237587, "learning_rate": 4.2633794556270865e-05, "loss": 4.927228670567274e-05, "step": 22475 }, { "epoch": 2.919423900350331, "grad_norm": 0.0004780844901688397, "learning_rate": 4.261136760384112e-05, "loss": 4.69692749902606e-05, "step": 22500 }, { "epoch": 2.9226677046840535, "grad_norm": 0.0013504858361557126, "learning_rate": 4.2588912481233666e-05, "loss": 4.595948848873377e-05, "step": 22525 }, { "epoch": 2.925911509017776, "grad_norm": 0.0011311427224427462, "learning_rate": 4.256642922436648e-05, "loss": 5.157114937901497e-05, "step": 22550 }, { "epoch": 2.9291553133514987, "grad_norm": 0.0005859927623532712, "learning_rate": 4.2543917869202555e-05, "loss": 4.606516100466251e-05, "step": 22575 }, { "epoch": 2.9323991176852213, "grad_norm": 0.0004089867870789021, "learning_rate": 4.2521378451749805e-05, "loss": 4.387479275465011e-05, "step": 22600 }, { "epoch": 2.935642922018944, "grad_norm": 0.0004268248740117997, "learning_rate": 4.249881100806107e-05, "loss": 5.499421153217554e-05, "step": 22625 }, { "epoch": 2.9388867263526666, "grad_norm": 0.0009614244336262345, "learning_rate": 4.247621557423397e-05, "loss": 4.743567202240229e-05, "step": 22650 }, { "epoch": 2.9421305306863887, "grad_norm": 0.0008211962995119393, "learning_rate": 4.245359218641094e-05, "loss": 4.741067998111248e-05, "step": 22675 }, { "epoch": 2.9453743350201114, "grad_norm": 0.000726397498510778, "learning_rate": 4.2430940880779096e-05, "loss": 4.204121883958578e-05, "step": 22700 }, { "epoch": 2.948618139353834, "grad_norm": 0.0007934595923870802, "learning_rate": 4.240826169357024e-05, "loss": 5.328967701643706e-05, "step": 22725 }, { "epoch": 2.9518619436875566, "grad_norm": 0.0006481872405856848, "learning_rate": 4.238555466106074e-05, "loss": 4.360498860478401e-05, "step": 22750 }, { "epoch": 2.9551057480212792, "grad_norm": 0.000570033211261034, "learning_rate": 4.236281981957153e-05, "loss": 5.559736397117376e-05, "step": 22775 }, { "epoch": 2.958349552355002, "grad_norm": 0.0007283762097358704, "learning_rate": 4.234005720546801e-05, "loss": 5.535357166081667e-05, "step": 22800 }, { "epoch": 2.9615933566887245, "grad_norm": 0.0018429633928462863, "learning_rate": 4.231726685516002e-05, "loss": 7.30211939662695e-05, "step": 22825 }, { "epoch": 2.964837161022447, "grad_norm": 0.003399588167667389, "learning_rate": 4.229444880510174e-05, "loss": 6.436004769057035e-05, "step": 22850 }, { "epoch": 2.9680809653561697, "grad_norm": 0.0014293997082859278, "learning_rate": 4.227160309179168e-05, "loss": 6.246185395866632e-05, "step": 22875 }, { "epoch": 2.9713247696898923, "grad_norm": 0.0005023105768486857, "learning_rate": 4.2248729751772586e-05, "loss": 5.089652724564076e-05, "step": 22900 }, { "epoch": 2.974568574023615, "grad_norm": 0.0025808720383793116, "learning_rate": 4.22258288216314e-05, "loss": 5.433966405689716e-05, "step": 22925 }, { "epoch": 2.9778123783573376, "grad_norm": 0.0011027734726667404, "learning_rate": 4.2202900337999196e-05, "loss": 4.706557374447584e-05, "step": 22950 }, { "epoch": 2.98105618269106, "grad_norm": 0.0010811365209519863, "learning_rate": 4.217994433755111e-05, "loss": 5.178213585168123e-05, "step": 22975 }, { "epoch": 2.984299987024783, "grad_norm": 0.0014398471685126424, "learning_rate": 4.215696085700632e-05, "loss": 5.416898988187313e-05, "step": 23000 }, { "epoch": 2.9875437913585055, "grad_norm": 0.001313576241955161, "learning_rate": 4.213394993312792e-05, "loss": 5.0782710313796994e-05, "step": 23025 }, { "epoch": 2.990787595692228, "grad_norm": 0.0010119734797626734, "learning_rate": 4.2110911602722937e-05, "loss": 4.925228655338287e-05, "step": 23050 }, { "epoch": 2.9940314000259507, "grad_norm": 0.005673216190189123, "learning_rate": 4.208784590264221e-05, "loss": 4.786040168255567e-05, "step": 23075 }, { "epoch": 2.997275204359673, "grad_norm": 0.0018561886390671134, "learning_rate": 4.206475286978037e-05, "loss": 4.9104061909019946e-05, "step": 23100 }, { "epoch": 3.0005190086933955, "grad_norm": 0.0007219471735879779, "learning_rate": 4.204163254107577e-05, "loss": 4.9142478965222835e-05, "step": 23125 }, { "epoch": 3.003762813027118, "grad_norm": 0.0007355411653406918, "learning_rate": 4.201848495351042e-05, "loss": 4.990674555301666e-05, "step": 23150 }, { "epoch": 3.0070066173608407, "grad_norm": 0.0015934540424495935, "learning_rate": 4.1995310144109925e-05, "loss": 4.456935450434685e-05, "step": 23175 }, { "epoch": 3.0102504216945634, "grad_norm": 0.0004891761345788836, "learning_rate": 4.1972108149943445e-05, "loss": 5.340852774679661e-05, "step": 23200 }, { "epoch": 3.013494226028286, "grad_norm": 0.0012910655932500958, "learning_rate": 4.194887900812361e-05, "loss": 5.453863181173802e-05, "step": 23225 }, { "epoch": 3.0167380303620086, "grad_norm": 0.001096490421332419, "learning_rate": 4.19256227558065e-05, "loss": 4.994523711502552e-05, "step": 23250 }, { "epoch": 3.0199818346957312, "grad_norm": 0.0003527960507199168, "learning_rate": 4.190233943019152e-05, "loss": 4.942517261952162e-05, "step": 23275 }, { "epoch": 3.023225639029454, "grad_norm": 0.001336101908236742, "learning_rate": 4.187902906852141e-05, "loss": 5.277242511510849e-05, "step": 23300 }, { "epoch": 3.0264694433631765, "grad_norm": 0.0014060212997719646, "learning_rate": 4.185569170808215e-05, "loss": 4.9168048426508904e-05, "step": 23325 }, { "epoch": 3.029713247696899, "grad_norm": 0.0012066664639860392, "learning_rate": 4.1832327386202887e-05, "loss": 5.2311322651803496e-05, "step": 23350 }, { "epoch": 3.0329570520306217, "grad_norm": 0.0006254046456888318, "learning_rate": 4.1808936140255914e-05, "loss": 4.328955430537462e-05, "step": 23375 }, { "epoch": 3.036200856364344, "grad_norm": 0.0016662274720147252, "learning_rate": 4.17855180076566e-05, "loss": 4.760800860822201e-05, "step": 23400 }, { "epoch": 3.0394446606980665, "grad_norm": 0.0018067931523546576, "learning_rate": 4.176207302586329e-05, "loss": 5.8378507383167743e-05, "step": 23425 }, { "epoch": 3.042688465031789, "grad_norm": 0.0008956273668445647, "learning_rate": 4.173860123237729e-05, "loss": 5.692997016012668e-05, "step": 23450 }, { "epoch": 3.0459322693655118, "grad_norm": 0.0016926497919484973, "learning_rate": 4.171510266474281e-05, "loss": 5.297433119267225e-05, "step": 23475 }, { "epoch": 3.0491760736992344, "grad_norm": 0.00043769917101599276, "learning_rate": 4.1691577360546855e-05, "loss": 5.016302689909935e-05, "step": 23500 }, { "epoch": 3.052419878032957, "grad_norm": 0.0006089042290113866, "learning_rate": 4.1668025357419216e-05, "loss": 5.095783155411482e-05, "step": 23525 }, { "epoch": 3.0556636823666796, "grad_norm": 0.0015206679236143827, "learning_rate": 4.164444669303238e-05, "loss": 5.610996391624212e-05, "step": 23550 }, { "epoch": 3.0589074867004022, "grad_norm": 0.0011334880255162716, "learning_rate": 4.1620841405101495e-05, "loss": 5.005734041333199e-05, "step": 23575 }, { "epoch": 3.062151291034125, "grad_norm": 0.0009928274666890502, "learning_rate": 4.159720953138428e-05, "loss": 4.9824113957583905e-05, "step": 23600 }, { "epoch": 3.0653950953678475, "grad_norm": 0.001963290385901928, "learning_rate": 4.1573551109680986e-05, "loss": 5.1925103180110453e-05, "step": 23625 }, { "epoch": 3.06863889970157, "grad_norm": 0.0010959861101582646, "learning_rate": 4.154986617783433e-05, "loss": 5.488554947078228e-05, "step": 23650 }, { "epoch": 3.0718827040352927, "grad_norm": 0.0027747454587370157, "learning_rate": 4.152615477372941e-05, "loss": 5.018348339945078e-05, "step": 23675 }, { "epoch": 3.0751265083690154, "grad_norm": 0.0005823189858347178, "learning_rate": 4.1502416935293714e-05, "loss": 5.588240455836058e-05, "step": 23700 }, { "epoch": 3.078370312702738, "grad_norm": 0.0013753221137449145, "learning_rate": 4.147865270049698e-05, "loss": 5.2641192451119426e-05, "step": 23725 }, { "epoch": 3.08161411703646, "grad_norm": 0.000830132223200053, "learning_rate": 4.145486210735116e-05, "loss": 5.25648333132267e-05, "step": 23750 }, { "epoch": 3.0848579213701828, "grad_norm": 0.000760136463213712, "learning_rate": 4.143104519391039e-05, "loss": 4.2935977689921855e-05, "step": 23775 }, { "epoch": 3.0881017257039054, "grad_norm": 0.0009902231395244598, "learning_rate": 4.1407201998270905e-05, "loss": 5.089842714369297e-05, "step": 23800 }, { "epoch": 3.091345530037628, "grad_norm": 0.0003968613164033741, "learning_rate": 4.1383332558570966e-05, "loss": 3.752300748601556e-05, "step": 23825 }, { "epoch": 3.0945893343713506, "grad_norm": 0.004347462207078934, "learning_rate": 4.135943691299082e-05, "loss": 4.584980197250843e-05, "step": 23850 }, { "epoch": 3.0978331387050733, "grad_norm": 0.002084464766085148, "learning_rate": 4.133551509975264e-05, "loss": 5.020149052143097e-05, "step": 23875 }, { "epoch": 3.101076943038796, "grad_norm": 0.0003928530786652118, "learning_rate": 4.131156715712043e-05, "loss": 4.853044636547565e-05, "step": 23900 }, { "epoch": 3.1043207473725185, "grad_norm": 0.0008350599673576653, "learning_rate": 4.1287593123400024e-05, "loss": 4.786413628607988e-05, "step": 23925 }, { "epoch": 3.107564551706241, "grad_norm": 0.0003723597910720855, "learning_rate": 4.126359303693896e-05, "loss": 4.583088215440512e-05, "step": 23950 }, { "epoch": 3.1108083560399638, "grad_norm": 0.0012002879520878196, "learning_rate": 4.123956693612646e-05, "loss": 4.74942522123456e-05, "step": 23975 }, { "epoch": 3.1140521603736864, "grad_norm": 0.0006565111107192934, "learning_rate": 4.1215514859393364e-05, "loss": 4.615248180925846e-05, "step": 24000 }, { "epoch": 3.117295964707409, "grad_norm": 0.0010946964612230659, "learning_rate": 4.119143684521204e-05, "loss": 4.612576682120562e-05, "step": 24025 }, { "epoch": 3.1205397690411316, "grad_norm": 0.0011213753605261445, "learning_rate": 4.116733293209638e-05, "loss": 4.366521723568439e-05, "step": 24050 }, { "epoch": 3.1237835733748542, "grad_norm": 0.000841779459733516, "learning_rate": 4.1143203158601665e-05, "loss": 5.0774835981428625e-05, "step": 24075 }, { "epoch": 3.1270273777085764, "grad_norm": 0.00114744424354285, "learning_rate": 4.1119047563324566e-05, "loss": 4.8233699053525925e-05, "step": 24100 }, { "epoch": 3.130271182042299, "grad_norm": 0.0007853684364818037, "learning_rate": 4.109486618490305e-05, "loss": 4.8530851490795615e-05, "step": 24125 }, { "epoch": 3.1335149863760217, "grad_norm": 0.0008175890543498099, "learning_rate": 4.107065906201631e-05, "loss": 5.337031092494726e-05, "step": 24150 }, { "epoch": 3.1335149863760217, "eval_loss": 0.00021797235240228474, "eval_runtime": 7.2581, "eval_samples_per_second": 688.885, "eval_steps_per_second": 5.511, "step": 24150 }, { "epoch": 3.1335149863760217, "eval_holdout_avg_strict_f1": 0.23728175731135123, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.8110839445802771, "eval_holdout_nemotron_pii_strict_f1": 0.6026011560693642, "eval_holdout_open_pii_masking_500k_strict_f1": 0.6172578083642138, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.5791564214110081, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 24150 }, { "epoch": 3.1367587907097443, "grad_norm": 0.0011049035238102078, "learning_rate": 4.104642623338474e-05, "loss": 5.071741994470358e-05, "step": 24175 }, { "epoch": 3.140002595043467, "grad_norm": 0.0008526498568244278, "learning_rate": 4.1022167737769856e-05, "loss": 4.117593169212341e-05, "step": 24200 }, { "epoch": 3.1432463993771895, "grad_norm": 0.0007872623391449451, "learning_rate": 4.09978836139742e-05, "loss": 4.746176302433014e-05, "step": 24225 }, { "epoch": 3.146490203710912, "grad_norm": 0.001649911398999393, "learning_rate": 4.097357390084133e-05, "loss": 5.0397315062582494e-05, "step": 24250 }, { "epoch": 3.1497340080446348, "grad_norm": 0.0007325213518925011, "learning_rate": 4.0949238637255726e-05, "loss": 4.360366147011518e-05, "step": 24275 }, { "epoch": 3.1529778123783574, "grad_norm": 0.001049760146997869, "learning_rate": 4.092487786214275e-05, "loss": 4.308394156396389e-05, "step": 24300 }, { "epoch": 3.15622161671208, "grad_norm": 0.001078003435395658, "learning_rate": 4.0900491614468553e-05, "loss": 4.170850850641727e-05, "step": 24325 }, { "epoch": 3.1594654210458026, "grad_norm": 0.0008330512791872025, "learning_rate": 4.087607993324005e-05, "loss": 4.0026577189564704e-05, "step": 24350 }, { "epoch": 3.1627092253795253, "grad_norm": 0.000797474873252213, "learning_rate": 4.085164285750481e-05, "loss": 4.667103290557861e-05, "step": 24375 }, { "epoch": 3.165953029713248, "grad_norm": 0.0006769119645468891, "learning_rate": 4.0827180426351066e-05, "loss": 4.11426043137908e-05, "step": 24400 }, { "epoch": 3.1691968340469705, "grad_norm": 0.00039481144631281495, "learning_rate": 4.080269267890755e-05, "loss": 4.070752765983343e-05, "step": 24425 }, { "epoch": 3.1724406383806927, "grad_norm": 0.0007251129136420786, "learning_rate": 4.077817965434354e-05, "loss": 3.7402645684778694e-05, "step": 24450 }, { "epoch": 3.1756844427144153, "grad_norm": 0.0006603851215913892, "learning_rate": 4.075364139186872e-05, "loss": 4.6773822978138926e-05, "step": 24475 }, { "epoch": 3.178928247048138, "grad_norm": 0.0019482929492369294, "learning_rate": 4.072907793073316e-05, "loss": 4.236976150423288e-05, "step": 24500 }, { "epoch": 3.1821720513818605, "grad_norm": 0.0016959913773462176, "learning_rate": 4.07044893102272e-05, "loss": 4.3279379606246946e-05, "step": 24525 }, { "epoch": 3.185415855715583, "grad_norm": 0.0012383455177769065, "learning_rate": 4.067987556968147e-05, "loss": 4.251681733876467e-05, "step": 24550 }, { "epoch": 3.188659660049306, "grad_norm": 0.0005076311063021421, "learning_rate": 4.0655236748466754e-05, "loss": 3.654904430732131e-05, "step": 24575 }, { "epoch": 3.1919034643830284, "grad_norm": 0.0012782941339537501, "learning_rate": 4.063057288599395e-05, "loss": 4.438020754605532e-05, "step": 24600 }, { "epoch": 3.195147268716751, "grad_norm": 0.0007382527110166848, "learning_rate": 4.0605884021714035e-05, "loss": 5.104681942611933e-05, "step": 24625 }, { "epoch": 3.1983910730504737, "grad_norm": 0.0014297377783805132, "learning_rate": 4.0581170195117944e-05, "loss": 4.425813443958759e-05, "step": 24650 }, { "epoch": 3.2016348773841963, "grad_norm": 0.0007482185610570014, "learning_rate": 4.055643144573658e-05, "loss": 4.606293980032206e-05, "step": 24675 }, { "epoch": 3.204878681717919, "grad_norm": 0.0016250356566160917, "learning_rate": 4.053166781314068e-05, "loss": 5.0838473252952096e-05, "step": 24700 }, { "epoch": 3.2081224860516415, "grad_norm": 0.0006201331270858645, "learning_rate": 4.050687933694078e-05, "loss": 4.882507026195526e-05, "step": 24725 }, { "epoch": 3.211366290385364, "grad_norm": 0.0010023366194218397, "learning_rate": 4.048206605678719e-05, "loss": 3.863970283418894e-05, "step": 24750 }, { "epoch": 3.2146100947190863, "grad_norm": 0.0007926562684588134, "learning_rate": 4.045722801236986e-05, "loss": 4.4933930039405825e-05, "step": 24775 }, { "epoch": 3.217853899052809, "grad_norm": 0.0010426028165966272, "learning_rate": 4.043236524341836e-05, "loss": 4.443526268005371e-05, "step": 24800 }, { "epoch": 3.2210977033865316, "grad_norm": 0.0007293027592822909, "learning_rate": 4.0407477789701806e-05, "loss": 4.238741006702185e-05, "step": 24825 }, { "epoch": 3.224341507720254, "grad_norm": 0.0011672797845676541, "learning_rate": 4.038256569102883e-05, "loss": 4.823639988899231e-05, "step": 24850 }, { "epoch": 3.227585312053977, "grad_norm": 0.0023126108571887016, "learning_rate": 4.035762898724744e-05, "loss": 5.073826760053635e-05, "step": 24875 }, { "epoch": 3.2308291163876994, "grad_norm": 0.0029198569245636463, "learning_rate": 4.0332667718245014e-05, "loss": 5.273580085486174e-05, "step": 24900 }, { "epoch": 3.234072920721422, "grad_norm": 0.002168071921914816, "learning_rate": 4.030768192394824e-05, "loss": 4.973531235009432e-05, "step": 24925 }, { "epoch": 3.2373167250551447, "grad_norm": 0.0015744210686534643, "learning_rate": 4.028267164432302e-05, "loss": 5.010646302253008e-05, "step": 24950 }, { "epoch": 3.2405605293888673, "grad_norm": 0.0011502151610329747, "learning_rate": 4.025763691937443e-05, "loss": 3.841219935566187e-05, "step": 24975 }, { "epoch": 3.24380433372259, "grad_norm": 0.0016977791674435139, "learning_rate": 4.023257778914664e-05, "loss": 4.522805102169514e-05, "step": 25000 }, { "epoch": 3.2470481380563125, "grad_norm": 0.0013370297383517027, "learning_rate": 4.020749429372286e-05, "loss": 4.610826727002859e-05, "step": 25025 }, { "epoch": 3.250291942390035, "grad_norm": 0.0007792251417413354, "learning_rate": 4.018238647322528e-05, "loss": 4.913327284157276e-05, "step": 25050 }, { "epoch": 3.253535746723758, "grad_norm": 0.0011614428367465734, "learning_rate": 4.0157254367814974e-05, "loss": 4.837936256080866e-05, "step": 25075 }, { "epoch": 3.2567795510574804, "grad_norm": 0.000767648103646934, "learning_rate": 4.013209801769189e-05, "loss": 4.710054956376553e-05, "step": 25100 }, { "epoch": 3.260023355391203, "grad_norm": 0.0009009878267534077, "learning_rate": 4.010691746309476e-05, "loss": 4.51607396826148e-05, "step": 25125 }, { "epoch": 3.263267159724925, "grad_norm": 0.0017173445085063577, "learning_rate": 4.0081712744300996e-05, "loss": 4.329418763518333e-05, "step": 25150 }, { "epoch": 3.266510964058648, "grad_norm": 0.0025473670102655888, "learning_rate": 4.005648390162669e-05, "loss": 5.0683533772826194e-05, "step": 25175 }, { "epoch": 3.2697547683923704, "grad_norm": 0.0009185242233797908, "learning_rate": 4.003123097542654e-05, "loss": 4.50909323990345e-05, "step": 25200 }, { "epoch": 3.272998572726093, "grad_norm": 0.0005501555860973895, "learning_rate": 4.00059540060937e-05, "loss": 4.153378773480654e-05, "step": 25225 }, { "epoch": 3.2762423770598157, "grad_norm": 0.0018003856530413032, "learning_rate": 3.998065303405985e-05, "loss": 4.692575428634882e-05, "step": 25250 }, { "epoch": 3.2794861813935383, "grad_norm": 0.0018212782451882958, "learning_rate": 3.995532809979503e-05, "loss": 4.1383611969649794e-05, "step": 25275 }, { "epoch": 3.282729985727261, "grad_norm": 0.0009804447181522846, "learning_rate": 3.992997924380763e-05, "loss": 4.6277516521513465e-05, "step": 25300 }, { "epoch": 3.2859737900609836, "grad_norm": 0.0015102083561941981, "learning_rate": 3.990460650664426e-05, "loss": 4.39562788233161e-05, "step": 25325 }, { "epoch": 3.289217594394706, "grad_norm": 0.0009109156089834869, "learning_rate": 3.9879209928889785e-05, "loss": 4.4946861453354356e-05, "step": 25350 }, { "epoch": 3.292461398728429, "grad_norm": 0.000749499537050724, "learning_rate": 3.985378955116716e-05, "loss": 4.1038948111236096e-05, "step": 25375 }, { "epoch": 3.2957052030621514, "grad_norm": 0.0016160579398274422, "learning_rate": 3.9828345414137436e-05, "loss": 4.0924027562141415e-05, "step": 25400 }, { "epoch": 3.298949007395874, "grad_norm": 0.0005603424506261945, "learning_rate": 3.980287755849966e-05, "loss": 3.893689950928092e-05, "step": 25425 }, { "epoch": 3.3021928117295962, "grad_norm": 0.0008785100653767586, "learning_rate": 3.9777386024990824e-05, "loss": 4.453340079635382e-05, "step": 25450 }, { "epoch": 3.305436616063319, "grad_norm": 0.0009676118497736752, "learning_rate": 3.9751870854385775e-05, "loss": 4.8193433322012425e-05, "step": 25475 }, { "epoch": 3.3086804203970415, "grad_norm": 0.0005742667126469314, "learning_rate": 3.972633208749719e-05, "loss": 4.365178290754557e-05, "step": 25500 }, { "epoch": 3.311924224730764, "grad_norm": 0.0006617010803893209, "learning_rate": 3.970076976517546e-05, "loss": 4.2940513230860235e-05, "step": 25525 }, { "epoch": 3.3151680290644867, "grad_norm": 0.0009265561238862574, "learning_rate": 3.967518392830869e-05, "loss": 4.026053473353386e-05, "step": 25550 }, { "epoch": 3.3184118333982093, "grad_norm": 0.0007680606213398278, "learning_rate": 3.964957461782259e-05, "loss": 4.038482438772917e-05, "step": 25575 }, { "epoch": 3.321655637731932, "grad_norm": 0.0009180994820781052, "learning_rate": 3.962394187468039e-05, "loss": 4.715592600405216e-05, "step": 25600 }, { "epoch": 3.3248994420656546, "grad_norm": 0.0010919830529019237, "learning_rate": 3.959828573988283e-05, "loss": 4.570081830024719e-05, "step": 25625 }, { "epoch": 3.328143246399377, "grad_norm": 0.0005328446277417243, "learning_rate": 3.957260625446805e-05, "loss": 4.2049209587275984e-05, "step": 25650 }, { "epoch": 3.3313870507331, "grad_norm": 0.000701618439052254, "learning_rate": 3.954690345951155e-05, "loss": 4.1107647120952606e-05, "step": 25675 }, { "epoch": 3.3346308550668224, "grad_norm": 0.001251544221304357, "learning_rate": 3.952117739612612e-05, "loss": 3.938335459679365e-05, "step": 25700 }, { "epoch": 3.337874659400545, "grad_norm": 0.0021360618993639946, "learning_rate": 3.9495428105461746e-05, "loss": 4.332059994339943e-05, "step": 25725 }, { "epoch": 3.3411184637342677, "grad_norm": 0.0007971558370627463, "learning_rate": 3.9469655628705587e-05, "loss": 4.1300482116639614e-05, "step": 25750 }, { "epoch": 3.3443622680679903, "grad_norm": 0.0007549440488219261, "learning_rate": 3.944386000708189e-05, "loss": 4.618597682565451e-05, "step": 25775 }, { "epoch": 3.347606072401713, "grad_norm": 0.001196548924781382, "learning_rate": 3.9418041281851894e-05, "loss": 4.0021860040724275e-05, "step": 25800 }, { "epoch": 3.3508498767354356, "grad_norm": 0.0015290466835722327, "learning_rate": 3.939219949431384e-05, "loss": 4.2726476676762106e-05, "step": 25825 }, { "epoch": 3.3540936810691577, "grad_norm": 0.0011374454479664564, "learning_rate": 3.9366334685802824e-05, "loss": 4.317757207900286e-05, "step": 25850 }, { "epoch": 3.3573374854028804, "grad_norm": 0.0006876174593344331, "learning_rate": 3.9340446897690775e-05, "loss": 4.1418620385229586e-05, "step": 25875 }, { "epoch": 3.360581289736603, "grad_norm": 0.0008845838601700962, "learning_rate": 3.9314536171386386e-05, "loss": 4.776718560606241e-05, "step": 25900 }, { "epoch": 3.3638250940703256, "grad_norm": 0.0004571919562295079, "learning_rate": 3.9288602548335026e-05, "loss": 4.463609773665666e-05, "step": 25925 }, { "epoch": 3.367068898404048, "grad_norm": 0.0010682273423299193, "learning_rate": 3.9262646070018696e-05, "loss": 4.5226728543639185e-05, "step": 25950 }, { "epoch": 3.370312702737771, "grad_norm": 0.00048235064605250955, "learning_rate": 3.923666677795596e-05, "loss": 4.1063465178012846e-05, "step": 25975 }, { "epoch": 3.3735565070714935, "grad_norm": 0.0012263667304068804, "learning_rate": 3.921066471370186e-05, "loss": 4.2775408364832404e-05, "step": 26000 }, { "epoch": 3.376800311405216, "grad_norm": 0.0007704378222115338, "learning_rate": 3.918463991884789e-05, "loss": 4.452000837773085e-05, "step": 26025 }, { "epoch": 3.3800441157389387, "grad_norm": 0.0005937514360994101, "learning_rate": 3.9158592435021864e-05, "loss": 4.003109410405159e-05, "step": 26050 }, { "epoch": 3.3832879200726613, "grad_norm": 0.0010067919502034783, "learning_rate": 3.913252230388792e-05, "loss": 4.960934165865183e-05, "step": 26075 }, { "epoch": 3.386531724406384, "grad_norm": 0.0013152039609849453, "learning_rate": 3.91064295671464e-05, "loss": 5.104416981339455e-05, "step": 26100 }, { "epoch": 3.3897755287401066, "grad_norm": 0.0007728320779278874, "learning_rate": 3.908031426653383e-05, "loss": 5.3131557069718835e-05, "step": 26125 }, { "epoch": 3.3930193330738287, "grad_norm": 0.0005529953632503748, "learning_rate": 3.90541764438228e-05, "loss": 4.607404116541147e-05, "step": 26150 }, { "epoch": 3.3962631374075514, "grad_norm": 0.000674831448122859, "learning_rate": 3.902801614082194e-05, "loss": 3.8585239090025424e-05, "step": 26175 }, { "epoch": 3.399506941741274, "grad_norm": 0.0005916499649174511, "learning_rate": 3.9001833399375845e-05, "loss": 4.0659024380147455e-05, "step": 26200 }, { "epoch": 3.4027507460749966, "grad_norm": 0.0008919015526771545, "learning_rate": 3.8975628261364975e-05, "loss": 4.484883975237608e-05, "step": 26225 }, { "epoch": 3.4059945504087192, "grad_norm": 0.0005622811149805784, "learning_rate": 3.8949400768705646e-05, "loss": 4.4319117441773415e-05, "step": 26250 }, { "epoch": 3.409238354742442, "grad_norm": 0.0022214180789887905, "learning_rate": 3.892315096334992e-05, "loss": 4.354741424322128e-05, "step": 26275 }, { "epoch": 3.4124821590761645, "grad_norm": 0.0007228165050037205, "learning_rate": 3.889687888728553e-05, "loss": 4.285359289497137e-05, "step": 26300 }, { "epoch": 3.415725963409887, "grad_norm": 0.0016848612576723099, "learning_rate": 3.8870584582535854e-05, "loss": 5.4207840003073214e-05, "step": 26325 }, { "epoch": 3.4189697677436097, "grad_norm": 0.0012607871321961284, "learning_rate": 3.884426809115982e-05, "loss": 5.0637898966670035e-05, "step": 26350 }, { "epoch": 3.4222135720773323, "grad_norm": 0.0006543390918523073, "learning_rate": 3.8817929455251856e-05, "loss": 5.0002234056591986e-05, "step": 26375 }, { "epoch": 3.425457376411055, "grad_norm": 0.0009740188252180815, "learning_rate": 3.879156871694179e-05, "loss": 4.477706737816334e-05, "step": 26400 }, { "epoch": 3.4287011807447776, "grad_norm": 0.0007962465169839561, "learning_rate": 3.87651859183948e-05, "loss": 4.5455633662641047e-05, "step": 26425 }, { "epoch": 3.4319449850785, "grad_norm": 0.00077178975334391, "learning_rate": 3.8738781101811386e-05, "loss": 4.9968911334872245e-05, "step": 26450 }, { "epoch": 3.435188789412223, "grad_norm": 0.001411296776495874, "learning_rate": 3.8712354309427234e-05, "loss": 4.091090988367796e-05, "step": 26475 }, { "epoch": 3.4384325937459455, "grad_norm": 0.0015943945618346334, "learning_rate": 3.8685905583513186e-05, "loss": 4.412185400724411e-05, "step": 26500 }, { "epoch": 3.441676398079668, "grad_norm": 0.0007967297569848597, "learning_rate": 3.8659434966375184e-05, "loss": 4.155740607529879e-05, "step": 26525 }, { "epoch": 3.4449202024133903, "grad_norm": 0.0006187683320604265, "learning_rate": 3.8632942500354175e-05, "loss": 4.337940830737353e-05, "step": 26550 }, { "epoch": 3.448164006747113, "grad_norm": 0.0013412914704531431, "learning_rate": 3.8606428227826045e-05, "loss": 4.636721219867468e-05, "step": 26575 }, { "epoch": 3.4514078110808355, "grad_norm": 0.0014010907616466284, "learning_rate": 3.8579892191201585e-05, "loss": 5.015803035348654e-05, "step": 26600 }, { "epoch": 3.454651615414558, "grad_norm": 0.0009317592484876513, "learning_rate": 3.855333443292637e-05, "loss": 4.4922893866896626e-05, "step": 26625 }, { "epoch": 3.4578954197482807, "grad_norm": 0.0011733965948224068, "learning_rate": 3.852675499548073e-05, "loss": 4.4616740196943284e-05, "step": 26650 }, { "epoch": 3.4611392240820034, "grad_norm": 0.0010472305584698915, "learning_rate": 3.850015392137969e-05, "loss": 4.210486076772213e-05, "step": 26675 }, { "epoch": 3.464383028415726, "grad_norm": 0.0006999084143899381, "learning_rate": 3.847353125317287e-05, "loss": 4.324683453887701e-05, "step": 26700 }, { "epoch": 3.4676268327494486, "grad_norm": 0.002248960081487894, "learning_rate": 3.844688703344441e-05, "loss": 4.406421910971403e-05, "step": 26725 }, { "epoch": 3.4708706370831712, "grad_norm": 0.0010605253046378493, "learning_rate": 3.8420221304812964e-05, "loss": 4.555796273052692e-05, "step": 26750 }, { "epoch": 3.474114441416894, "grad_norm": 0.00042882320121861994, "learning_rate": 3.839353410993156e-05, "loss": 4.6089780516922475e-05, "step": 26775 }, { "epoch": 3.4773582457506165, "grad_norm": 0.001153589109890163, "learning_rate": 3.8366825491487576e-05, "loss": 4.236591514199972e-05, "step": 26800 }, { "epoch": 3.480602050084339, "grad_norm": 0.0013077822513878345, "learning_rate": 3.834009549220264e-05, "loss": 4.917863290756941e-05, "step": 26825 }, { "epoch": 3.4838458544180613, "grad_norm": 0.0018597767921164632, "learning_rate": 3.8313344154832607e-05, "loss": 4.684834741055965e-05, "step": 26850 }, { "epoch": 3.487089658751784, "grad_norm": 0.0005985863390378654, "learning_rate": 3.8286571522167434e-05, "loss": 4.713954869657755e-05, "step": 26875 }, { "epoch": 3.4903334630855065, "grad_norm": 0.0006300100940279663, "learning_rate": 3.825977763703118e-05, "loss": 4.8584076575934884e-05, "step": 26900 }, { "epoch": 3.493577267419229, "grad_norm": 0.0008330089040100574, "learning_rate": 3.8232962542281844e-05, "loss": 4.778506699949503e-05, "step": 26925 }, { "epoch": 3.4968210717529518, "grad_norm": 0.00101736921351403, "learning_rate": 3.8206126280811417e-05, "loss": 4.386803600937128e-05, "step": 26950 }, { "epoch": 3.5000648760866744, "grad_norm": 0.0007974600302986801, "learning_rate": 3.817926889554567e-05, "loss": 4.554572980850935e-05, "step": 26975 }, { "epoch": 3.503308680420397, "grad_norm": 0.0010274762753397226, "learning_rate": 3.815239042944424e-05, "loss": 5.729952361434698e-05, "step": 27000 }, { "epoch": 3.5065524847541196, "grad_norm": 0.0010318615240976214, "learning_rate": 3.8125490925500425e-05, "loss": 4.19567571952939e-05, "step": 27025 }, { "epoch": 3.5097962890878422, "grad_norm": 0.0011736239539459348, "learning_rate": 3.8098570426741195e-05, "loss": 3.7924698553979396e-05, "step": 27050 }, { "epoch": 3.513040093421565, "grad_norm": 0.0011153623927384615, "learning_rate": 3.807162897622712e-05, "loss": 4.521119873970747e-05, "step": 27075 }, { "epoch": 3.5162838977552875, "grad_norm": 0.000678789394441992, "learning_rate": 3.804466661705226e-05, "loss": 4.33031003922224e-05, "step": 27100 }, { "epoch": 3.51952770208901, "grad_norm": 0.0010023320792242885, "learning_rate": 3.8017683392344117e-05, "loss": 5.229397676885128e-05, "step": 27125 }, { "epoch": 3.5227715064227327, "grad_norm": 0.0004979510558769107, "learning_rate": 3.799067934526358e-05, "loss": 4.892734345048666e-05, "step": 27150 }, { "epoch": 3.5260153107564554, "grad_norm": 0.0007002564962022007, "learning_rate": 3.7963654519004854e-05, "loss": 4.582558758556843e-05, "step": 27175 }, { "epoch": 3.529259115090178, "grad_norm": 0.0009455396793782711, "learning_rate": 3.793660895679536e-05, "loss": 4.893849603831768e-05, "step": 27200 }, { "epoch": 3.5325029194239006, "grad_norm": 0.0005176793201826513, "learning_rate": 3.79095427018957e-05, "loss": 4.527305252850056e-05, "step": 27225 }, { "epoch": 3.535746723757623, "grad_norm": 0.0009484347538091242, "learning_rate": 3.7882455797599554e-05, "loss": 4.474479705095291e-05, "step": 27250 }, { "epoch": 3.5389905280913454, "grad_norm": 0.0007579782395623624, "learning_rate": 3.7855348287233664e-05, "loss": 4.32556914165616e-05, "step": 27275 }, { "epoch": 3.542234332425068, "grad_norm": 0.0016155162593349814, "learning_rate": 3.782822021415772e-05, "loss": 4.654820077121258e-05, "step": 27300 }, { "epoch": 3.5454781367587906, "grad_norm": 0.00043548340909183025, "learning_rate": 3.780107162176429e-05, "loss": 4.602530505508184e-05, "step": 27325 }, { "epoch": 3.5487219410925133, "grad_norm": 0.000834956590551883, "learning_rate": 3.777390255347878e-05, "loss": 4.5967334881424907e-05, "step": 27350 }, { "epoch": 3.551965745426236, "grad_norm": 0.0010358686558902264, "learning_rate": 3.774671305275934e-05, "loss": 4.221521783620119e-05, "step": 27375 }, { "epoch": 3.5552095497599585, "grad_norm": 0.0024636469315737486, "learning_rate": 3.77195031630968e-05, "loss": 4.087288398295641e-05, "step": 27400 }, { "epoch": 3.558453354093681, "grad_norm": 0.0015681411605328321, "learning_rate": 3.769227292801462e-05, "loss": 4.380861762911081e-05, "step": 27425 }, { "epoch": 3.5616971584274038, "grad_norm": 0.0014030461898073554, "learning_rate": 3.766502239106877e-05, "loss": 4.140289034694433e-05, "step": 27450 }, { "epoch": 3.5649409627611264, "grad_norm": 0.0011733801802620292, "learning_rate": 3.763775159584773e-05, "loss": 4.9926661886274816e-05, "step": 27475 }, { "epoch": 3.568184767094849, "grad_norm": 0.0030635970178991556, "learning_rate": 3.7610460585972364e-05, "loss": 5.2119335159659385e-05, "step": 27500 }, { "epoch": 3.571428571428571, "grad_norm": 0.0008918663370423019, "learning_rate": 3.7583149405095875e-05, "loss": 4.523496143519878e-05, "step": 27525 }, { "epoch": 3.574672375762294, "grad_norm": 0.002284057904034853, "learning_rate": 3.755581809690373e-05, "loss": 5.2195517346262934e-05, "step": 27550 }, { "epoch": 3.5779161800960164, "grad_norm": 0.0017790596466511488, "learning_rate": 3.7528466705113585e-05, "loss": 4.811733029782772e-05, "step": 27575 }, { "epoch": 3.581159984429739, "grad_norm": 0.0015652584843337536, "learning_rate": 3.750109527347524e-05, "loss": 4.849928896874189e-05, "step": 27600 }, { "epoch": 3.581159984429739, "eval_loss": 0.0001966304989764467, "eval_runtime": 7.3093, "eval_samples_per_second": 684.065, "eval_steps_per_second": 5.473, "step": 27600 }, { "epoch": 3.581159984429739, "eval_holdout_avg_strict_f1": 0.2461496509519545, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7688773165875324, "eval_holdout_nemotron_pii_strict_f1": 0.7004830917874395, "eval_holdout_open_pii_masking_500k_strict_f1": 0.6425013835085778, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.59578436858795, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 27600 }, { "epoch": 3.5844037887634617, "grad_norm": 0.000579492945689708, "learning_rate": 3.7473703845770524e-05, "loss": 4.093813709914684e-05, "step": 27625 }, { "epoch": 3.5876475930971843, "grad_norm": 0.001159926992841065, "learning_rate": 3.744629246581326e-05, "loss": 4.170746076852083e-05, "step": 27650 }, { "epoch": 3.590891397430907, "grad_norm": 0.0006607286049984396, "learning_rate": 3.7418861177449196e-05, "loss": 4.208443686366081e-05, "step": 27675 }, { "epoch": 3.5941352017646295, "grad_norm": 0.0008463714038953185, "learning_rate": 3.7391410024555915e-05, "loss": 4.309007432311773e-05, "step": 27700 }, { "epoch": 3.597379006098352, "grad_norm": 0.0012798175448551774, "learning_rate": 3.736393905104277e-05, "loss": 4.040234256535768e-05, "step": 27725 }, { "epoch": 3.6006228104320748, "grad_norm": 0.0008972099749371409, "learning_rate": 3.733644830085084e-05, "loss": 4.9261972308158874e-05, "step": 27750 }, { "epoch": 3.6038666147657974, "grad_norm": 0.0003859047719743103, "learning_rate": 3.7308937817952794e-05, "loss": 4.8236758448183534e-05, "step": 27775 }, { "epoch": 3.60711041909952, "grad_norm": 0.0004121142264921218, "learning_rate": 3.7281407646352916e-05, "loss": 4.1202623397111896e-05, "step": 27800 }, { "epoch": 3.6103542234332426, "grad_norm": 0.0009229574352502823, "learning_rate": 3.7253857830086943e-05, "loss": 4.3535013683140276e-05, "step": 27825 }, { "epoch": 3.6135980277669653, "grad_norm": 0.004811108577996492, "learning_rate": 3.722628841322207e-05, "loss": 4.4567473232746123e-05, "step": 27850 }, { "epoch": 3.616841832100688, "grad_norm": 0.0013914438895881176, "learning_rate": 3.71986994398568e-05, "loss": 4.7705145552754404e-05, "step": 27875 }, { "epoch": 3.6200856364344105, "grad_norm": 0.00039448714233003557, "learning_rate": 3.717109095412095e-05, "loss": 4.450332373380661e-05, "step": 27900 }, { "epoch": 3.623329440768133, "grad_norm": 0.0008975021191872656, "learning_rate": 3.7143463000175546e-05, "loss": 4.278914537280798e-05, "step": 27925 }, { "epoch": 3.6265732451018553, "grad_norm": 0.0006182831129990518, "learning_rate": 3.7115815622212746e-05, "loss": 4.423223435878754e-05, "step": 27950 }, { "epoch": 3.629817049435578, "grad_norm": 0.00046005778131075203, "learning_rate": 3.708814886445577e-05, "loss": 4.272536374628544e-05, "step": 27975 }, { "epoch": 3.6330608537693005, "grad_norm": 0.0010756660485640168, "learning_rate": 3.706046277115886e-05, "loss": 3.647723002359271e-05, "step": 28000 }, { "epoch": 3.636304658103023, "grad_norm": 0.0004885623347945511, "learning_rate": 3.703275738660717e-05, "loss": 4.357357043772936e-05, "step": 28025 }, { "epoch": 3.639548462436746, "grad_norm": 0.0007503111264668405, "learning_rate": 3.7005032755116696e-05, "loss": 4.35685645788908e-05, "step": 28050 }, { "epoch": 3.6427922667704684, "grad_norm": 0.0005663898773491383, "learning_rate": 3.697728892103426e-05, "loss": 4.6284496784210204e-05, "step": 28075 }, { "epoch": 3.646036071104191, "grad_norm": 0.0008000602829270065, "learning_rate": 3.694952592873737e-05, "loss": 4.58226352930069e-05, "step": 28100 }, { "epoch": 3.6492798754379137, "grad_norm": 0.0008124265004880726, "learning_rate": 3.6921743822634184e-05, "loss": 3.977790474891662e-05, "step": 28125 }, { "epoch": 3.6525236797716363, "grad_norm": 0.0005852468311786652, "learning_rate": 3.689394264716344e-05, "loss": 4.080305807292461e-05, "step": 28150 }, { "epoch": 3.655767484105359, "grad_norm": 0.0009462133166380227, "learning_rate": 3.686612244679436e-05, "loss": 4.4563543051481245e-05, "step": 28175 }, { "epoch": 3.659011288439081, "grad_norm": 0.00035757297882810235, "learning_rate": 3.6838283266026624e-05, "loss": 4.430042579770088e-05, "step": 28200 }, { "epoch": 3.6622550927728037, "grad_norm": 0.00030553690157830715, "learning_rate": 3.6810425149390256e-05, "loss": 4.2357766069471836e-05, "step": 28225 }, { "epoch": 3.6654988971065263, "grad_norm": 0.0007969033322297037, "learning_rate": 3.678254814144557e-05, "loss": 4.378282930701971e-05, "step": 28250 }, { "epoch": 3.668742701440249, "grad_norm": 0.0006500875460915267, "learning_rate": 3.6754652286783094e-05, "loss": 4.015873651951551e-05, "step": 28275 }, { "epoch": 3.6719865057739716, "grad_norm": 0.0009039485012181103, "learning_rate": 3.6726737630023516e-05, "loss": 4.300362430512905e-05, "step": 28300 }, { "epoch": 3.675230310107694, "grad_norm": 0.0015822529094293714, "learning_rate": 3.669880421581759e-05, "loss": 4.368979949504137e-05, "step": 28325 }, { "epoch": 3.678474114441417, "grad_norm": 0.0021356954239308834, "learning_rate": 3.667085208884606e-05, "loss": 5.103406962007284e-05, "step": 28350 }, { "epoch": 3.6817179187751394, "grad_norm": 0.0010864350479096174, "learning_rate": 3.6642881293819645e-05, "loss": 5.066077224910259e-05, "step": 28375 }, { "epoch": 3.684961723108862, "grad_norm": 0.0009791644988581538, "learning_rate": 3.661489187547886e-05, "loss": 4.246945027261972e-05, "step": 28400 }, { "epoch": 3.6882055274425847, "grad_norm": 0.0008474582573398948, "learning_rate": 3.658688387859406e-05, "loss": 4.2847120203077796e-05, "step": 28425 }, { "epoch": 3.6914493317763073, "grad_norm": 0.0007384908967651427, "learning_rate": 3.655885734796529e-05, "loss": 3.806462977081537e-05, "step": 28450 }, { "epoch": 3.69469313611003, "grad_norm": 0.0005540383281186223, "learning_rate": 3.653081232842227e-05, "loss": 4.403109196573496e-05, "step": 28475 }, { "epoch": 3.6979369404437525, "grad_norm": 0.0009769611060619354, "learning_rate": 3.650274886482427e-05, "loss": 5.200906191021204e-05, "step": 28500 }, { "epoch": 3.701180744777475, "grad_norm": 0.002168738516047597, "learning_rate": 3.6474667002060046e-05, "loss": 4.8386240378022196e-05, "step": 28525 }, { "epoch": 3.704424549111198, "grad_norm": 0.0006590100238099694, "learning_rate": 3.644656678504784e-05, "loss": 4.783316515386105e-05, "step": 28550 }, { "epoch": 3.7076683534449204, "grad_norm": 0.0012781767873093486, "learning_rate": 3.641844825873518e-05, "loss": 4.736518487334252e-05, "step": 28575 }, { "epoch": 3.710912157778643, "grad_norm": 0.0005332400905899704, "learning_rate": 3.6390311468098955e-05, "loss": 5.1671057008206844e-05, "step": 28600 }, { "epoch": 3.7141559621123656, "grad_norm": 0.0013959227362647653, "learning_rate": 3.636215645814521e-05, "loss": 4.4792355038225653e-05, "step": 28625 }, { "epoch": 3.717399766446088, "grad_norm": 0.0013732523657381535, "learning_rate": 3.633398327390916e-05, "loss": 4.781631287187338e-05, "step": 28650 }, { "epoch": 3.7206435707798104, "grad_norm": 0.001106116222217679, "learning_rate": 3.630579196045508e-05, "loss": 4.639900289475918e-05, "step": 28675 }, { "epoch": 3.723887375113533, "grad_norm": 0.0006651783478446305, "learning_rate": 3.6277582562876254e-05, "loss": 5.062442272901535e-05, "step": 28700 }, { "epoch": 3.7271311794472557, "grad_norm": 0.0006117269513197243, "learning_rate": 3.624935512629489e-05, "loss": 4.209231585264206e-05, "step": 28725 }, { "epoch": 3.7303749837809783, "grad_norm": 0.0010664125438779593, "learning_rate": 3.622110969586205e-05, "loss": 4.5886998996138574e-05, "step": 28750 }, { "epoch": 3.733618788114701, "grad_norm": 0.00069056311622262, "learning_rate": 3.6192846316757575e-05, "loss": 4.181074909865856e-05, "step": 28775 }, { "epoch": 3.7368625924484236, "grad_norm": 0.0019420117605477571, "learning_rate": 3.6164565034190004e-05, "loss": 5.034476052969694e-05, "step": 28800 }, { "epoch": 3.740106396782146, "grad_norm": 0.0010657603852450848, "learning_rate": 3.613626589339653e-05, "loss": 4.37586335465312e-05, "step": 28825 }, { "epoch": 3.743350201115869, "grad_norm": 0.0005589672364294529, "learning_rate": 3.610794893964291e-05, "loss": 3.851477755233645e-05, "step": 28850 }, { "epoch": 3.7465940054495914, "grad_norm": 0.0007448703399859369, "learning_rate": 3.607961421822339e-05, "loss": 4.2333905585110185e-05, "step": 28875 }, { "epoch": 3.7498378097833136, "grad_norm": 0.0005998964770697057, "learning_rate": 3.605126177446064e-05, "loss": 4.6966997906565666e-05, "step": 28900 }, { "epoch": 3.7530816141170362, "grad_norm": 0.0010890827979892492, "learning_rate": 3.602289165370567e-05, "loss": 4.143530037254095e-05, "step": 28925 }, { "epoch": 3.756325418450759, "grad_norm": 0.0006310606840997934, "learning_rate": 3.5994503901337765e-05, "loss": 4.265272058546543e-05, "step": 28950 }, { "epoch": 3.7595692227844815, "grad_norm": 0.0012408404145389795, "learning_rate": 3.5966098562764423e-05, "loss": 5.7461885735392573e-05, "step": 28975 }, { "epoch": 3.762813027118204, "grad_norm": 0.0004135805938858539, "learning_rate": 3.593767568342126e-05, "loss": 4.853859543800354e-05, "step": 29000 }, { "epoch": 3.7660568314519267, "grad_norm": 0.0005169966025277972, "learning_rate": 3.590923530877196e-05, "loss": 4.140664357692003e-05, "step": 29025 }, { "epoch": 3.7693006357856493, "grad_norm": 0.0006860361318103969, "learning_rate": 3.588077748430819e-05, "loss": 3.85969178751111e-05, "step": 29050 }, { "epoch": 3.772544440119372, "grad_norm": 0.0005394192994572222, "learning_rate": 3.5852302255549516e-05, "loss": 4.517662338912487e-05, "step": 29075 }, { "epoch": 3.7757882444530946, "grad_norm": 0.00036774849286302924, "learning_rate": 3.582380966804336e-05, "loss": 4.1026147082448004e-05, "step": 29100 }, { "epoch": 3.779032048786817, "grad_norm": 0.0012324764393270016, "learning_rate": 3.5795299767364894e-05, "loss": 4.746244288980961e-05, "step": 29125 }, { "epoch": 3.78227585312054, "grad_norm": 0.0005778320482932031, "learning_rate": 3.5766772599116996e-05, "loss": 4.195526242256165e-05, "step": 29150 }, { "epoch": 3.7855196574542624, "grad_norm": 0.0007507649133913219, "learning_rate": 3.5738228208930156e-05, "loss": 4.6314774081110955e-05, "step": 29175 }, { "epoch": 3.788763461787985, "grad_norm": 0.0009611630230210721, "learning_rate": 3.5709666642462424e-05, "loss": 4.794475622475147e-05, "step": 29200 }, { "epoch": 3.7920072661217077, "grad_norm": 0.0021040732972323895, "learning_rate": 3.568108794539931e-05, "loss": 4.8093004152178765e-05, "step": 29225 }, { "epoch": 3.7952510704554303, "grad_norm": 0.002999034943059087, "learning_rate": 3.565249216345373e-05, "loss": 5.0621130503714086e-05, "step": 29250 }, { "epoch": 3.798494874789153, "grad_norm": 0.000765145116019994, "learning_rate": 3.562387934236593e-05, "loss": 4.709196742624044e-05, "step": 29275 }, { "epoch": 3.8017386791228756, "grad_norm": 0.0007772850804030895, "learning_rate": 3.5595249527903406e-05, "loss": 4.114629235118628e-05, "step": 29300 }, { "epoch": 3.804982483456598, "grad_norm": 0.0014263386838138103, "learning_rate": 3.556660276586084e-05, "loss": 4.038166254758835e-05, "step": 29325 }, { "epoch": 3.8082262877903204, "grad_norm": 0.0007371911779046059, "learning_rate": 3.553793910206003e-05, "loss": 4.180803894996643e-05, "step": 29350 }, { "epoch": 3.811470092124043, "grad_norm": 0.00046720815589651465, "learning_rate": 3.550925858234979e-05, "loss": 3.7809752393513917e-05, "step": 29375 }, { "epoch": 3.8147138964577656, "grad_norm": 0.0009568090899847448, "learning_rate": 3.5480561252605906e-05, "loss": 4.30109491571784e-05, "step": 29400 }, { "epoch": 3.817957700791488, "grad_norm": 0.000866416550707072, "learning_rate": 3.5451847158731054e-05, "loss": 4.7249556519091127e-05, "step": 29425 }, { "epoch": 3.821201505125211, "grad_norm": 0.001589387422427535, "learning_rate": 3.542311634665473e-05, "loss": 4.026572685688734e-05, "step": 29450 }, { "epoch": 3.8244453094589335, "grad_norm": 0.0007528674905188382, "learning_rate": 3.539436886233316e-05, "loss": 4.9334922805428506e-05, "step": 29475 }, { "epoch": 3.827689113792656, "grad_norm": 0.000520294823218137, "learning_rate": 3.5365604751749245e-05, "loss": 4.374162293970585e-05, "step": 29500 }, { "epoch": 3.8309329181263787, "grad_norm": 0.0014153922675177455, "learning_rate": 3.533682406091248e-05, "loss": 4.525240510702133e-05, "step": 29525 }, { "epoch": 3.8341767224601013, "grad_norm": 0.0007036132155917585, "learning_rate": 3.5308026835858874e-05, "loss": 4.214779008179903e-05, "step": 29550 }, { "epoch": 3.837420526793824, "grad_norm": 0.0006403983570635319, "learning_rate": 3.5279213122650894e-05, "loss": 4.084830638021231e-05, "step": 29575 }, { "epoch": 3.840664331127546, "grad_norm": 0.0008834561449475586, "learning_rate": 3.525038296737738e-05, "loss": 4.056744277477264e-05, "step": 29600 }, { "epoch": 3.8439081354612687, "grad_norm": 0.000818278465885669, "learning_rate": 3.522153641615345e-05, "loss": 4.5461212284863e-05, "step": 29625 }, { "epoch": 3.8471519397949914, "grad_norm": 0.0008416397613473237, "learning_rate": 3.5192673515120484e-05, "loss": 4.721867851912975e-05, "step": 29650 }, { "epoch": 3.850395744128714, "grad_norm": 0.0011702534975484014, "learning_rate": 3.516379431044598e-05, "loss": 4.1946396231651305e-05, "step": 29675 }, { "epoch": 3.8536395484624366, "grad_norm": 0.0016884766519069672, "learning_rate": 3.513489884832354e-05, "loss": 4.822119604796171e-05, "step": 29700 }, { "epoch": 3.8568833527961592, "grad_norm": 0.0005229106172919273, "learning_rate": 3.510598717497276e-05, "loss": 4.5842695981264115e-05, "step": 29725 }, { "epoch": 3.860127157129882, "grad_norm": 0.00026401266222819686, "learning_rate": 3.507705933663916e-05, "loss": 4.979894962161779e-05, "step": 29750 }, { "epoch": 3.8633709614636045, "grad_norm": 0.0005717190797440708, "learning_rate": 3.504811537959414e-05, "loss": 4.3308231979608536e-05, "step": 29775 }, { "epoch": 3.866614765797327, "grad_norm": 0.00048159091966226697, "learning_rate": 3.501915535013485e-05, "loss": 3.8807550445199014e-05, "step": 29800 }, { "epoch": 3.8698585701310497, "grad_norm": 0.0014631426893174648, "learning_rate": 3.4990179294584166e-05, "loss": 4.3907035142183304e-05, "step": 29825 }, { "epoch": 3.8731023744647723, "grad_norm": 0.0036375452764332294, "learning_rate": 3.4961187259290606e-05, "loss": 5.7531106285750866e-05, "step": 29850 }, { "epoch": 3.876346178798495, "grad_norm": 0.0007787732756696641, "learning_rate": 3.493217929062823e-05, "loss": 4.123023711144924e-05, "step": 29875 }, { "epoch": 3.8795899831322176, "grad_norm": 0.0006102106417529285, "learning_rate": 3.49031554349966e-05, "loss": 4.180466756224632e-05, "step": 29900 }, { "epoch": 3.88283378746594, "grad_norm": 0.0009175249724648893, "learning_rate": 3.4874115738820687e-05, "loss": 4.482083022594452e-05, "step": 29925 }, { "epoch": 3.886077591799663, "grad_norm": 0.0006578820757567883, "learning_rate": 3.484506024855078e-05, "loss": 4.761261865496636e-05, "step": 29950 }, { "epoch": 3.8893213961333855, "grad_norm": 0.0006080331513658166, "learning_rate": 3.481598901066247e-05, "loss": 4.493354354053736e-05, "step": 29975 }, { "epoch": 3.892565200467108, "grad_norm": 0.0005110282218083739, "learning_rate": 3.4786902071656496e-05, "loss": 4.177106078714132e-05, "step": 30000 }, { "epoch": 3.8958090048008303, "grad_norm": 0.001680354354903102, "learning_rate": 3.475779947805874e-05, "loss": 4.2620105668902395e-05, "step": 30025 }, { "epoch": 3.899052809134553, "grad_norm": 0.0016681165434420109, "learning_rate": 3.472868127642011e-05, "loss": 4.522707313299179e-05, "step": 30050 }, { "epoch": 3.9022966134682755, "grad_norm": 0.0011501472909003496, "learning_rate": 3.469954751331649e-05, "loss": 5.2937916480004786e-05, "step": 30075 }, { "epoch": 3.905540417801998, "grad_norm": 0.001312978914938867, "learning_rate": 3.467039823534864e-05, "loss": 4.9301437102258205e-05, "step": 30100 }, { "epoch": 3.9087842221357207, "grad_norm": 0.0008413792820647359, "learning_rate": 3.4641233489142154e-05, "loss": 3.9707059040665624e-05, "step": 30125 }, { "epoch": 3.9120280264694434, "grad_norm": 0.0006712483009323478, "learning_rate": 3.4612053321347365e-05, "loss": 3.752066288143396e-05, "step": 30150 }, { "epoch": 3.915271830803166, "grad_norm": 0.0017063062405213714, "learning_rate": 3.458285777863926e-05, "loss": 4.718075506389141e-05, "step": 30175 }, { "epoch": 3.9185156351368886, "grad_norm": 0.0008512115455232561, "learning_rate": 3.455364690771743e-05, "loss": 4.3321875855326654e-05, "step": 30200 }, { "epoch": 3.9217594394706112, "grad_norm": 0.001352629391476512, "learning_rate": 3.4524420755305987e-05, "loss": 4.337666090577841e-05, "step": 30225 }, { "epoch": 3.925003243804334, "grad_norm": 0.001108775264583528, "learning_rate": 3.4495179368153476e-05, "loss": 4.3663405813276766e-05, "step": 30250 }, { "epoch": 3.9282470481380565, "grad_norm": 0.0010016593150794506, "learning_rate": 3.446592279303282e-05, "loss": 4.088206682354212e-05, "step": 30275 }, { "epoch": 3.9314908524717787, "grad_norm": 0.0006289388402365148, "learning_rate": 3.443665107674122e-05, "loss": 3.960864152759314e-05, "step": 30300 }, { "epoch": 3.9347346568055013, "grad_norm": 0.001564680365845561, "learning_rate": 3.440736426610013e-05, "loss": 4.200912546366453e-05, "step": 30325 }, { "epoch": 3.937978461139224, "grad_norm": 0.0009601306519471109, "learning_rate": 3.43780624079551e-05, "loss": 4.324753303080797e-05, "step": 30350 }, { "epoch": 3.9412222654729465, "grad_norm": 0.0005783789674751461, "learning_rate": 3.43487455491758e-05, "loss": 3.8075561169534924e-05, "step": 30375 }, { "epoch": 3.944466069806669, "grad_norm": 0.0007904541562311351, "learning_rate": 3.431941373665585e-05, "loss": 3.8756835274398326e-05, "step": 30400 }, { "epoch": 3.9477098741403918, "grad_norm": 0.0008955388329923153, "learning_rate": 3.429006701731282e-05, "loss": 4.1949660517275336e-05, "step": 30425 }, { "epoch": 3.9509536784741144, "grad_norm": 0.001402698690071702, "learning_rate": 3.426070543808811e-05, "loss": 4.544123075902462e-05, "step": 30450 }, { "epoch": 3.954197482807837, "grad_norm": 0.001056926092132926, "learning_rate": 3.42313290459469e-05, "loss": 4.398563876748085e-05, "step": 30475 }, { "epoch": 3.9574412871415596, "grad_norm": 0.002265698043629527, "learning_rate": 3.420193788787803e-05, "loss": 5.054359324276447e-05, "step": 30500 }, { "epoch": 3.9606850914752822, "grad_norm": 0.002391388639807701, "learning_rate": 3.4172532010894015e-05, "loss": 3.840285586193204e-05, "step": 30525 }, { "epoch": 3.963928895809005, "grad_norm": 0.0007932708831503987, "learning_rate": 3.4143111462030864e-05, "loss": 4.295884631574154e-05, "step": 30550 }, { "epoch": 3.9671727001427275, "grad_norm": 0.003871380351483822, "learning_rate": 3.411367628834808e-05, "loss": 4.05646488070488e-05, "step": 30575 }, { "epoch": 3.97041650447645, "grad_norm": 0.0008865263080224395, "learning_rate": 3.4084226536928547e-05, "loss": 4.383246414363384e-05, "step": 30600 }, { "epoch": 3.9736603088101727, "grad_norm": 0.0004901876673102379, "learning_rate": 3.4054762254878476e-05, "loss": 4.114629235118628e-05, "step": 30625 }, { "epoch": 3.9769041131438954, "grad_norm": 0.0012620000634342432, "learning_rate": 3.402528348932732e-05, "loss": 4.6502589248120786e-05, "step": 30650 }, { "epoch": 3.980147917477618, "grad_norm": 0.0005894643254578114, "learning_rate": 3.399579028742769e-05, "loss": 3.604410449042916e-05, "step": 30675 }, { "epoch": 3.9833917218113406, "grad_norm": 0.000613975920714438, "learning_rate": 3.3966282696355304e-05, "loss": 3.935560118407011e-05, "step": 30700 }, { "epoch": 3.986635526145063, "grad_norm": 0.0004943959065712988, "learning_rate": 3.3936760763308884e-05, "loss": 4.177260678261519e-05, "step": 30725 }, { "epoch": 3.9898793304787854, "grad_norm": 0.0007429063552990556, "learning_rate": 3.390722453551008e-05, "loss": 4.4387392699718474e-05, "step": 30750 }, { "epoch": 3.993123134812508, "grad_norm": 0.001701177447102964, "learning_rate": 3.387767406020343e-05, "loss": 4.883730784058571e-05, "step": 30775 }, { "epoch": 3.9963669391462306, "grad_norm": 0.002209197264164686, "learning_rate": 3.384810938465626e-05, "loss": 4.782387986779213e-05, "step": 30800 }, { "epoch": 3.9996107434799533, "grad_norm": 0.0005626680795103312, "learning_rate": 3.38185305561586e-05, "loss": 4.8786252737045285e-05, "step": 30825 }, { "epoch": 4.0028545478136754, "grad_norm": 0.0006302755791693926, "learning_rate": 3.3788937622023116e-05, "loss": 4.13300096988678e-05, "step": 30850 }, { "epoch": 4.006098352147398, "grad_norm": 0.0010307558113709092, "learning_rate": 3.375933062958505e-05, "loss": 4.80516068637371e-05, "step": 30875 }, { "epoch": 4.009342156481121, "grad_norm": 0.0016848400700837374, "learning_rate": 3.372970962620212e-05, "loss": 4.3321172706782815e-05, "step": 30900 }, { "epoch": 4.012585960814843, "grad_norm": 0.001094983541406691, "learning_rate": 3.370007465925446e-05, "loss": 4.126347601413727e-05, "step": 30925 }, { "epoch": 4.015829765148566, "grad_norm": 0.0009657402406446636, "learning_rate": 3.367042577614454e-05, "loss": 3.775587771087885e-05, "step": 30950 }, { "epoch": 4.0190735694822886, "grad_norm": 0.0005453363410197198, "learning_rate": 3.3640763024297076e-05, "loss": 3.879838157445192e-05, "step": 30975 }, { "epoch": 4.022317373816011, "grad_norm": 0.0007350433734245598, "learning_rate": 3.3611086451158997e-05, "loss": 4.561838693916798e-05, "step": 31000 }, { "epoch": 4.025561178149734, "grad_norm": 0.0009553885320201516, "learning_rate": 3.35813961041993e-05, "loss": 4.2931614443659783e-05, "step": 31025 }, { "epoch": 4.028804982483456, "grad_norm": 0.0012727656867355108, "learning_rate": 3.3551692030909056e-05, "loss": 4.373057745397091e-05, "step": 31050 }, { "epoch": 4.028804982483456, "eval_loss": 0.00019020377658307552, "eval_runtime": 6.719, "eval_samples_per_second": 744.16, "eval_steps_per_second": 5.953, "step": 31050 }, { "epoch": 4.028804982483456, "eval_holdout_avg_strict_f1": 0.23954815121252093, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7523406825732408, "eval_holdout_nemotron_pii_strict_f1": 0.6680273066366389, "eval_holdout_open_pii_masking_500k_strict_f1": 0.6387629965342577, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.5758986775935929, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 31050 }, { "epoch": 4.032048786817179, "grad_norm": 0.0007933687884360552, "learning_rate": 3.352197427880126e-05, "loss": 4.128076136112213e-05, "step": 31075 }, { "epoch": 4.035292591150902, "grad_norm": 0.0009104072232730687, "learning_rate": 3.34922428954108e-05, "loss": 3.9971936494112016e-05, "step": 31100 }, { "epoch": 4.038536395484624, "grad_norm": 0.0010102967498824, "learning_rate": 3.346249792829437e-05, "loss": 3.8443473167717455e-05, "step": 31125 }, { "epoch": 4.041780199818347, "grad_norm": 0.0018192894058302045, "learning_rate": 3.343273942503039e-05, "loss": 3.866849234327674e-05, "step": 31150 }, { "epoch": 4.0450240041520695, "grad_norm": 0.0007464617374353111, "learning_rate": 3.3402967433218926e-05, "loss": 4.0462985634803775e-05, "step": 31175 }, { "epoch": 4.048267808485792, "grad_norm": 0.0009881342994049191, "learning_rate": 3.3373182000481614e-05, "loss": 3.398416563868523e-05, "step": 31200 }, { "epoch": 4.051511612819515, "grad_norm": 0.0008194869151338935, "learning_rate": 3.3343383174461604e-05, "loss": 4.106852225959301e-05, "step": 31225 }, { "epoch": 4.054755417153237, "grad_norm": 0.0005734270089305937, "learning_rate": 3.331357100282348e-05, "loss": 3.751244861632585e-05, "step": 31250 }, { "epoch": 4.05799922148696, "grad_norm": 0.001114882412366569, "learning_rate": 3.3283745533253133e-05, "loss": 3.884643316268921e-05, "step": 31275 }, { "epoch": 4.061243025820683, "grad_norm": 0.0018056039698421955, "learning_rate": 3.325390681345777e-05, "loss": 4.500715062022209e-05, "step": 31300 }, { "epoch": 4.064486830154405, "grad_norm": 0.0009239026694558561, "learning_rate": 3.322405489116575e-05, "loss": 4.742770455777645e-05, "step": 31325 }, { "epoch": 4.067730634488128, "grad_norm": 0.0009272396564483643, "learning_rate": 3.319418981412659e-05, "loss": 4.221109673380852e-05, "step": 31350 }, { "epoch": 4.0709744388218505, "grad_norm": 0.0013702315045520663, "learning_rate": 3.3164311630110805e-05, "loss": 3.5240459255874156e-05, "step": 31375 }, { "epoch": 4.074218243155573, "grad_norm": 0.00036812658072449267, "learning_rate": 3.3134420386909926e-05, "loss": 3.8682452868670224e-05, "step": 31400 }, { "epoch": 4.077462047489296, "grad_norm": 0.0007345686317421496, "learning_rate": 3.3104516132336326e-05, "loss": 4.4012241996824745e-05, "step": 31425 }, { "epoch": 4.080705851823018, "grad_norm": 0.002128400607034564, "learning_rate": 3.3074598914223224e-05, "loss": 4.0409453213214874e-05, "step": 31450 }, { "epoch": 4.083949656156741, "grad_norm": 0.00042503036092966795, "learning_rate": 3.304466878042456e-05, "loss": 3.579919692128897e-05, "step": 31475 }, { "epoch": 4.087193460490464, "grad_norm": 0.0007577290525659919, "learning_rate": 3.301472577881492e-05, "loss": 4.5718024484813216e-05, "step": 31500 }, { "epoch": 4.090437264824186, "grad_norm": 0.0017202527960762382, "learning_rate": 3.29847699572895e-05, "loss": 4.859009757637978e-05, "step": 31525 }, { "epoch": 4.093681069157908, "grad_norm": 0.0008393269963562489, "learning_rate": 3.295480136376399e-05, "loss": 4.105864092707634e-05, "step": 31550 }, { "epoch": 4.096924873491631, "grad_norm": 0.0008916324004530907, "learning_rate": 3.292482004617451e-05, "loss": 4.303882829844951e-05, "step": 31575 }, { "epoch": 4.100168677825353, "grad_norm": 0.001986779971048236, "learning_rate": 3.289482605247752e-05, "loss": 4.744171164929867e-05, "step": 31600 }, { "epoch": 4.103412482159076, "grad_norm": 0.0005542522994801402, "learning_rate": 3.2864819430649775e-05, "loss": 4.6629314310848714e-05, "step": 31625 }, { "epoch": 4.1066562864927985, "grad_norm": 0.0011069872416555882, "learning_rate": 3.2834800228688216e-05, "loss": 4.138426855206489e-05, "step": 31650 }, { "epoch": 4.109900090826521, "grad_norm": 0.0011263068299740553, "learning_rate": 3.280476849460992e-05, "loss": 4.94669983163476e-05, "step": 31675 }, { "epoch": 4.113143895160244, "grad_norm": 0.0007649706094525754, "learning_rate": 3.2774724276452e-05, "loss": 4.8141200095415116e-05, "step": 31700 }, { "epoch": 4.116387699493966, "grad_norm": 0.0006496445857919753, "learning_rate": 3.274466762227154e-05, "loss": 4.00736415758729e-05, "step": 31725 }, { "epoch": 4.119631503827689, "grad_norm": 0.0005315531743690372, "learning_rate": 3.2714598580145505e-05, "loss": 4.5153666287660596e-05, "step": 31750 }, { "epoch": 4.122875308161412, "grad_norm": 0.0005679182359017432, "learning_rate": 3.2684517198170705e-05, "loss": 4.370857495814562e-05, "step": 31775 }, { "epoch": 4.126119112495134, "grad_norm": 0.0006154331495054066, "learning_rate": 3.265442352446365e-05, "loss": 3.659602487459779e-05, "step": 31800 }, { "epoch": 4.129362916828857, "grad_norm": 0.00219510355964303, "learning_rate": 3.262431760716054e-05, "loss": 3.920928575098515e-05, "step": 31825 }, { "epoch": 4.132606721162579, "grad_norm": 0.0012211360735818744, "learning_rate": 3.259419949441714e-05, "loss": 5.08597819134593e-05, "step": 31850 }, { "epoch": 4.135850525496302, "grad_norm": 0.00045715554733760655, "learning_rate": 3.256406923440874e-05, "loss": 4.2544761672616e-05, "step": 31875 }, { "epoch": 4.139094329830025, "grad_norm": 0.000959446479100734, "learning_rate": 3.2533926875330056e-05, "loss": 3.611764870584011e-05, "step": 31900 }, { "epoch": 4.142338134163747, "grad_norm": 0.0005631069070659578, "learning_rate": 3.250377246539515e-05, "loss": 3.9381356909871105e-05, "step": 31925 }, { "epoch": 4.14558193849747, "grad_norm": 0.00018616810848470777, "learning_rate": 3.247360605283735e-05, "loss": 3.869094653055072e-05, "step": 31950 }, { "epoch": 4.1488257428311925, "grad_norm": 0.001016015070490539, "learning_rate": 3.24434276859092e-05, "loss": 4.658703692257404e-05, "step": 31975 }, { "epoch": 4.152069547164915, "grad_norm": 0.0006941891624592245, "learning_rate": 3.2413237412882366e-05, "loss": 4.190226551145315e-05, "step": 32000 }, { "epoch": 4.155313351498638, "grad_norm": 0.0018753495533019304, "learning_rate": 3.2383035282047545e-05, "loss": 3.993718419224024e-05, "step": 32025 }, { "epoch": 4.15855715583236, "grad_norm": 0.0010982095263898373, "learning_rate": 3.2352821341714426e-05, "loss": 3.857559058815241e-05, "step": 32050 }, { "epoch": 4.161800960166083, "grad_norm": 0.0008810916333459318, "learning_rate": 3.232259564021156e-05, "loss": 4.173537716269493e-05, "step": 32075 }, { "epoch": 4.165044764499806, "grad_norm": 0.0006364569417200983, "learning_rate": 3.229235822588631e-05, "loss": 4.2998692952096465e-05, "step": 32100 }, { "epoch": 4.168288568833528, "grad_norm": 0.00054854218615219, "learning_rate": 3.2262109147104803e-05, "loss": 3.9736293256282803e-05, "step": 32125 }, { "epoch": 4.171532373167251, "grad_norm": 0.0003750608884729445, "learning_rate": 3.22318484522518e-05, "loss": 4.7603924758732316e-05, "step": 32150 }, { "epoch": 4.1747761775009735, "grad_norm": 0.0005375933833420277, "learning_rate": 3.2201576189730645e-05, "loss": 4.166022874414921e-05, "step": 32175 }, { "epoch": 4.178019981834696, "grad_norm": 0.0012104285415261984, "learning_rate": 3.21712924079632e-05, "loss": 4.364199470728636e-05, "step": 32200 }, { "epoch": 4.181263786168419, "grad_norm": 0.0011686263605952263, "learning_rate": 3.214099715538973e-05, "loss": 4.083540290594101e-05, "step": 32225 }, { "epoch": 4.1845075905021405, "grad_norm": 0.0007423795177601278, "learning_rate": 3.2110690480468865e-05, "loss": 4.595385864377022e-05, "step": 32250 }, { "epoch": 4.187751394835863, "grad_norm": 0.0005573073867708445, "learning_rate": 3.2080372431677496e-05, "loss": 4.1611706838011745e-05, "step": 32275 }, { "epoch": 4.190995199169586, "grad_norm": 0.000597019970882684, "learning_rate": 3.2050043057510716e-05, "loss": 4.21640370041132e-05, "step": 32300 }, { "epoch": 4.194239003503308, "grad_norm": 0.0007300911238417029, "learning_rate": 3.201970240648172e-05, "loss": 3.706555347889662e-05, "step": 32325 }, { "epoch": 4.197482807837031, "grad_norm": 0.0005267758970148861, "learning_rate": 3.198935052712176e-05, "loss": 4.307395778596401e-05, "step": 32350 }, { "epoch": 4.200726612170754, "grad_norm": 0.0023743039928376675, "learning_rate": 3.195898746798003e-05, "loss": 4.454361274838447e-05, "step": 32375 }, { "epoch": 4.203970416504476, "grad_norm": 0.0008573386003263295, "learning_rate": 3.192861327762362e-05, "loss": 4.113227594643831e-05, "step": 32400 }, { "epoch": 4.207214220838199, "grad_norm": 0.0015900400467216969, "learning_rate": 3.189822800463742e-05, "loss": 4.3436284177005294e-05, "step": 32425 }, { "epoch": 4.2104580251719215, "grad_norm": 0.0009297629585489631, "learning_rate": 3.186783169762403e-05, "loss": 4.586858674883842e-05, "step": 32450 }, { "epoch": 4.213701829505644, "grad_norm": 0.0008448681910522282, "learning_rate": 3.183742440520373e-05, "loss": 4.341584164649248e-05, "step": 32475 }, { "epoch": 4.216945633839367, "grad_norm": 0.0004387926892377436, "learning_rate": 3.180700617601436e-05, "loss": 4.335416946560144e-05, "step": 32500 }, { "epoch": 4.220189438173089, "grad_norm": 0.00027698648045770824, "learning_rate": 3.177657705871124e-05, "loss": 3.825915511697531e-05, "step": 32525 }, { "epoch": 4.223433242506812, "grad_norm": 0.0006968023371882737, "learning_rate": 3.174613710196713e-05, "loss": 4.568591713905334e-05, "step": 32550 }, { "epoch": 4.226677046840535, "grad_norm": 0.0016449949471279979, "learning_rate": 3.171568635447211e-05, "loss": 4.75675193592906e-05, "step": 32575 }, { "epoch": 4.229920851174257, "grad_norm": 0.0005710233235731721, "learning_rate": 3.1685224864933517e-05, "loss": 3.662124276161194e-05, "step": 32600 }, { "epoch": 4.23316465550798, "grad_norm": 0.00035801532794721425, "learning_rate": 3.1654752682075885e-05, "loss": 3.827927866950631e-05, "step": 32625 }, { "epoch": 4.2364084598417024, "grad_norm": 0.0007548233843408525, "learning_rate": 3.162426985464085e-05, "loss": 4.19571390375495e-05, "step": 32650 }, { "epoch": 4.239652264175425, "grad_norm": 0.000512225495185703, "learning_rate": 3.159377643138708e-05, "loss": 4.7115990892052654e-05, "step": 32675 }, { "epoch": 4.242896068509148, "grad_norm": 0.0006434716051444411, "learning_rate": 3.156327246109016e-05, "loss": 4.1378345340490344e-05, "step": 32700 }, { "epoch": 4.24613987284287, "grad_norm": 0.0006347388261929154, "learning_rate": 3.1532757992542575e-05, "loss": 4.484648816287518e-05, "step": 32725 }, { "epoch": 4.249383677176593, "grad_norm": 0.0009701927192509174, "learning_rate": 3.15022330745536e-05, "loss": 4.7663100995123384e-05, "step": 32750 }, { "epoch": 4.2526274815103156, "grad_norm": 0.0022077863104641438, "learning_rate": 3.147169775594923e-05, "loss": 4.276616498827934e-05, "step": 32775 }, { "epoch": 4.255871285844038, "grad_norm": 0.0016236669616773725, "learning_rate": 3.1441152085572054e-05, "loss": 4.325578920543194e-05, "step": 32800 }, { "epoch": 4.259115090177761, "grad_norm": 0.0007040695054456592, "learning_rate": 3.141059611228129e-05, "loss": 4.38710767775774e-05, "step": 32825 }, { "epoch": 4.262358894511483, "grad_norm": 0.0005770160350948572, "learning_rate": 3.138002988495257e-05, "loss": 4.170538391917944e-05, "step": 32850 }, { "epoch": 4.265602698845206, "grad_norm": 0.0009465402690693736, "learning_rate": 3.134945345247797e-05, "loss": 4.439473617821932e-05, "step": 32875 }, { "epoch": 4.268846503178928, "grad_norm": 0.001205923967063427, "learning_rate": 3.131886686376586e-05, "loss": 4.780955146998167e-05, "step": 32900 }, { "epoch": 4.27209030751265, "grad_norm": 0.0012874921085312963, "learning_rate": 3.128827016774088e-05, "loss": 4.44213580340147e-05, "step": 32925 }, { "epoch": 4.275334111846373, "grad_norm": 0.0007066029938869178, "learning_rate": 3.125766341334382e-05, "loss": 4.118289798498154e-05, "step": 32950 }, { "epoch": 4.278577916180096, "grad_norm": 0.0004606159927789122, "learning_rate": 3.122704664953158e-05, "loss": 4.20650141313672e-05, "step": 32975 }, { "epoch": 4.281821720513818, "grad_norm": 0.0014317076420411468, "learning_rate": 3.119641992527703e-05, "loss": 4.002626519650221e-05, "step": 33000 }, { "epoch": 4.285065524847541, "grad_norm": 0.0009985576616600156, "learning_rate": 3.116578328956903e-05, "loss": 3.6176873836666343e-05, "step": 33025 }, { "epoch": 4.2883093291812635, "grad_norm": 0.0007075460744090378, "learning_rate": 3.113513679141224e-05, "loss": 3.761680098250508e-05, "step": 33050 }, { "epoch": 4.291553133514986, "grad_norm": 0.0005633379332721233, "learning_rate": 3.1104480479827135e-05, "loss": 3.7854043766856195e-05, "step": 33075 }, { "epoch": 4.294796937848709, "grad_norm": 0.0007735916296951473, "learning_rate": 3.107381440384985e-05, "loss": 4.141091834753752e-05, "step": 33100 }, { "epoch": 4.298040742182431, "grad_norm": 0.0005041982512921095, "learning_rate": 3.104313861253217e-05, "loss": 3.767411690205336e-05, "step": 33125 }, { "epoch": 4.301284546516154, "grad_norm": 0.0006955405115149915, "learning_rate": 3.10124531549414e-05, "loss": 3.606323152780533e-05, "step": 33150 }, { "epoch": 4.304528350849877, "grad_norm": 0.001904516015201807, "learning_rate": 3.0981758080160326e-05, "loss": 3.6226571537554265e-05, "step": 33175 }, { "epoch": 4.307772155183599, "grad_norm": 0.0009950855746865273, "learning_rate": 3.0951053437287095e-05, "loss": 3.7000335287302735e-05, "step": 33200 }, { "epoch": 4.311015959517322, "grad_norm": 0.0012861865106970072, "learning_rate": 3.092033927543518e-05, "loss": 3.6603480111807585e-05, "step": 33225 }, { "epoch": 4.3142597638510445, "grad_norm": 0.0005990606150589883, "learning_rate": 3.088961564373327e-05, "loss": 4.178570117801428e-05, "step": 33250 }, { "epoch": 4.317503568184767, "grad_norm": 0.0006554584833793342, "learning_rate": 3.085888259132519e-05, "loss": 4.3816850520670415e-05, "step": 33275 }, { "epoch": 4.32074737251849, "grad_norm": 0.0006530211539939046, "learning_rate": 3.082814016736985e-05, "loss": 5.184758920222521e-05, "step": 33300 }, { "epoch": 4.323991176852212, "grad_norm": 0.0014934006612747908, "learning_rate": 3.079738842104115e-05, "loss": 4.014892503619194e-05, "step": 33325 }, { "epoch": 4.327234981185935, "grad_norm": 0.0005168573698028922, "learning_rate": 3.076662740152789e-05, "loss": 4.475909750908613e-05, "step": 33350 }, { "epoch": 4.330478785519658, "grad_norm": 0.0007492057047784328, "learning_rate": 3.073585715803372e-05, "loss": 4.244320560246706e-05, "step": 33375 }, { "epoch": 4.33372258985338, "grad_norm": 0.0005741631612181664, "learning_rate": 3.070507773977702e-05, "loss": 4.226524382829666e-05, "step": 33400 }, { "epoch": 4.336966394187103, "grad_norm": 0.0014934317441657186, "learning_rate": 3.067428919599087e-05, "loss": 3.800830338150263e-05, "step": 33425 }, { "epoch": 4.3402101985208255, "grad_norm": 0.0010312673402950168, "learning_rate": 3.064349157592293e-05, "loss": 4.00563795119524e-05, "step": 33450 }, { "epoch": 4.343454002854548, "grad_norm": 0.0007950470317155123, "learning_rate": 3.061268492883539e-05, "loss": 4.437966737896204e-05, "step": 33475 }, { "epoch": 4.346697807188271, "grad_norm": 0.0011677031870931387, "learning_rate": 3.058186930400487e-05, "loss": 4.6711810864508155e-05, "step": 33500 }, { "epoch": 4.349941611521993, "grad_norm": 0.0009158438188023865, "learning_rate": 3.0551044750722346e-05, "loss": 3.760573687031865e-05, "step": 33525 }, { "epoch": 4.353185415855716, "grad_norm": 0.0006705686682835221, "learning_rate": 3.05202113182931e-05, "loss": 3.29125695861876e-05, "step": 33550 }, { "epoch": 4.356429220189439, "grad_norm": 0.0004166231956332922, "learning_rate": 3.048936905603658e-05, "loss": 3.679577959701419e-05, "step": 33575 }, { "epoch": 4.359673024523161, "grad_norm": 0.0010163875995203853, "learning_rate": 3.0458518013286392e-05, "loss": 3.7833380047231914e-05, "step": 33600 }, { "epoch": 4.362916828856884, "grad_norm": 0.0014566602185368538, "learning_rate": 3.0427658239390168e-05, "loss": 4.073228221386671e-05, "step": 33625 }, { "epoch": 4.3661606331906055, "grad_norm": 0.0005651727551594377, "learning_rate": 3.03967897837095e-05, "loss": 3.501393366605044e-05, "step": 33650 }, { "epoch": 4.369404437524328, "grad_norm": 0.0005215705605223775, "learning_rate": 3.0365912695619892e-05, "loss": 3.3706910908222196e-05, "step": 33675 }, { "epoch": 4.372648241858051, "grad_norm": 0.0010555817279964685, "learning_rate": 3.033502702451063e-05, "loss": 3.686183597892523e-05, "step": 33700 }, { "epoch": 4.375892046191773, "grad_norm": 0.0007402165210805833, "learning_rate": 3.030413281978475e-05, "loss": 4.091533832252026e-05, "step": 33725 }, { "epoch": 4.379135850525496, "grad_norm": 0.0011391042498871684, "learning_rate": 3.0273230130858908e-05, "loss": 3.775578690692782e-05, "step": 33750 }, { "epoch": 4.382379654859219, "grad_norm": 0.0007492948789149523, "learning_rate": 3.0242319007163373e-05, "loss": 4.3316013179719445e-05, "step": 33775 }, { "epoch": 4.385623459192941, "grad_norm": 0.000701119308359921, "learning_rate": 3.021139949814187e-05, "loss": 3.8804602809250355e-05, "step": 33800 }, { "epoch": 4.388867263526664, "grad_norm": 0.00048724483349360526, "learning_rate": 3.0180471653251552e-05, "loss": 3.246823558583856e-05, "step": 33825 }, { "epoch": 4.3921110678603865, "grad_norm": 0.0006583110080100596, "learning_rate": 3.01495355219629e-05, "loss": 3.9127436466515064e-05, "step": 33850 }, { "epoch": 4.395354872194109, "grad_norm": 0.0007582821999676526, "learning_rate": 3.0118591153759664e-05, "loss": 3.426725743338466e-05, "step": 33875 }, { "epoch": 4.398598676527832, "grad_norm": 0.00050599459791556, "learning_rate": 3.0087638598138747e-05, "loss": 3.4433531109243635e-05, "step": 33900 }, { "epoch": 4.401842480861554, "grad_norm": 0.0010431238915771246, "learning_rate": 3.0056677904610164e-05, "loss": 4.375654738396406e-05, "step": 33925 }, { "epoch": 4.405086285195277, "grad_norm": 0.00044811275438405573, "learning_rate": 3.0025709122696945e-05, "loss": 3.680224996060133e-05, "step": 33950 }, { "epoch": 4.408330089529, "grad_norm": 0.0006667483248747885, "learning_rate": 2.999473230193505e-05, "loss": 3.932956606149674e-05, "step": 33975 }, { "epoch": 4.411573893862722, "grad_norm": 0.00037590754800476134, "learning_rate": 2.99637474918733e-05, "loss": 4.315707832574844e-05, "step": 34000 }, { "epoch": 4.414817698196445, "grad_norm": 0.0008701678598299623, "learning_rate": 2.993275474207331e-05, "loss": 4.160461481660604e-05, "step": 34025 }, { "epoch": 4.4180615025301675, "grad_norm": 0.00044261376024223864, "learning_rate": 2.990175410210937e-05, "loss": 3.740609390661121e-05, "step": 34050 }, { "epoch": 4.42130530686389, "grad_norm": 0.0013543760869652033, "learning_rate": 2.9870745621568408e-05, "loss": 3.530652495101094e-05, "step": 34075 }, { "epoch": 4.424549111197613, "grad_norm": 0.0009281061356887221, "learning_rate": 2.9839729350049895e-05, "loss": 3.9146221242845056e-05, "step": 34100 }, { "epoch": 4.427792915531335, "grad_norm": 0.0010026423260569572, "learning_rate": 2.9808705337165742e-05, "loss": 3.306262427940965e-05, "step": 34125 }, { "epoch": 4.431036719865058, "grad_norm": 0.0005490522598847747, "learning_rate": 2.9777673632540275e-05, "loss": 3.7121158093214036e-05, "step": 34150 }, { "epoch": 4.434280524198781, "grad_norm": 0.0005508559406735003, "learning_rate": 2.9746634285810103e-05, "loss": 4.004005342721939e-05, "step": 34175 }, { "epoch": 4.437524328532503, "grad_norm": 0.0006071496172808111, "learning_rate": 2.9715587346624058e-05, "loss": 4.001982044428587e-05, "step": 34200 }, { "epoch": 4.440768132866226, "grad_norm": 0.0009047069470398128, "learning_rate": 2.9684532864643122e-05, "loss": 3.993217833340168e-05, "step": 34225 }, { "epoch": 4.4440119371999485, "grad_norm": 0.0005028257728554308, "learning_rate": 2.965347088954034e-05, "loss": 3.929023630917072e-05, "step": 34250 }, { "epoch": 4.447255741533671, "grad_norm": 0.0013740395661443472, "learning_rate": 2.962240147100075e-05, "loss": 3.288256237283349e-05, "step": 34275 }, { "epoch": 4.450499545867393, "grad_norm": 0.0006901064771227539, "learning_rate": 2.9591324658721282e-05, "loss": 3.397275926545263e-05, "step": 34300 }, { "epoch": 4.4537433502011154, "grad_norm": 0.00034208668512292206, "learning_rate": 2.9560240502410706e-05, "loss": 2.9406384564936163e-05, "step": 34325 }, { "epoch": 4.456987154534838, "grad_norm": 0.0004202490672469139, "learning_rate": 2.9529149051789535e-05, "loss": 3.756300546228886e-05, "step": 34350 }, { "epoch": 4.460230958868561, "grad_norm": 0.0009160100016742945, "learning_rate": 2.9498050356589935e-05, "loss": 3.710371209308505e-05, "step": 34375 }, { "epoch": 4.463474763202283, "grad_norm": 0.0006076236022636294, "learning_rate": 2.946694446655569e-05, "loss": 4.0398011915385726e-05, "step": 34400 }, { "epoch": 4.466718567536006, "grad_norm": 0.0003576447197701782, "learning_rate": 2.9435831431442075e-05, "loss": 3.814438357949257e-05, "step": 34425 }, { "epoch": 4.469962371869729, "grad_norm": 0.0007447937969118357, "learning_rate": 2.940471130101578e-05, "loss": 5.181849468499422e-05, "step": 34450 }, { "epoch": 4.473206176203451, "grad_norm": 0.0007530784932896495, "learning_rate": 2.937358412505487e-05, "loss": 4.064603243023157e-05, "step": 34475 }, { "epoch": 4.476449980537174, "grad_norm": 0.0004697466210927814, "learning_rate": 2.9342449953348667e-05, "loss": 3.726462135091424e-05, "step": 34500 }, { "epoch": 4.476449980537174, "eval_loss": 0.000173921711393632, "eval_runtime": 6.4995, "eval_samples_per_second": 769.29, "eval_steps_per_second": 6.154, "step": 34500 }, { "epoch": 4.476449980537174, "eval_holdout_avg_strict_f1": 0.2580485823092506, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7734278668310729, "eval_holdout_nemotron_pii_strict_f1": 0.7363740896895363, "eval_holdout_open_pii_masking_500k_strict_f1": 0.6794395195882184, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.6492929292929293, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 34500 }, { "epoch": 4.479693784870896, "grad_norm": 0.0, "learning_rate": 2.931130883569768e-05, "loss": 3.336877794936299e-05, "step": 34525 }, { "epoch": 4.482937589204619, "grad_norm": 0.0009307398577220738, "learning_rate": 2.9280160821913543e-05, "loss": 3.611719235777855e-05, "step": 34550 }, { "epoch": 4.486181393538342, "grad_norm": 0.0003804250154644251, "learning_rate": 2.92490059618189e-05, "loss": 3.176772268489003e-05, "step": 34575 }, { "epoch": 4.489425197872064, "grad_norm": 0.0010610689641907811, "learning_rate": 2.9217844305247368e-05, "loss": 3.5637076944112775e-05, "step": 34600 }, { "epoch": 4.492669002205787, "grad_norm": 0.00024295052571687847, "learning_rate": 2.918667590204341e-05, "loss": 4.0753735229372976e-05, "step": 34625 }, { "epoch": 4.4959128065395095, "grad_norm": 0.0009275286574847996, "learning_rate": 2.9155500802062297e-05, "loss": 4.188789054751396e-05, "step": 34650 }, { "epoch": 4.499156610873232, "grad_norm": 0.0015759505331516266, "learning_rate": 2.9124319055170014e-05, "loss": 4.104943014681339e-05, "step": 34675 }, { "epoch": 4.502400415206955, "grad_norm": 0.0008328352123498917, "learning_rate": 2.909313071124317e-05, "loss": 4.1110762394964696e-05, "step": 34700 }, { "epoch": 4.505644219540677, "grad_norm": 0.0008898891392163932, "learning_rate": 2.9061935820168934e-05, "loss": 3.609901061281562e-05, "step": 34725 }, { "epoch": 4.5088880238744, "grad_norm": 0.0011193981627002358, "learning_rate": 2.903073443184494e-05, "loss": 4.573770798742771e-05, "step": 34750 }, { "epoch": 4.512131828208123, "grad_norm": 0.0020215080585330725, "learning_rate": 2.8999526596179217e-05, "loss": 5.203929729759693e-05, "step": 34775 }, { "epoch": 4.515375632541845, "grad_norm": 0.0005364791722968221, "learning_rate": 2.89683123630901e-05, "loss": 4.316029138863087e-05, "step": 34800 }, { "epoch": 4.518619436875568, "grad_norm": 0.00053931720321998, "learning_rate": 2.8937091782506177e-05, "loss": 4.2742150835692886e-05, "step": 34825 }, { "epoch": 4.5218632412092905, "grad_norm": 0.0005388120771385729, "learning_rate": 2.8905864904366177e-05, "loss": 3.681514179334044e-05, "step": 34850 }, { "epoch": 4.525107045543013, "grad_norm": 0.0011750467820093036, "learning_rate": 2.8874631778618887e-05, "loss": 4.41757682710886e-05, "step": 34875 }, { "epoch": 4.528350849876736, "grad_norm": 0.001186250476166606, "learning_rate": 2.8843392455223116e-05, "loss": 4.044479224830866e-05, "step": 34900 }, { "epoch": 4.531594654210458, "grad_norm": 0.0005478340899571776, "learning_rate": 2.881214698414757e-05, "loss": 3.4660212695598605e-05, "step": 34925 }, { "epoch": 4.534838458544181, "grad_norm": 0.0006180902710184455, "learning_rate": 2.8780895415370785e-05, "loss": 3.794180927798152e-05, "step": 34950 }, { "epoch": 4.538082262877904, "grad_norm": 0.001312060048803687, "learning_rate": 2.8749637798881057e-05, "loss": 3.808504436165094e-05, "step": 34975 }, { "epoch": 4.541326067211626, "grad_norm": 0.00033861352130770683, "learning_rate": 2.8718374184676362e-05, "loss": 3.8655262906104325e-05, "step": 35000 }, { "epoch": 4.544569871545349, "grad_norm": 0.0005116929532960057, "learning_rate": 2.8687104622764253e-05, "loss": 3.555746050551534e-05, "step": 35025 }, { "epoch": 4.547813675879071, "grad_norm": 0.00046359392581507564, "learning_rate": 2.8655829163161812e-05, "loss": 4.1861832141876223e-05, "step": 35050 }, { "epoch": 4.551057480212793, "grad_norm": 0.00044747197534888983, "learning_rate": 2.8624547855895557e-05, "loss": 4.318142309784889e-05, "step": 35075 }, { "epoch": 4.554301284546516, "grad_norm": 0.0006316831568256021, "learning_rate": 2.8593260751001332e-05, "loss": 3.557635471224785e-05, "step": 35100 }, { "epoch": 4.5575450888802385, "grad_norm": 0.0007391299004666507, "learning_rate": 2.856196789852429e-05, "loss": 4.2761429212987423e-05, "step": 35125 }, { "epoch": 4.560788893213961, "grad_norm": 0.0008205951889976859, "learning_rate": 2.8530669348518753e-05, "loss": 4.2315274477005005e-05, "step": 35150 }, { "epoch": 4.564032697547684, "grad_norm": 0.0009971773251891136, "learning_rate": 2.8499365151048168e-05, "loss": 3.548080800101161e-05, "step": 35175 }, { "epoch": 4.567276501881406, "grad_norm": 0.0007799628074280918, "learning_rate": 2.8468055356185018e-05, "loss": 3.833168186247349e-05, "step": 35200 }, { "epoch": 4.570520306215129, "grad_norm": 0.0003785428998526186, "learning_rate": 2.8436740014010722e-05, "loss": 3.4973863512277605e-05, "step": 35225 }, { "epoch": 4.573764110548852, "grad_norm": 0.0006793165812268853, "learning_rate": 2.8405419174615594e-05, "loss": 3.4793703816831114e-05, "step": 35250 }, { "epoch": 4.577007914882574, "grad_norm": 0.0005775963072665036, "learning_rate": 2.8374092888098725e-05, "loss": 3.72037966735661e-05, "step": 35275 }, { "epoch": 4.580251719216297, "grad_norm": 0.001127386698499322, "learning_rate": 2.834276120456793e-05, "loss": 4.335041623562574e-05, "step": 35300 }, { "epoch": 4.583495523550019, "grad_norm": 0.0008708020905032754, "learning_rate": 2.8311424174139644e-05, "loss": 4.123654682189226e-05, "step": 35325 }, { "epoch": 4.586739327883742, "grad_norm": 0.0023426746483892202, "learning_rate": 2.828008184693886e-05, "loss": 4.362540319561958e-05, "step": 35350 }, { "epoch": 4.589983132217465, "grad_norm": 0.0005438149673864245, "learning_rate": 2.824873427309907e-05, "loss": 4.679302684962749e-05, "step": 35375 }, { "epoch": 4.593226936551187, "grad_norm": 0.0008884759736247361, "learning_rate": 2.8217381502762108e-05, "loss": 3.729326883330941e-05, "step": 35400 }, { "epoch": 4.59647074088491, "grad_norm": 0.000501542235724628, "learning_rate": 2.8186023586078146e-05, "loss": 4.321662243455649e-05, "step": 35425 }, { "epoch": 4.5997145452186325, "grad_norm": 0.00024432403733953834, "learning_rate": 2.8154660573205604e-05, "loss": 3.628972452133894e-05, "step": 35450 }, { "epoch": 4.602958349552355, "grad_norm": 0.0009992937557399273, "learning_rate": 2.8123292514311027e-05, "loss": 4.1996887885034086e-05, "step": 35475 }, { "epoch": 4.606202153886078, "grad_norm": 0.0003185585665050894, "learning_rate": 2.8091919459569045e-05, "loss": 4.0802923031151295e-05, "step": 35500 }, { "epoch": 4.6094459582198, "grad_norm": 0.0006628817063756287, "learning_rate": 2.8060541459162272e-05, "loss": 4.110474605113268e-05, "step": 35525 }, { "epoch": 4.612689762553523, "grad_norm": 0.0010700649581849575, "learning_rate": 2.8029158563281234e-05, "loss": 4.239363130182028e-05, "step": 35550 }, { "epoch": 4.615933566887246, "grad_norm": 0.0003746141155716032, "learning_rate": 2.7997770822124296e-05, "loss": 4.157417919486761e-05, "step": 35575 }, { "epoch": 4.619177371220968, "grad_norm": 0.0010432557901367545, "learning_rate": 2.796637828589757e-05, "loss": 4.389554262161255e-05, "step": 35600 }, { "epoch": 4.622421175554691, "grad_norm": 0.0006849509663879871, "learning_rate": 2.793498100481483e-05, "loss": 3.962317015975714e-05, "step": 35625 }, { "epoch": 4.6256649798884135, "grad_norm": 0.0007996795466169715, "learning_rate": 2.7903579029097443e-05, "loss": 3.540988080203533e-05, "step": 35650 }, { "epoch": 4.628908784222135, "grad_norm": 0.0005196417914703488, "learning_rate": 2.7872172408974294e-05, "loss": 4.2824498377740385e-05, "step": 35675 }, { "epoch": 4.632152588555858, "grad_norm": 0.0009519275045022368, "learning_rate": 2.7840761194681686e-05, "loss": 3.7264367565512655e-05, "step": 35700 }, { "epoch": 4.6353963928895805, "grad_norm": 0.0010013097198680043, "learning_rate": 2.780934543646327e-05, "loss": 3.952788189053535e-05, "step": 35725 }, { "epoch": 4.638640197223303, "grad_norm": 0.0010325988987460732, "learning_rate": 2.7777925184569976e-05, "loss": 3.9081084541976454e-05, "step": 35750 }, { "epoch": 4.641884001557026, "grad_norm": 0.0008648153743706644, "learning_rate": 2.7746500489259908e-05, "loss": 4.078222904354334e-05, "step": 35775 }, { "epoch": 4.645127805890748, "grad_norm": 0.0008446076535619795, "learning_rate": 2.7715071400798297e-05, "loss": 3.9768414571881296e-05, "step": 35800 }, { "epoch": 4.648371610224471, "grad_norm": 0.00043696057400666177, "learning_rate": 2.768363796945739e-05, "loss": 4.0078437887132165e-05, "step": 35825 }, { "epoch": 4.651615414558194, "grad_norm": 0.0013674326473847032, "learning_rate": 2.765220024551636e-05, "loss": 4.32458845898509e-05, "step": 35850 }, { "epoch": 4.654859218891916, "grad_norm": 0.0010083907982334495, "learning_rate": 2.7620758279261294e-05, "loss": 4.503101110458374e-05, "step": 35875 }, { "epoch": 4.658103023225639, "grad_norm": 0.0007725781761109829, "learning_rate": 2.7589312120985012e-05, "loss": 3.572899149730802e-05, "step": 35900 }, { "epoch": 4.6613468275593615, "grad_norm": 0.001091826823540032, "learning_rate": 2.7557861820987073e-05, "loss": 4.0119336917996404e-05, "step": 35925 }, { "epoch": 4.664590631893084, "grad_norm": 0.0005822695093229413, "learning_rate": 2.7526407429573657e-05, "loss": 3.5729561932384965e-05, "step": 35950 }, { "epoch": 4.667834436226807, "grad_norm": 0.0006506218924187124, "learning_rate": 2.749494899705748e-05, "loss": 3.405211260542273e-05, "step": 35975 }, { "epoch": 4.671078240560529, "grad_norm": 0.0010840105824172497, "learning_rate": 2.7463486573757724e-05, "loss": 3.810702823102474e-05, "step": 36000 }, { "epoch": 4.674322044894252, "grad_norm": 0.0007507480913773179, "learning_rate": 2.7432020209999955e-05, "loss": 3.848991356790066e-05, "step": 36025 }, { "epoch": 4.677565849227975, "grad_norm": 0.0006195183377712965, "learning_rate": 2.7400549956116046e-05, "loss": 3.835128620266914e-05, "step": 36050 }, { "epoch": 4.680809653561697, "grad_norm": 0.0017082876292988658, "learning_rate": 2.7369075862444082e-05, "loss": 4.426393657922745e-05, "step": 36075 }, { "epoch": 4.68405345789542, "grad_norm": 0.0013238344108685851, "learning_rate": 2.7337597979328305e-05, "loss": 3.8863413501530885e-05, "step": 36100 }, { "epoch": 4.6872972622291424, "grad_norm": 0.000718685332685709, "learning_rate": 2.730611635711901e-05, "loss": 3.84543975815177e-05, "step": 36125 }, { "epoch": 4.690541066562865, "grad_norm": 0.0010830347891896963, "learning_rate": 2.727463104617247e-05, "loss": 3.999556880444288e-05, "step": 36150 }, { "epoch": 4.693784870896588, "grad_norm": 0.0006952297990210354, "learning_rate": 2.7243142096850867e-05, "loss": 3.4521480556577445e-05, "step": 36175 }, { "epoch": 4.69702867523031, "grad_norm": 0.0006497997674159706, "learning_rate": 2.721164955952218e-05, "loss": 3.6269715055823324e-05, "step": 36200 }, { "epoch": 4.700272479564033, "grad_norm": 0.0015531796962022781, "learning_rate": 2.7180153484560162e-05, "loss": 3.3827079460024836e-05, "step": 36225 }, { "epoch": 4.703516283897756, "grad_norm": 0.0005983860464766622, "learning_rate": 2.7148653922344203e-05, "loss": 3.583181416615844e-05, "step": 36250 }, { "epoch": 4.706760088231478, "grad_norm": 0.0006591008859686553, "learning_rate": 2.7117150923259277e-05, "loss": 3.597404807806015e-05, "step": 36275 }, { "epoch": 4.710003892565201, "grad_norm": 0.0020070828031748533, "learning_rate": 2.7085644537695848e-05, "loss": 4.203666467219591e-05, "step": 36300 }, { "epoch": 4.713247696898923, "grad_norm": 0.0, "learning_rate": 2.705413481604981e-05, "loss": 3.611213993281126e-05, "step": 36325 }, { "epoch": 4.716491501232646, "grad_norm": 0.0007751074736006558, "learning_rate": 2.7022621808722377e-05, "loss": 3.889452666044235e-05, "step": 36350 }, { "epoch": 4.719735305566369, "grad_norm": 0.000997640541754663, "learning_rate": 2.6991105566120027e-05, "loss": 3.361131530255079e-05, "step": 36375 }, { "epoch": 4.722979109900091, "grad_norm": 0.0003068481746595353, "learning_rate": 2.6959586138654418e-05, "loss": 4.144566133618355e-05, "step": 36400 }, { "epoch": 4.726222914233814, "grad_norm": 0.0009561215993016958, "learning_rate": 2.69280635767423e-05, "loss": 3.3543026074767115e-05, "step": 36425 }, { "epoch": 4.729466718567536, "grad_norm": 0.0008506106096319854, "learning_rate": 2.689653793080543e-05, "loss": 4.105718806385994e-05, "step": 36450 }, { "epoch": 4.732710522901258, "grad_norm": 0.0005009942105971277, "learning_rate": 2.6865009251270507e-05, "loss": 3.3807598520070314e-05, "step": 36475 }, { "epoch": 4.735954327234981, "grad_norm": 0.0007317872368730605, "learning_rate": 2.6833477588569067e-05, "loss": 3.725995309650898e-05, "step": 36500 }, { "epoch": 4.7391981315687035, "grad_norm": 0.0003682608366943896, "learning_rate": 2.6801942993137437e-05, "loss": 3.670587437227368e-05, "step": 36525 }, { "epoch": 4.742441935902426, "grad_norm": 0.00045066099846735597, "learning_rate": 2.6770405515416625e-05, "loss": 4.1775228455662725e-05, "step": 36550 }, { "epoch": 4.745685740236149, "grad_norm": 0.0010954657336696982, "learning_rate": 2.673886520585225e-05, "loss": 4.227147903293371e-05, "step": 36575 }, { "epoch": 4.748929544569871, "grad_norm": 0.0009537553996779025, "learning_rate": 2.6707322114894457e-05, "loss": 3.9988006465137e-05, "step": 36600 }, { "epoch": 4.752173348903594, "grad_norm": 0.0006414856179617345, "learning_rate": 2.6675776292997852e-05, "loss": 3.6609016824513674e-05, "step": 36625 }, { "epoch": 4.755417153237317, "grad_norm": 0.0006512664258480072, "learning_rate": 2.6644227790621395e-05, "loss": 3.251847112551331e-05, "step": 36650 }, { "epoch": 4.758660957571039, "grad_norm": 0.00036602350883185863, "learning_rate": 2.6612676658228346e-05, "loss": 4.035871475934982e-05, "step": 36675 }, { "epoch": 4.761904761904762, "grad_norm": 0.0005470770411193371, "learning_rate": 2.6581122946286163e-05, "loss": 3.7623820826411244e-05, "step": 36700 }, { "epoch": 4.7651485662384845, "grad_norm": 0.0006381148705258965, "learning_rate": 2.6549566705266433e-05, "loss": 3.7395344115793705e-05, "step": 36725 }, { "epoch": 4.768392370572207, "grad_norm": 0.0016396589344367385, "learning_rate": 2.6518007985644778e-05, "loss": 3.847555024549365e-05, "step": 36750 }, { "epoch": 4.77163617490593, "grad_norm": 0.0006662808009423316, "learning_rate": 2.6486446837900814e-05, "loss": 3.875174093991518e-05, "step": 36775 }, { "epoch": 4.774879979239652, "grad_norm": 0.0006751398905180395, "learning_rate": 2.6454883312518013e-05, "loss": 3.8278684951365e-05, "step": 36800 }, { "epoch": 4.778123783573375, "grad_norm": 0.000585883273743093, "learning_rate": 2.6423317459983666e-05, "loss": 3.979416098445654e-05, "step": 36825 }, { "epoch": 4.781367587907098, "grad_norm": 0.0004128923756070435, "learning_rate": 2.6391749330788762e-05, "loss": 3.4840134903788564e-05, "step": 36850 }, { "epoch": 4.78461139224082, "grad_norm": 0.0008302299538627267, "learning_rate": 2.636017897542797e-05, "loss": 3.7656771019101144e-05, "step": 36875 }, { "epoch": 4.787855196574543, "grad_norm": 0.00031721845152787864, "learning_rate": 2.632860644439948e-05, "loss": 3.865843405947089e-05, "step": 36900 }, { "epoch": 4.7910990009082655, "grad_norm": 0.0004355985438451171, "learning_rate": 2.6297031788205002e-05, "loss": 3.535999683663249e-05, "step": 36925 }, { "epoch": 4.794342805241988, "grad_norm": 0.0004651838098652661, "learning_rate": 2.6265455057349604e-05, "loss": 3.586487146094442e-05, "step": 36950 }, { "epoch": 4.797586609575711, "grad_norm": 0.0004937793128192425, "learning_rate": 2.62338763023417e-05, "loss": 3.9715240709483624e-05, "step": 36975 }, { "epoch": 4.800830413909433, "grad_norm": 0.0005703428760170937, "learning_rate": 2.6202295573692936e-05, "loss": 3.571536624804139e-05, "step": 37000 }, { "epoch": 4.804074218243156, "grad_norm": 0.001336882822215557, "learning_rate": 2.617071292191811e-05, "loss": 4.036291502416134e-05, "step": 37025 }, { "epoch": 4.807318022576878, "grad_norm": 0.0008732742862775922, "learning_rate": 2.6139128397535105e-05, "loss": 3.829450579360127e-05, "step": 37050 }, { "epoch": 4.8105618269106, "grad_norm": 0.0014881333336234093, "learning_rate": 2.61075420510648e-05, "loss": 4.478400107473135e-05, "step": 37075 }, { "epoch": 4.813805631244323, "grad_norm": 0.0007765120244584978, "learning_rate": 2.607595393303096e-05, "loss": 3.7345264572650195e-05, "step": 37100 }, { "epoch": 4.8170494355780455, "grad_norm": 0.0007383976480923593, "learning_rate": 2.6044364093960232e-05, "loss": 3.570413216948509e-05, "step": 37125 }, { "epoch": 4.820293239911768, "grad_norm": 0.0005844950210303068, "learning_rate": 2.6012772584381972e-05, "loss": 3.924828954041004e-05, "step": 37150 }, { "epoch": 4.823537044245491, "grad_norm": 0.0004558035871013999, "learning_rate": 2.598117945482823e-05, "loss": 3.527100896462798e-05, "step": 37175 }, { "epoch": 4.826780848579213, "grad_norm": 0.0005404905532486737, "learning_rate": 2.594958475583365e-05, "loss": 4.437487106770277e-05, "step": 37200 }, { "epoch": 4.830024652912936, "grad_norm": 0.0013711262727156281, "learning_rate": 2.5917988537935374e-05, "loss": 3.789080772548914e-05, "step": 37225 }, { "epoch": 4.833268457246659, "grad_norm": 0.0013004003558307886, "learning_rate": 2.5886390851672983e-05, "loss": 3.993455786257982e-05, "step": 37250 }, { "epoch": 4.836512261580381, "grad_norm": 0.0010389263043180108, "learning_rate": 2.5854791747588393e-05, "loss": 4.692257847636938e-05, "step": 37275 }, { "epoch": 4.839756065914104, "grad_norm": 0.0008038925006985664, "learning_rate": 2.5823191276225812e-05, "loss": 4.048589151352644e-05, "step": 37300 }, { "epoch": 4.8429998702478265, "grad_norm": 0.0005735877784900367, "learning_rate": 2.579158948813161e-05, "loss": 3.4819375723600385e-05, "step": 37325 }, { "epoch": 4.846243674581549, "grad_norm": 0.00042485364247113466, "learning_rate": 2.5759986433854283e-05, "loss": 3.548180684447289e-05, "step": 37350 }, { "epoch": 4.849487478915272, "grad_norm": 0.0004163100093137473, "learning_rate": 2.5728382163944338e-05, "loss": 3.728169249370694e-05, "step": 37375 }, { "epoch": 4.852731283248994, "grad_norm": 0.0009800869738683105, "learning_rate": 2.569677672895423e-05, "loss": 4.040942527353764e-05, "step": 37400 }, { "epoch": 4.855975087582717, "grad_norm": 0.0013112891465425491, "learning_rate": 2.566517017943828e-05, "loss": 3.951534163206816e-05, "step": 37425 }, { "epoch": 4.85921889191644, "grad_norm": 0.0019332034280523658, "learning_rate": 2.5633562565952596e-05, "loss": 3.685235511511564e-05, "step": 37450 }, { "epoch": 4.862462696250162, "grad_norm": 0.00048283228534273803, "learning_rate": 2.560195393905498e-05, "loss": 3.729834221303463e-05, "step": 37475 }, { "epoch": 4.865706500583885, "grad_norm": 0.0011075000511482358, "learning_rate": 2.5570344349304853e-05, "loss": 3.9619547314941884e-05, "step": 37500 }, { "epoch": 4.8689503049176075, "grad_norm": 0.0006382036954164505, "learning_rate": 2.5538733847263185e-05, "loss": 3.6542089655995366e-05, "step": 37525 }, { "epoch": 4.87219410925133, "grad_norm": 0.0005819716025143862, "learning_rate": 2.550712248349241e-05, "loss": 4.150549415498972e-05, "step": 37550 }, { "epoch": 4.875437913585053, "grad_norm": 0.0007582259131595492, "learning_rate": 2.5475510308556316e-05, "loss": 4.1024540551006793e-05, "step": 37575 }, { "epoch": 4.878681717918775, "grad_norm": 0.0009135333821177483, "learning_rate": 2.544389737302002e-05, "loss": 3.882033750414848e-05, "step": 37600 }, { "epoch": 4.881925522252498, "grad_norm": 0.0010457292664796114, "learning_rate": 2.5412283727449826e-05, "loss": 4.056185949593782e-05, "step": 37625 }, { "epoch": 4.885169326586221, "grad_norm": 0.0005853557377122343, "learning_rate": 2.5380669422413194e-05, "loss": 3.5850724671036006e-05, "step": 37650 }, { "epoch": 4.888413130919943, "grad_norm": 0.0007774127880111337, "learning_rate": 2.5349054508478637e-05, "loss": 3.4409034997224806e-05, "step": 37675 }, { "epoch": 4.891656935253666, "grad_norm": 0.0003980479668825865, "learning_rate": 2.5317439036215628e-05, "loss": 3.818449331447482e-05, "step": 37700 }, { "epoch": 4.8949007395873885, "grad_norm": 0.0003619285998865962, "learning_rate": 2.5285823056194545e-05, "loss": 3.634564112871885e-05, "step": 37725 }, { "epoch": 4.898144543921111, "grad_norm": 0.0025687862653285265, "learning_rate": 2.525420661898658e-05, "loss": 4.15163254365325e-05, "step": 37750 }, { "epoch": 4.901388348254834, "grad_norm": 0.001299195340834558, "learning_rate": 2.5222589775163653e-05, "loss": 3.866537706926465e-05, "step": 37775 }, { "epoch": 4.904632152588556, "grad_norm": 0.0006807277677580714, "learning_rate": 2.5190972575298323e-05, "loss": 3.614152548834682e-05, "step": 37800 }, { "epoch": 4.907875956922278, "grad_norm": 0.0012657828629016876, "learning_rate": 2.515935506996374e-05, "loss": 3.931540064513683e-05, "step": 37825 }, { "epoch": 4.911119761256001, "grad_norm": 0.0007375584100373089, "learning_rate": 2.5127737309733523e-05, "loss": 3.544008126482367e-05, "step": 37850 }, { "epoch": 4.914363565589723, "grad_norm": 0.0005433216574601829, "learning_rate": 2.509611934518172e-05, "loss": 3.75429168343544e-05, "step": 37875 }, { "epoch": 4.917607369923446, "grad_norm": 0.000554739439394325, "learning_rate": 2.5064501226882674e-05, "loss": 4.042088519781828e-05, "step": 37900 }, { "epoch": 4.920851174257169, "grad_norm": 0.0008476474322378635, "learning_rate": 2.5032883005411008e-05, "loss": 4.039444494992495e-05, "step": 37925 }, { "epoch": 4.924094978590891, "grad_norm": 0.00039724487578496337, "learning_rate": 2.500126473134149e-05, "loss": 3.712556092068553e-05, "step": 37950 }, { "epoch": 4.924094978590891, "eval_loss": 0.00017548276809975505, "eval_runtime": 7.0818, "eval_samples_per_second": 706.04, "eval_steps_per_second": 5.648, "step": 37950 }, { "epoch": 4.924094978590891, "eval_holdout_avg_strict_f1": 0.25935640469215876, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7622515551509633, "eval_holdout_nemotron_pii_strict_f1": 0.7458786936236392, "eval_holdout_open_pii_masking_500k_strict_f1": 0.6987882285054818, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.6460019743336624, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 37950 }, { "epoch": 4.927338782924614, "grad_norm": 0.0007336424314416945, "learning_rate": 2.4969646455248975e-05, "loss": 3.692074213176966e-05, "step": 37975 }, { "epoch": 4.930582587258336, "grad_norm": 0.0009516449645161629, "learning_rate": 2.493802822770833e-05, "loss": 3.264190396293998e-05, "step": 38000 }, { "epoch": 4.933826391592059, "grad_norm": 0.0008411401067860425, "learning_rate": 2.4906410099294328e-05, "loss": 3.6902432329952715e-05, "step": 38025 }, { "epoch": 4.937070195925782, "grad_norm": 0.0005434856284409761, "learning_rate": 2.48747921205816e-05, "loss": 3.196479054167867e-05, "step": 38050 }, { "epoch": 4.940314000259504, "grad_norm": 0.0007919002091512084, "learning_rate": 2.4843174342144527e-05, "loss": 3.54078272357583e-05, "step": 38075 }, { "epoch": 4.943557804593227, "grad_norm": 0.0006806162418797612, "learning_rate": 2.481155681455718e-05, "loss": 3.7157433107495306e-05, "step": 38100 }, { "epoch": 4.9468016089269495, "grad_norm": 0.0012368635507300496, "learning_rate": 2.477993958839321e-05, "loss": 3.6225933581590655e-05, "step": 38125 }, { "epoch": 4.950045413260672, "grad_norm": 0.0005686442018486559, "learning_rate": 2.4748322714225806e-05, "loss": 2.9319827444851398e-05, "step": 38150 }, { "epoch": 4.953289217594395, "grad_norm": 0.0008208067156374454, "learning_rate": 2.4716706242627587e-05, "loss": 3.544721752405167e-05, "step": 38175 }, { "epoch": 4.956533021928117, "grad_norm": 0.000628229056019336, "learning_rate": 2.468509022417053e-05, "loss": 3.0432981438934804e-05, "step": 38200 }, { "epoch": 4.95977682626184, "grad_norm": 0.00043095170985907316, "learning_rate": 2.465347470942587e-05, "loss": 3.1566263642162086e-05, "step": 38225 }, { "epoch": 4.963020630595563, "grad_norm": 0.0004111073212698102, "learning_rate": 2.462185974896407e-05, "loss": 3.527242224663496e-05, "step": 38250 }, { "epoch": 4.966264434929285, "grad_norm": 0.0013627948937937617, "learning_rate": 2.4590245393354667e-05, "loss": 3.679891116917133e-05, "step": 38275 }, { "epoch": 4.969508239263008, "grad_norm": 0.0014606284676119685, "learning_rate": 2.4558631693166265e-05, "loss": 3.631780156865716e-05, "step": 38300 }, { "epoch": 4.9727520435967305, "grad_norm": 0.0009779700776562095, "learning_rate": 2.4527018698966397e-05, "loss": 3.286857157945633e-05, "step": 38325 }, { "epoch": 4.975995847930453, "grad_norm": 0.0010756009723991156, "learning_rate": 2.4495406461321478e-05, "loss": 3.5770991817116735e-05, "step": 38350 }, { "epoch": 4.979239652264176, "grad_norm": 0.0005085722077637911, "learning_rate": 2.4463795030796706e-05, "loss": 4.003158770501613e-05, "step": 38375 }, { "epoch": 4.982483456597898, "grad_norm": 0.0008947788737714291, "learning_rate": 2.4432184457956e-05, "loss": 3.6009070463478565e-05, "step": 38400 }, { "epoch": 4.98572726093162, "grad_norm": 0.0009265370317734778, "learning_rate": 2.4400574793361884e-05, "loss": 3.7950112018734215e-05, "step": 38425 }, { "epoch": 4.988971065265343, "grad_norm": 0.0009381886338815093, "learning_rate": 2.436896608757546e-05, "loss": 3.534083487465978e-05, "step": 38450 }, { "epoch": 4.992214869599065, "grad_norm": 0.0013656043447554111, "learning_rate": 2.433735839115627e-05, "loss": 3.881210926920175e-05, "step": 38475 }, { "epoch": 4.995458673932788, "grad_norm": 0.0023738103918731213, "learning_rate": 2.4305751754662256e-05, "loss": 3.9926059544086455e-05, "step": 38500 }, { "epoch": 4.998702478266511, "grad_norm": 0.0005564165767282248, "learning_rate": 2.4274146228649657e-05, "loss": 3.7359155248850585e-05, "step": 38525 }, { "epoch": 5.001946282600233, "grad_norm": 0.0011174085084348917, "learning_rate": 2.4242541863672943e-05, "loss": 3.898711409419775e-05, "step": 38550 }, { "epoch": 5.005190086933956, "grad_norm": 0.00027771375607699156, "learning_rate": 2.421093871028472e-05, "loss": 4.036671947687864e-05, "step": 38575 }, { "epoch": 5.0084338912676785, "grad_norm": 0.0011072272900491953, "learning_rate": 2.4179336819035658e-05, "loss": 3.8915090262889864e-05, "step": 38600 }, { "epoch": 5.011677695601401, "grad_norm": 0.0006293128826655447, "learning_rate": 2.414773624047441e-05, "loss": 3.493772121146321e-05, "step": 38625 }, { "epoch": 5.014921499935124, "grad_norm": 0.0005594551330432296, "learning_rate": 2.411613702514753e-05, "loss": 3.461454296484589e-05, "step": 38650 }, { "epoch": 5.018165304268846, "grad_norm": 0.0012060876470059156, "learning_rate": 2.4084539223599384e-05, "loss": 4.012612625956535e-05, "step": 38675 }, { "epoch": 5.021409108602569, "grad_norm": 0.0017512954073026776, "learning_rate": 2.405294288637209e-05, "loss": 3.012987785041332e-05, "step": 38700 }, { "epoch": 5.024652912936292, "grad_norm": 0.0020989610347896814, "learning_rate": 2.4021348064005412e-05, "loss": 3.549520391970873e-05, "step": 38725 }, { "epoch": 5.027896717270014, "grad_norm": 0.0004239692643750459, "learning_rate": 2.3989754807036698e-05, "loss": 3.6704502999782566e-05, "step": 38750 }, { "epoch": 5.031140521603737, "grad_norm": 0.00028746563475579023, "learning_rate": 2.3958163166000788e-05, "loss": 3.3190641552209854e-05, "step": 38775 }, { "epoch": 5.034384325937459, "grad_norm": 0.0005334346788004041, "learning_rate": 2.3926573191429936e-05, "loss": 3.42881609685719e-05, "step": 38800 }, { "epoch": 5.037628130271182, "grad_norm": 0.000834273116197437, "learning_rate": 2.3894984933853733e-05, "loss": 3.7415665574371814e-05, "step": 38825 }, { "epoch": 5.040871934604905, "grad_norm": 0.0008046645671129227, "learning_rate": 2.386339844379903e-05, "loss": 3.573982277885079e-05, "step": 38850 }, { "epoch": 5.044115738938627, "grad_norm": 0.0005773119046352804, "learning_rate": 2.383181377178984e-05, "loss": 3.486335510388017e-05, "step": 38875 }, { "epoch": 5.04735954327235, "grad_norm": 0.0011473337654024363, "learning_rate": 2.3800230968347268e-05, "loss": 3.4210954327136277e-05, "step": 38900 }, { "epoch": 5.0506033476060725, "grad_norm": 0.000454535213066265, "learning_rate": 2.3768650083989434e-05, "loss": 3.537123091518879e-05, "step": 38925 }, { "epoch": 5.053847151939795, "grad_norm": 0.0005149758071638644, "learning_rate": 2.3737071169231393e-05, "loss": 3.667290089651942e-05, "step": 38950 }, { "epoch": 5.057090956273518, "grad_norm": 0.001077947672456503, "learning_rate": 2.3705494274585034e-05, "loss": 3.690620418637991e-05, "step": 38975 }, { "epoch": 5.06033476060724, "grad_norm": 0.0008131286012940109, "learning_rate": 2.3673919450559043e-05, "loss": 3.82863194681704e-05, "step": 39000 }, { "epoch": 5.063578564940963, "grad_norm": 0.001513584633357823, "learning_rate": 2.364234674765877e-05, "loss": 3.5062967799603936e-05, "step": 39025 }, { "epoch": 5.066822369274686, "grad_norm": 0.0013216988882049918, "learning_rate": 2.3610776216386176e-05, "loss": 3.551670582965016e-05, "step": 39050 }, { "epoch": 5.070066173608408, "grad_norm": 0.000439887517131865, "learning_rate": 2.3579207907239756e-05, "loss": 2.917287638410926e-05, "step": 39075 }, { "epoch": 5.073309977942131, "grad_norm": 0.0005394738982431591, "learning_rate": 2.354764187071444e-05, "loss": 3.766768146306276e-05, "step": 39100 }, { "epoch": 5.0765537822758535, "grad_norm": 0.0005945770535618067, "learning_rate": 2.3516078157301536e-05, "loss": 3.788141766563058e-05, "step": 39125 }, { "epoch": 5.079797586609576, "grad_norm": 0.0007794775301590562, "learning_rate": 2.3484516817488623e-05, "loss": 3.262016689404845e-05, "step": 39150 }, { "epoch": 5.083041390943298, "grad_norm": 0.0006156744202598929, "learning_rate": 2.3452957901759488e-05, "loss": 3.3945092000067233e-05, "step": 39175 }, { "epoch": 5.0862851952770205, "grad_norm": 0.00035493256291374564, "learning_rate": 2.342140146059405e-05, "loss": 3.531168447807431e-05, "step": 39200 }, { "epoch": 5.089528999610743, "grad_norm": 0.0011472372571006417, "learning_rate": 2.338984754446825e-05, "loss": 3.3657015301287174e-05, "step": 39225 }, { "epoch": 5.092772803944466, "grad_norm": 0.0007865283405408263, "learning_rate": 2.3358296203854012e-05, "loss": 3.186973510310054e-05, "step": 39250 }, { "epoch": 5.096016608278188, "grad_norm": 0.0006774862413294613, "learning_rate": 2.3326747489219125e-05, "loss": 3.727457718923688e-05, "step": 39275 }, { "epoch": 5.099260412611911, "grad_norm": 0.00045590687659569085, "learning_rate": 2.3295201451027185e-05, "loss": 3.228567074984312e-05, "step": 39300 }, { "epoch": 5.102504216945634, "grad_norm": 0.00047398469178006053, "learning_rate": 2.3263658139737503e-05, "loss": 3.275995841249824e-05, "step": 39325 }, { "epoch": 5.105748021279356, "grad_norm": 0.0010455676820129156, "learning_rate": 2.3232117605805025e-05, "loss": 3.800575155764818e-05, "step": 39350 }, { "epoch": 5.108991825613079, "grad_norm": 0.001014607958495617, "learning_rate": 2.320057989968027e-05, "loss": 3.679883433505893e-05, "step": 39375 }, { "epoch": 5.1122356299468015, "grad_norm": 0.0007133743492886424, "learning_rate": 2.3169045071809215e-05, "loss": 3.84627329185605e-05, "step": 39400 }, { "epoch": 5.115479434280524, "grad_norm": 0.0009869997156783938, "learning_rate": 2.3137513172633242e-05, "loss": 3.5960150416940454e-05, "step": 39425 }, { "epoch": 5.118723238614247, "grad_norm": 0.0005499795661307871, "learning_rate": 2.3105984252589048e-05, "loss": 3.6994474940001964e-05, "step": 39450 }, { "epoch": 5.121967042947969, "grad_norm": 0.0007318228599615395, "learning_rate": 2.3074458362108566e-05, "loss": 3.802223596721888e-05, "step": 39475 }, { "epoch": 5.125210847281692, "grad_norm": 0.0011927468003705144, "learning_rate": 2.304293555161888e-05, "loss": 3.376345383003354e-05, "step": 39500 }, { "epoch": 5.128454651615415, "grad_norm": 0.0006394406664185226, "learning_rate": 2.3011415871542143e-05, "loss": 3.57970199547708e-05, "step": 39525 }, { "epoch": 5.131698455949137, "grad_norm": 0.0013338228454813361, "learning_rate": 2.297989937229552e-05, "loss": 3.932836465537548e-05, "step": 39550 }, { "epoch": 5.13494226028286, "grad_norm": 0.00036305550020188093, "learning_rate": 2.2948386104291068e-05, "loss": 4.078434780240059e-05, "step": 39575 }, { "epoch": 5.1381860646165824, "grad_norm": 0.0005979565321467817, "learning_rate": 2.291687611793568e-05, "loss": 3.356846049427986e-05, "step": 39600 }, { "epoch": 5.141429868950305, "grad_norm": 0.00042727863183245063, "learning_rate": 2.2885369463631e-05, "loss": 3.9827940054237845e-05, "step": 39625 }, { "epoch": 5.144673673284028, "grad_norm": 0.0008573044324293733, "learning_rate": 2.285386619177335e-05, "loss": 3.771298099309206e-05, "step": 39650 }, { "epoch": 5.14791747761775, "grad_norm": 0.001125094830058515, "learning_rate": 2.2822366352753638e-05, "loss": 3.616074100136757e-05, "step": 39675 }, { "epoch": 5.151161281951473, "grad_norm": 0.0005142796435393393, "learning_rate": 2.279086999695727e-05, "loss": 3.1558810733258724e-05, "step": 39700 }, { "epoch": 5.154405086285196, "grad_norm": 0.0004248359764460474, "learning_rate": 2.2759377174764095e-05, "loss": 3.627287223935127e-05, "step": 39725 }, { "epoch": 5.157648890618918, "grad_norm": 0.0008018579101189971, "learning_rate": 2.2727887936548298e-05, "loss": 3.0095193069428204e-05, "step": 39750 }, { "epoch": 5.160892694952641, "grad_norm": 0.0006705617415718734, "learning_rate": 2.2696402332678347e-05, "loss": 4.129357170313597e-05, "step": 39775 }, { "epoch": 5.164136499286363, "grad_norm": 0.0018878512782976031, "learning_rate": 2.266492041351688e-05, "loss": 3.6284299567341806e-05, "step": 39800 }, { "epoch": 5.167380303620086, "grad_norm": 0.0009589095134288073, "learning_rate": 2.263344222942065e-05, "loss": 3.6503158044070004e-05, "step": 39825 }, { "epoch": 5.170624107953808, "grad_norm": 0.0013336640549823642, "learning_rate": 2.2601967830740436e-05, "loss": 3.6746952682733534e-05, "step": 39850 }, { "epoch": 5.17386791228753, "grad_norm": 0.0005441991961561143, "learning_rate": 2.2570497267820958e-05, "loss": 3.0102957971394062e-05, "step": 39875 }, { "epoch": 5.177111716621253, "grad_norm": 0.0003540418401826173, "learning_rate": 2.2539030591000804e-05, "loss": 3.669253550469875e-05, "step": 39900 }, { "epoch": 5.180355520954976, "grad_norm": 0.00039597717113792896, "learning_rate": 2.250756785061234e-05, "loss": 3.165107220411301e-05, "step": 39925 }, { "epoch": 5.183599325288698, "grad_norm": 0.00041181265260092914, "learning_rate": 2.2476109096981645e-05, "loss": 3.234543604776263e-05, "step": 39950 }, { "epoch": 5.186843129622421, "grad_norm": 0.000465402496047318, "learning_rate": 2.2444654380428412e-05, "loss": 3.164597786962986e-05, "step": 39975 }, { "epoch": 5.1900869339561435, "grad_norm": 0.0007209201576188207, "learning_rate": 2.2413203751265883e-05, "loss": 3.0564579647034406e-05, "step": 40000 }, { "epoch": 5.193330738289866, "grad_norm": 0.0004392920236568898, "learning_rate": 2.238175725980076e-05, "loss": 3.528837813064456e-05, "step": 40025 }, { "epoch": 5.196574542623589, "grad_norm": 0.0004988521104678512, "learning_rate": 2.2350314956333117e-05, "loss": 3.356021130457521e-05, "step": 40050 }, { "epoch": 5.199818346957311, "grad_norm": 0.0006691695307381451, "learning_rate": 2.2318876891156356e-05, "loss": 3.542667254805565e-05, "step": 40075 }, { "epoch": 5.203062151291034, "grad_norm": 0.0007078124326653779, "learning_rate": 2.2287443114557066e-05, "loss": 3.861297387629747e-05, "step": 40100 }, { "epoch": 5.206305955624757, "grad_norm": 0.0007065761601552367, "learning_rate": 2.2256013676815002e-05, "loss": 2.9668023344129325e-05, "step": 40125 }, { "epoch": 5.209549759958479, "grad_norm": 0.0008651968673802912, "learning_rate": 2.2224588628202962e-05, "loss": 3.578677773475647e-05, "step": 40150 }, { "epoch": 5.212793564292202, "grad_norm": 0.001273816218599677, "learning_rate": 2.2193168018986733e-05, "loss": 3.625702112913132e-05, "step": 40175 }, { "epoch": 5.2160373686259245, "grad_norm": 0.0004998835502192378, "learning_rate": 2.2161751899425002e-05, "loss": 3.43891279771924e-05, "step": 40200 }, { "epoch": 5.219281172959647, "grad_norm": 0.0003223626408725977, "learning_rate": 2.2130340319769263e-05, "loss": 3.391265869140625e-05, "step": 40225 }, { "epoch": 5.22252497729337, "grad_norm": 0.000611421128269285, "learning_rate": 2.2098933330263763e-05, "loss": 4.262352827936411e-05, "step": 40250 }, { "epoch": 5.225768781627092, "grad_norm": 0.0009712225873954594, "learning_rate": 2.2067530981145395e-05, "loss": 3.332823514938354e-05, "step": 40275 }, { "epoch": 5.229012585960815, "grad_norm": 0.001119474065490067, "learning_rate": 2.2036133322643636e-05, "loss": 3.539574565365911e-05, "step": 40300 }, { "epoch": 5.232256390294538, "grad_norm": 0.0008194440160878003, "learning_rate": 2.2004740404980458e-05, "loss": 3.92886670306325e-05, "step": 40325 }, { "epoch": 5.23550019462826, "grad_norm": 0.001205066335387528, "learning_rate": 2.197335227837025e-05, "loss": 3.121045418083668e-05, "step": 40350 }, { "epoch": 5.238743998961983, "grad_norm": 0.0009045677725225687, "learning_rate": 2.1941968993019743e-05, "loss": 3.547331551089883e-05, "step": 40375 }, { "epoch": 5.2419878032957055, "grad_norm": 0.0010481550125405192, "learning_rate": 2.1910590599127914e-05, "loss": 3.80846718326211e-05, "step": 40400 }, { "epoch": 5.245231607629428, "grad_norm": 0.00032702117459848523, "learning_rate": 2.1879217146885923e-05, "loss": 3.6054588854312896e-05, "step": 40425 }, { "epoch": 5.248475411963151, "grad_norm": 0.0003583450161386281, "learning_rate": 2.1847848686477024e-05, "loss": 3.836564254015684e-05, "step": 40450 }, { "epoch": 5.251719216296873, "grad_norm": 0.0008335181046277285, "learning_rate": 2.1816485268076478e-05, "loss": 3.775698831304908e-05, "step": 40475 }, { "epoch": 5.254963020630596, "grad_norm": 0.0008788928389549255, "learning_rate": 2.1785126941851496e-05, "loss": 3.0141838360577823e-05, "step": 40500 }, { "epoch": 5.258206824964319, "grad_norm": 0.0008917336235754192, "learning_rate": 2.175377375796114e-05, "loss": 3.5633393563330176e-05, "step": 40525 }, { "epoch": 5.261450629298041, "grad_norm": 0.0007224097498692572, "learning_rate": 2.1722425766556234e-05, "loss": 3.7833114620298145e-05, "step": 40550 }, { "epoch": 5.264694433631763, "grad_norm": 0.00169628974981606, "learning_rate": 2.1691083017779313e-05, "loss": 4.089570604264736e-05, "step": 40575 }, { "epoch": 5.2679382379654855, "grad_norm": 0.0006219330825842917, "learning_rate": 2.1659745561764517e-05, "loss": 3.544875886291266e-05, "step": 40600 }, { "epoch": 5.271182042299208, "grad_norm": 0.001994143472984433, "learning_rate": 2.1628413448637523e-05, "loss": 3.686951939016581e-05, "step": 40625 }, { "epoch": 5.274425846632931, "grad_norm": 0.001044769654981792, "learning_rate": 2.1597086728515456e-05, "loss": 4.340538755059242e-05, "step": 40650 }, { "epoch": 5.277669650966653, "grad_norm": 0.0005074161454103887, "learning_rate": 2.1565765451506827e-05, "loss": 3.790276125073433e-05, "step": 40675 }, { "epoch": 5.280913455300376, "grad_norm": 0.00029255743720568717, "learning_rate": 2.1534449667711426e-05, "loss": 3.7999812047928574e-05, "step": 40700 }, { "epoch": 5.284157259634099, "grad_norm": 0.0006138301105238497, "learning_rate": 2.1503139427220265e-05, "loss": 3.784730797633529e-05, "step": 40725 }, { "epoch": 5.287401063967821, "grad_norm": 0.0010414443677291274, "learning_rate": 2.147183478011549e-05, "loss": 3.542397636920214e-05, "step": 40750 }, { "epoch": 5.290644868301544, "grad_norm": 0.00040520113543607295, "learning_rate": 2.1440535776470297e-05, "loss": 3.57150798663497e-05, "step": 40775 }, { "epoch": 5.2938886726352665, "grad_norm": 0.0006216389592736959, "learning_rate": 2.1409242466348856e-05, "loss": 3.6789895966649054e-05, "step": 40800 }, { "epoch": 5.297132476968989, "grad_norm": 0.0010347212664783, "learning_rate": 2.1377954899806226e-05, "loss": 4.201638512313366e-05, "step": 40825 }, { "epoch": 5.300376281302712, "grad_norm": 0.0011249822564423084, "learning_rate": 2.1346673126888283e-05, "loss": 3.415676997974515e-05, "step": 40850 }, { "epoch": 5.303620085636434, "grad_norm": 0.0006840202840976417, "learning_rate": 2.1315397197631636e-05, "loss": 3.507858840748668e-05, "step": 40875 }, { "epoch": 5.306863889970157, "grad_norm": 0.0005911306361667812, "learning_rate": 2.1284127162063545e-05, "loss": 3.622143995016813e-05, "step": 40900 }, { "epoch": 5.31010769430388, "grad_norm": 0.0005923482240177691, "learning_rate": 2.125286307020185e-05, "loss": 3.875668859109282e-05, "step": 40925 }, { "epoch": 5.313351498637602, "grad_norm": 0.0007045479724183679, "learning_rate": 2.1221604972054876e-05, "loss": 3.522270359098911e-05, "step": 40950 }, { "epoch": 5.316595302971325, "grad_norm": 0.0003560212498996407, "learning_rate": 2.1190352917621358e-05, "loss": 3.251039888709784e-05, "step": 40975 }, { "epoch": 5.3198391073050475, "grad_norm": 0.0007896185852587223, "learning_rate": 2.1159106956890368e-05, "loss": 3.0399714596569538e-05, "step": 41000 }, { "epoch": 5.32308291163877, "grad_norm": 0.0006807523313909769, "learning_rate": 2.1127867139841234e-05, "loss": 3.12235695309937e-05, "step": 41025 }, { "epoch": 5.326326715972493, "grad_norm": 0.0008569970377720892, "learning_rate": 2.1096633516443456e-05, "loss": 3.596044844016433e-05, "step": 41050 }, { "epoch": 5.329570520306215, "grad_norm": 0.0015345194842666388, "learning_rate": 2.106540613665662e-05, "loss": 3.608013736084104e-05, "step": 41075 }, { "epoch": 5.332814324639938, "grad_norm": 0.0006165965460240841, "learning_rate": 2.1034185050430334e-05, "loss": 3.120830748230219e-05, "step": 41100 }, { "epoch": 5.336058128973661, "grad_norm": 0.0004883591900579631, "learning_rate": 2.1002970307704132e-05, "loss": 3.4955162554979324e-05, "step": 41125 }, { "epoch": 5.339301933307383, "grad_norm": 0.0012525917263701558, "learning_rate": 2.0971761958407403e-05, "loss": 3.785837441682816e-05, "step": 41150 }, { "epoch": 5.342545737641106, "grad_norm": 0.0010342559544369578, "learning_rate": 2.0940560052459317e-05, "loss": 3.4461412578821186e-05, "step": 41175 }, { "epoch": 5.3457895419748285, "grad_norm": 0.001385239651426673, "learning_rate": 2.090936463976873e-05, "loss": 3.7816727999597785e-05, "step": 41200 }, { "epoch": 5.34903334630855, "grad_norm": 0.0008575211395509541, "learning_rate": 2.087817577023411e-05, "loss": 3.2356732990592715e-05, "step": 41225 }, { "epoch": 5.352277150642273, "grad_norm": 0.0009425346506759524, "learning_rate": 2.084699349374346e-05, "loss": 3.106700954958797e-05, "step": 41250 }, { "epoch": 5.3555209549759955, "grad_norm": 0.0008362224325537682, "learning_rate": 2.0815817860174248e-05, "loss": 3.617254784330726e-05, "step": 41275 }, { "epoch": 5.358764759309718, "grad_norm": 0.0003468517679721117, "learning_rate": 2.0784648919393297e-05, "loss": 3.6440412513911725e-05, "step": 41300 }, { "epoch": 5.362008563643441, "grad_norm": 0.0010122782550752163, "learning_rate": 2.0753486721256746e-05, "loss": 2.9611079953610896e-05, "step": 41325 }, { "epoch": 5.365252367977163, "grad_norm": 0.0008508769096806645, "learning_rate": 2.072233131560993e-05, "loss": 3.527132794260979e-05, "step": 41350 }, { "epoch": 5.368496172310886, "grad_norm": 0.0005464851856231689, "learning_rate": 2.069118275228733e-05, "loss": 3.2099394593387844e-05, "step": 41375 }, { "epoch": 5.371739976644609, "grad_norm": 0.0005711254780180752, "learning_rate": 2.066004108111248e-05, "loss": 3.304804675281048e-05, "step": 41400 }, { "epoch": 5.371739976644609, "eval_loss": 0.00017630154616199434, "eval_runtime": 6.4964, "eval_samples_per_second": 769.662, "eval_steps_per_second": 6.157, "step": 41400 }, { "epoch": 5.371739976644609, "eval_holdout_avg_strict_f1": 0.27389753863534344, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7677942752181234, "eval_holdout_nemotron_pii_strict_f1": 0.8157583937911254, "eval_holdout_open_pii_masking_500k_strict_f1": 0.7216734456711215, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.7076468103084074, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 41400 }, { "epoch": 5.374983780978331, "grad_norm": 0.0003447926719672978, "learning_rate": 2.0628906351897888e-05, "loss": 3.171050688251853e-05, "step": 41425 }, { "epoch": 5.378227585312054, "grad_norm": 0.0003155374724883586, "learning_rate": 2.0597778614444955e-05, "loss": 3.607511986047029e-05, "step": 41450 }, { "epoch": 5.381471389645776, "grad_norm": 0.0010399599559605122, "learning_rate": 2.056665791854391e-05, "loss": 3.7603375967592e-05, "step": 41475 }, { "epoch": 5.384715193979499, "grad_norm": 0.0007962668314576149, "learning_rate": 2.053554431397371e-05, "loss": 3.42640932649374e-05, "step": 41500 }, { "epoch": 5.387958998313222, "grad_norm": 0.00046274266787804663, "learning_rate": 2.050443785050197e-05, "loss": 2.986235311254859e-05, "step": 41525 }, { "epoch": 5.391202802646944, "grad_norm": 0.0013692715438082814, "learning_rate": 2.0473338577884884e-05, "loss": 3.787472378462553e-05, "step": 41550 }, { "epoch": 5.394446606980667, "grad_norm": 0.0005168935167603195, "learning_rate": 2.044224654586714e-05, "loss": 3.50738107226789e-05, "step": 41575 }, { "epoch": 5.3976904113143895, "grad_norm": 0.000507035234477371, "learning_rate": 2.0411161804181844e-05, "loss": 3.248632652685046e-05, "step": 41600 }, { "epoch": 5.400934215648112, "grad_norm": 0.0014494856586679816, "learning_rate": 2.0380084402550454e-05, "loss": 3.3133686520159246e-05, "step": 41625 }, { "epoch": 5.404178019981835, "grad_norm": 0.0008606257033534348, "learning_rate": 2.0349014390682667e-05, "loss": 3.456233767792582e-05, "step": 41650 }, { "epoch": 5.407421824315557, "grad_norm": 0.0035244033206254244, "learning_rate": 2.0317951818276372e-05, "loss": 3.900798037648201e-05, "step": 41675 }, { "epoch": 5.41066562864928, "grad_norm": 0.000787843600846827, "learning_rate": 2.0286896735017563e-05, "loss": 3.584078745916486e-05, "step": 41700 }, { "epoch": 5.413909432983003, "grad_norm": 0.0011109032202512026, "learning_rate": 2.025584919058024e-05, "loss": 2.8612841852009297e-05, "step": 41725 }, { "epoch": 5.417153237316725, "grad_norm": 0.0018584902863949537, "learning_rate": 2.022480923462636e-05, "loss": 3.6484347656369206e-05, "step": 41750 }, { "epoch": 5.420397041650448, "grad_norm": 0.0003295684582553804, "learning_rate": 2.019377691680572e-05, "loss": 3.93568305298686e-05, "step": 41775 }, { "epoch": 5.4236408459841705, "grad_norm": 0.0007339833537116647, "learning_rate": 2.016275228675593e-05, "loss": 3.6586727946996686e-05, "step": 41800 }, { "epoch": 5.426884650317893, "grad_norm": 0.0006379656842909753, "learning_rate": 2.0131735394102284e-05, "loss": 3.22925322689116e-05, "step": 41825 }, { "epoch": 5.430128454651616, "grad_norm": 0.0008012205944396555, "learning_rate": 2.010072628845769e-05, "loss": 3.497367026284337e-05, "step": 41850 }, { "epoch": 5.433372258985338, "grad_norm": 0.0010278543923050165, "learning_rate": 2.0069725019422625e-05, "loss": 3.792500123381615e-05, "step": 41875 }, { "epoch": 5.436616063319061, "grad_norm": 0.00032442581141367555, "learning_rate": 2.0038731636585016e-05, "loss": 3.840473713353276e-05, "step": 41900 }, { "epoch": 5.439859867652784, "grad_norm": 0.0010624043643474579, "learning_rate": 2.000774618952017e-05, "loss": 4.0880865417420867e-05, "step": 41925 }, { "epoch": 5.443103671986506, "grad_norm": 0.0006429856875911355, "learning_rate": 1.9976768727790723e-05, "loss": 3.466059686616063e-05, "step": 41950 }, { "epoch": 5.446347476320228, "grad_norm": 0.00034211084130220115, "learning_rate": 1.994579930094652e-05, "loss": 3.487125039100647e-05, "step": 41975 }, { "epoch": 5.449591280653951, "grad_norm": 0.000793265993706882, "learning_rate": 1.9914837958524546e-05, "loss": 3.795626573264599e-05, "step": 42000 }, { "epoch": 5.452835084987673, "grad_norm": 0.0008763002115301788, "learning_rate": 1.9883884750048875e-05, "loss": 3.91480652615428e-05, "step": 42025 }, { "epoch": 5.456078889321396, "grad_norm": 0.001021828269585967, "learning_rate": 1.985293972503056e-05, "loss": 3.5806249361485246e-05, "step": 42050 }, { "epoch": 5.4593226936551185, "grad_norm": 0.000777697074227035, "learning_rate": 1.982200293296757e-05, "loss": 3.134052734822035e-05, "step": 42075 }, { "epoch": 5.462566497988841, "grad_norm": 0.00031042585032992065, "learning_rate": 1.9791074423344695e-05, "loss": 3.357605310156941e-05, "step": 42100 }, { "epoch": 5.465810302322564, "grad_norm": 0.0009199327905662358, "learning_rate": 1.9760154245633485e-05, "loss": 3.438829444348812e-05, "step": 42125 }, { "epoch": 5.469054106656286, "grad_norm": 0.0007298655109480023, "learning_rate": 1.9729242449292163e-05, "loss": 3.961754031479359e-05, "step": 42150 }, { "epoch": 5.472297910990009, "grad_norm": 0.0002720272168517113, "learning_rate": 1.969833908376554e-05, "loss": 3.0849976465106014e-05, "step": 42175 }, { "epoch": 5.475541715323732, "grad_norm": 0.0013830031966790557, "learning_rate": 1.966744419848494e-05, "loss": 3.514885436743498e-05, "step": 42200 }, { "epoch": 5.478785519657454, "grad_norm": 0.0006746058934368193, "learning_rate": 1.963655784286814e-05, "loss": 3.1070515979081394e-05, "step": 42225 }, { "epoch": 5.482029323991177, "grad_norm": 0.00048766445252113044, "learning_rate": 1.9605680066319247e-05, "loss": 3.45993391238153e-05, "step": 42250 }, { "epoch": 5.485273128324899, "grad_norm": 0.0007253969670273364, "learning_rate": 1.9574810918228667e-05, "loss": 3.6262196954339745e-05, "step": 42275 }, { "epoch": 5.488516932658622, "grad_norm": 0.0007532121380791068, "learning_rate": 1.954395044797299e-05, "loss": 4.1428147815167906e-05, "step": 42300 }, { "epoch": 5.491760736992345, "grad_norm": 0.0003363989235367626, "learning_rate": 1.951309870491494e-05, "loss": 3.080271417275071e-05, "step": 42325 }, { "epoch": 5.495004541326067, "grad_norm": 0.0005035257781855762, "learning_rate": 1.9482255738403264e-05, "loss": 3.849953180179e-05, "step": 42350 }, { "epoch": 5.49824834565979, "grad_norm": 0.0006614447920583189, "learning_rate": 1.945142159777269e-05, "loss": 3.274504328146577e-05, "step": 42375 }, { "epoch": 5.5014921499935125, "grad_norm": 0.0005344692035578191, "learning_rate": 1.942059633234381e-05, "loss": 3.3483500592410566e-05, "step": 42400 }, { "epoch": 5.504735954327235, "grad_norm": 0.0007481445209123194, "learning_rate": 1.938977999142303e-05, "loss": 3.191194497048855e-05, "step": 42425 }, { "epoch": 5.507979758660958, "grad_norm": 0.000592496246099472, "learning_rate": 1.9358972624302478e-05, "loss": 2.964415354654193e-05, "step": 42450 }, { "epoch": 5.51122356299468, "grad_norm": 0.0009682731470093131, "learning_rate": 1.9328174280259937e-05, "loss": 3.322131698951125e-05, "step": 42475 }, { "epoch": 5.514467367328403, "grad_norm": 0.0009263160172849894, "learning_rate": 1.9297385008558734e-05, "loss": 3.263577353209257e-05, "step": 42500 }, { "epoch": 5.517711171662126, "grad_norm": 0.0008814931497909129, "learning_rate": 1.9266604858447713e-05, "loss": 3.560051089152694e-05, "step": 42525 }, { "epoch": 5.520954975995848, "grad_norm": 0.0004746408376377076, "learning_rate": 1.9235833879161103e-05, "loss": 3.901608288288116e-05, "step": 42550 }, { "epoch": 5.524198780329571, "grad_norm": 0.0010288344928994775, "learning_rate": 1.9205072119918483e-05, "loss": 3.2903011888265606e-05, "step": 42575 }, { "epoch": 5.527442584663293, "grad_norm": 0.00099998211953789, "learning_rate": 1.9174319629924677e-05, "loss": 3.5559027455747124e-05, "step": 42600 }, { "epoch": 5.530686388997015, "grad_norm": 0.001140299835242331, "learning_rate": 1.914357645836967e-05, "loss": 3.6098873242735865e-05, "step": 42625 }, { "epoch": 5.533930193330738, "grad_norm": 0.0009257998317480087, "learning_rate": 1.9112842654428564e-05, "loss": 3.301772056147456e-05, "step": 42650 }, { "epoch": 5.5371739976644605, "grad_norm": 0.0008400730439461768, "learning_rate": 1.908211826726146e-05, "loss": 3.6845034919679165e-05, "step": 42675 }, { "epoch": 5.540417801998183, "grad_norm": 0.000979163683950901, "learning_rate": 1.9051403346013406e-05, "loss": 4.062208812683821e-05, "step": 42700 }, { "epoch": 5.543661606331906, "grad_norm": 0.0009712688042782247, "learning_rate": 1.9020697939814308e-05, "loss": 3.867189167067409e-05, "step": 42725 }, { "epoch": 5.546905410665628, "grad_norm": 0.0006910244701430202, "learning_rate": 1.8990002097778846e-05, "loss": 3.363564144819975e-05, "step": 42750 }, { "epoch": 5.550149214999351, "grad_norm": 0.0005086984019726515, "learning_rate": 1.8959315869006406e-05, "loss": 3.1981857027858495e-05, "step": 42775 }, { "epoch": 5.553393019333074, "grad_norm": 0.00036166716017760336, "learning_rate": 1.8928639302580993e-05, "loss": 3.1276959925889966e-05, "step": 42800 }, { "epoch": 5.556636823666796, "grad_norm": 0.001310638734139502, "learning_rate": 1.8897972447571167e-05, "loss": 4.5279408805072305e-05, "step": 42825 }, { "epoch": 5.559880628000519, "grad_norm": 0.0009923514444380999, "learning_rate": 1.8867315353029935e-05, "loss": 3.408446907997131e-05, "step": 42850 }, { "epoch": 5.5631244323342415, "grad_norm": 0.002106586005538702, "learning_rate": 1.883666806799472e-05, "loss": 3.742799162864685e-05, "step": 42875 }, { "epoch": 5.566368236667964, "grad_norm": 0.0013417864684015512, "learning_rate": 1.880603064148723e-05, "loss": 4.020377062261105e-05, "step": 42900 }, { "epoch": 5.569612041001687, "grad_norm": 0.0009282378014177084, "learning_rate": 1.8775403122513417e-05, "loss": 3.903612261638045e-05, "step": 42925 }, { "epoch": 5.572855845335409, "grad_norm": 0.0008536592358723283, "learning_rate": 1.874478556006337e-05, "loss": 3.3002090640366076e-05, "step": 42950 }, { "epoch": 5.576099649669132, "grad_norm": 0.0018817938398569822, "learning_rate": 1.871417800311128e-05, "loss": 3.421848872676492e-05, "step": 42975 }, { "epoch": 5.579343454002855, "grad_norm": 0.0012047310592606664, "learning_rate": 1.8683580500615293e-05, "loss": 3.5081584937870505e-05, "step": 43000 }, { "epoch": 5.582587258336577, "grad_norm": 0.0010378746083006263, "learning_rate": 1.865299310151752e-05, "loss": 3.210710594430566e-05, "step": 43025 }, { "epoch": 5.5858310626703, "grad_norm": 0.0007468964322470129, "learning_rate": 1.862241585474387e-05, "loss": 3.428138326853514e-05, "step": 43050 }, { "epoch": 5.5890748670040225, "grad_norm": 0.0004456656170077622, "learning_rate": 1.859184880920403e-05, "loss": 3.5493955947458745e-05, "step": 43075 }, { "epoch": 5.592318671337745, "grad_norm": 0.0018055331893265247, "learning_rate": 1.8561292013791386e-05, "loss": 3.265962237492204e-05, "step": 43100 }, { "epoch": 5.595562475671468, "grad_norm": 0.0007904988015070558, "learning_rate": 1.8530745517382898e-05, "loss": 2.959674224257469e-05, "step": 43125 }, { "epoch": 5.59880628000519, "grad_norm": 0.0005005915882065892, "learning_rate": 1.8500209368839068e-05, "loss": 3.370829625055194e-05, "step": 43150 }, { "epoch": 5.602050084338913, "grad_norm": 0.0006189539562910795, "learning_rate": 1.8469683617003844e-05, "loss": 3.0167580116540195e-05, "step": 43175 }, { "epoch": 5.605293888672636, "grad_norm": 0.000640127866063267, "learning_rate": 1.8439168310704547e-05, "loss": 3.189460374414921e-05, "step": 43200 }, { "epoch": 5.608537693006358, "grad_norm": 0.00029737348086200655, "learning_rate": 1.8408663498751787e-05, "loss": 3.2326674554497006e-05, "step": 43225 }, { "epoch": 5.611781497340081, "grad_norm": 0.0011306910309940577, "learning_rate": 1.837816922993939e-05, "loss": 3.597356379032135e-05, "step": 43250 }, { "epoch": 5.615025301673803, "grad_norm": 0.0009017206029966474, "learning_rate": 1.8347685553044314e-05, "loss": 3.2497330103069544e-05, "step": 43275 }, { "epoch": 5.618269106007526, "grad_norm": 0.0012536051217466593, "learning_rate": 1.8317212516826576e-05, "loss": 4.117356147617102e-05, "step": 43300 }, { "epoch": 5.621512910341249, "grad_norm": 0.0008136740070767701, "learning_rate": 1.8286750170029175e-05, "loss": 3.830726258456707e-05, "step": 43325 }, { "epoch": 5.624756714674971, "grad_norm": 0.002603736938908696, "learning_rate": 1.8256298561378006e-05, "loss": 3.546147374436259e-05, "step": 43350 }, { "epoch": 5.628000519008693, "grad_norm": 0.0007220706320367754, "learning_rate": 1.8225857739581793e-05, "loss": 3.4566831309348346e-05, "step": 43375 }, { "epoch": 5.631244323342416, "grad_norm": 0.0008333612349815667, "learning_rate": 1.8195427753332007e-05, "loss": 3.354140091687441e-05, "step": 43400 }, { "epoch": 5.634488127676138, "grad_norm": 0.0002411217865301296, "learning_rate": 1.8165008651302788e-05, "loss": 3.590764477849007e-05, "step": 43425 }, { "epoch": 5.637731932009861, "grad_norm": 0.0007234059739857912, "learning_rate": 1.8134600482150863e-05, "loss": 3.391143633052707e-05, "step": 43450 }, { "epoch": 5.6409757363435835, "grad_norm": 0.0007020625052973628, "learning_rate": 1.8104203294515463e-05, "loss": 3.309016115963459e-05, "step": 43475 }, { "epoch": 5.644219540677306, "grad_norm": 0.0014542859280481935, "learning_rate": 1.8073817137018275e-05, "loss": 3.4324661828577516e-05, "step": 43500 }, { "epoch": 5.647463345011029, "grad_norm": 0.0008912260527722538, "learning_rate": 1.8043442058263333e-05, "loss": 2.9500594828277825e-05, "step": 43525 }, { "epoch": 5.650707149344751, "grad_norm": 0.0007156787905842066, "learning_rate": 1.801307810683692e-05, "loss": 3.207592060789466e-05, "step": 43550 }, { "epoch": 5.653950953678474, "grad_norm": 0.0007577273063361645, "learning_rate": 1.798272533130757e-05, "loss": 3.4522206988185644e-05, "step": 43575 }, { "epoch": 5.657194758012197, "grad_norm": 0.0009578069439157844, "learning_rate": 1.7952383780225915e-05, "loss": 3.284200327470898e-05, "step": 43600 }, { "epoch": 5.660438562345919, "grad_norm": 0.0012657666811719537, "learning_rate": 1.792205350212463e-05, "loss": 3.522145096212626e-05, "step": 43625 }, { "epoch": 5.663682366679642, "grad_norm": 0.0019580030348151922, "learning_rate": 1.789173454551837e-05, "loss": 3.477544290944934e-05, "step": 43650 }, { "epoch": 5.6669261710133645, "grad_norm": 0.001219601253978908, "learning_rate": 1.786142695890367e-05, "loss": 3.38741741143167e-05, "step": 43675 }, { "epoch": 5.670169975347087, "grad_norm": 0.0005745863891206682, "learning_rate": 1.7831130790758882e-05, "loss": 3.1842950265854595e-05, "step": 43700 }, { "epoch": 5.67341377968081, "grad_norm": 0.0009125495562329888, "learning_rate": 1.7800846089544105e-05, "loss": 3.364956937730312e-05, "step": 43725 }, { "epoch": 5.676657584014532, "grad_norm": 0.0011430213926360011, "learning_rate": 1.7770572903701083e-05, "loss": 3.637634450569749e-05, "step": 43750 }, { "epoch": 5.679901388348255, "grad_norm": 0.000300808809697628, "learning_rate": 1.774031128165314e-05, "loss": 3.7516341544687746e-05, "step": 43775 }, { "epoch": 5.683145192681978, "grad_norm": 0.0008132244111038744, "learning_rate": 1.7710061271805106e-05, "loss": 3.551581175997853e-05, "step": 43800 }, { "epoch": 5.6863889970157, "grad_norm": 0.001522608450613916, "learning_rate": 1.7679822922543237e-05, "loss": 3.5753054544329646e-05, "step": 43825 }, { "epoch": 5.689632801349423, "grad_norm": 0.0006548297242261469, "learning_rate": 1.764959628223515e-05, "loss": 3.43604595400393e-05, "step": 43850 }, { "epoch": 5.6928766056831455, "grad_norm": 0.0023479964584112167, "learning_rate": 1.7619381399229702e-05, "loss": 3.56587627902627e-05, "step": 43875 }, { "epoch": 5.696120410016868, "grad_norm": 0.0005983021692372859, "learning_rate": 1.758917832185698e-05, "loss": 3.260161262005567e-05, "step": 43900 }, { "epoch": 5.699364214350591, "grad_norm": 0.0006758114323019981, "learning_rate": 1.755898709842816e-05, "loss": 3.403231967240572e-05, "step": 43925 }, { "epoch": 5.702608018684313, "grad_norm": 0.000569262367207557, "learning_rate": 1.7528807777235467e-05, "loss": 3.103907452896237e-05, "step": 43950 }, { "epoch": 5.705851823018035, "grad_norm": 0.001122274436056614, "learning_rate": 1.7498640406552093e-05, "loss": 3.0203028582036496e-05, "step": 43975 }, { "epoch": 5.709095627351758, "grad_norm": 0.0007168201263993979, "learning_rate": 1.7468485034632107e-05, "loss": 3.024468896910548e-05, "step": 44000 }, { "epoch": 5.71233943168548, "grad_norm": 0.0007423022761940956, "learning_rate": 1.7438341709710388e-05, "loss": 3.701714333146811e-05, "step": 44025 }, { "epoch": 5.715583236019203, "grad_norm": 0.0009292782633565366, "learning_rate": 1.7408210480002547e-05, "loss": 3.118921536952257e-05, "step": 44050 }, { "epoch": 5.7188270403529256, "grad_norm": 0.00045964852324686944, "learning_rate": 1.737809139370484e-05, "loss": 3.862307174131274e-05, "step": 44075 }, { "epoch": 5.722070844686648, "grad_norm": 0.0008330807322636247, "learning_rate": 1.734798449899412e-05, "loss": 3.78507049754262e-05, "step": 44100 }, { "epoch": 5.725314649020371, "grad_norm": 0.0011455132625997066, "learning_rate": 1.7317889844027707e-05, "loss": 3.725441638380289e-05, "step": 44125 }, { "epoch": 5.728558453354093, "grad_norm": 0.0011840220540761948, "learning_rate": 1.728780747694337e-05, "loss": 3.826684318482876e-05, "step": 44150 }, { "epoch": 5.731802257687816, "grad_norm": 0.00035759026650339365, "learning_rate": 1.7257737445859214e-05, "loss": 4.0943073108792306e-05, "step": 44175 }, { "epoch": 5.735046062021539, "grad_norm": 0.0011836397461593151, "learning_rate": 1.7227679798873612e-05, "loss": 3.7250998429954054e-05, "step": 44200 }, { "epoch": 5.738289866355261, "grad_norm": 0.000907732464838773, "learning_rate": 1.7197634584065117e-05, "loss": 3.6307566333562135e-05, "step": 44225 }, { "epoch": 5.741533670688984, "grad_norm": 0.0005703204078599811, "learning_rate": 1.716760184949242e-05, "loss": 3.5108770243823526e-05, "step": 44250 }, { "epoch": 5.7447774750227065, "grad_norm": 0.0013771287631243467, "learning_rate": 1.7137581643194233e-05, "loss": 3.3447430469095706e-05, "step": 44275 }, { "epoch": 5.748021279356429, "grad_norm": 0.0006393163348548114, "learning_rate": 1.7107574013189225e-05, "loss": 3.762681968510151e-05, "step": 44300 }, { "epoch": 5.751265083690152, "grad_norm": 0.0009807593887671828, "learning_rate": 1.7077579007475967e-05, "loss": 3.643144853413105e-05, "step": 44325 }, { "epoch": 5.754508888023874, "grad_norm": 0.000368144508684054, "learning_rate": 1.7047596674032812e-05, "loss": 3.543465165421367e-05, "step": 44350 }, { "epoch": 5.757752692357597, "grad_norm": 0.0006687345448881388, "learning_rate": 1.7017627060817865e-05, "loss": 3.34339402616024e-05, "step": 44375 }, { "epoch": 5.76099649669132, "grad_norm": 0.0006457180134020746, "learning_rate": 1.698767021576887e-05, "loss": 3.613668726757169e-05, "step": 44400 }, { "epoch": 5.764240301025042, "grad_norm": 0.0011989366030320525, "learning_rate": 1.695772618680316e-05, "loss": 3.657035296782851e-05, "step": 44425 }, { "epoch": 5.767484105358765, "grad_norm": 0.0011120324488729239, "learning_rate": 1.6927795021817557e-05, "loss": 3.683137008920312e-05, "step": 44450 }, { "epoch": 5.7707279096924875, "grad_norm": 0.0002983024751301855, "learning_rate": 1.6897876768688306e-05, "loss": 2.727555576711893e-05, "step": 44475 }, { "epoch": 5.77397171402621, "grad_norm": 0.0003894299443345517, "learning_rate": 1.6867971475271013e-05, "loss": 3.6816888023167846e-05, "step": 44500 }, { "epoch": 5.777215518359933, "grad_norm": 0.001185109606012702, "learning_rate": 1.683807918940054e-05, "loss": 3.2908269204199315e-05, "step": 44525 }, { "epoch": 5.780459322693655, "grad_norm": 0.0021734843030571938, "learning_rate": 1.6808199958890953e-05, "loss": 3.4093703143298625e-05, "step": 44550 }, { "epoch": 5.783703127027378, "grad_norm": 0.0014617459382861853, "learning_rate": 1.677833383153542e-05, "loss": 3.422403940930963e-05, "step": 44575 }, { "epoch": 5.786946931361101, "grad_norm": 0.0007793279364705086, "learning_rate": 1.6748480855106173e-05, "loss": 3.475864883512259e-05, "step": 44600 }, { "epoch": 5.790190735694823, "grad_norm": 0.0007358041475526989, "learning_rate": 1.6718641077354384e-05, "loss": 3.0824036803096535e-05, "step": 44625 }, { "epoch": 5.793434540028546, "grad_norm": 0.0004450454143807292, "learning_rate": 1.6688814546010133e-05, "loss": 3.131725825369358e-05, "step": 44650 }, { "epoch": 5.7966783443622685, "grad_norm": 0.0009489704971201718, "learning_rate": 1.6659001308782304e-05, "loss": 3.608612343668938e-05, "step": 44675 }, { "epoch": 5.799922148695991, "grad_norm": 0.000541912391781807, "learning_rate": 1.6629201413358515e-05, "loss": 3.6489765625447036e-05, "step": 44700 }, { "epoch": 5.803165953029714, "grad_norm": 0.0011107847094535828, "learning_rate": 1.6599414907405035e-05, "loss": 3.829463152214885e-05, "step": 44725 }, { "epoch": 5.8064097573634355, "grad_norm": 0.0007204223074950278, "learning_rate": 1.656964183856674e-05, "loss": 3.402756061404944e-05, "step": 44750 }, { "epoch": 5.809653561697158, "grad_norm": 0.001135558821260929, "learning_rate": 1.653988225446698e-05, "loss": 3.181448671966791e-05, "step": 44775 }, { "epoch": 5.812897366030881, "grad_norm": 0.0008803303353488445, "learning_rate": 1.6510136202707576e-05, "loss": 3.657634137198329e-05, "step": 44800 }, { "epoch": 5.816141170364603, "grad_norm": 0.0003098087036050856, "learning_rate": 1.6480403730868664e-05, "loss": 3.794696880504489e-05, "step": 44825 }, { "epoch": 5.819384974698326, "grad_norm": 0.0002971770882140845, "learning_rate": 1.6450684886508682e-05, "loss": 3.218784229829908e-05, "step": 44850 }, { "epoch": 5.819384974698326, "eval_loss": 0.00017269652744289488, "eval_runtime": 6.6723, "eval_samples_per_second": 749.372, "eval_steps_per_second": 5.995, "step": 44850 }, { "epoch": 5.819384974698326, "eval_holdout_avg_strict_f1": 0.24360180832285555, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.5871857258718572, "eval_holdout_nemotron_pii_strict_f1": 0.7445714724161744, "eval_holdout_open_pii_masking_500k_strict_f1": 0.6801233529576675, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.667739340305712, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 44850 }, { "epoch": 5.822628779032049, "grad_norm": 0.0005650305538438261, "learning_rate": 1.6420979717164263e-05, "loss": 3.231115406379104e-05, "step": 44875 }, { "epoch": 5.825872583365771, "grad_norm": 0.0016982100205495954, "learning_rate": 1.639128827035017e-05, "loss": 3.281958401203156e-05, "step": 44900 }, { "epoch": 5.829116387699494, "grad_norm": 0.001262062112800777, "learning_rate": 1.6361610593559205e-05, "loss": 2.7833005879074336e-05, "step": 44925 }, { "epoch": 5.832360192033216, "grad_norm": 0.0010602573165670037, "learning_rate": 1.6331946734262153e-05, "loss": 3.0317208729684352e-05, "step": 44950 }, { "epoch": 5.835603996366939, "grad_norm": 0.0004804774362128228, "learning_rate": 1.630229673990771e-05, "loss": 3.5996059887111186e-05, "step": 44975 }, { "epoch": 5.838847800700662, "grad_norm": 0.0007923576631583273, "learning_rate": 1.627266065792236e-05, "loss": 3.808297449722886e-05, "step": 45000 }, { "epoch": 5.842091605034384, "grad_norm": 0.0010291525395587087, "learning_rate": 1.6243038535710366e-05, "loss": 3.5210971254855395e-05, "step": 45025 }, { "epoch": 5.845335409368107, "grad_norm": 0.0018452517688274384, "learning_rate": 1.621343042065365e-05, "loss": 3.378171473741531e-05, "step": 45050 }, { "epoch": 5.8485792137018295, "grad_norm": 0.001037756446748972, "learning_rate": 1.6183836360111732e-05, "loss": 3.7244597915560004e-05, "step": 45075 }, { "epoch": 5.851823018035552, "grad_norm": 0.000662600330542773, "learning_rate": 1.6154256401421638e-05, "loss": 3.777044359594584e-05, "step": 45100 }, { "epoch": 5.855066822369275, "grad_norm": 0.0007359360461123288, "learning_rate": 1.6124690591897856e-05, "loss": 3.465160261839628e-05, "step": 45125 }, { "epoch": 5.858310626702997, "grad_norm": 0.00038835773011669517, "learning_rate": 1.6095138978832224e-05, "loss": 3.217269666492939e-05, "step": 45150 }, { "epoch": 5.86155443103672, "grad_norm": 0.0008764363010413945, "learning_rate": 1.6065601609493897e-05, "loss": 3.870492335408926e-05, "step": 45175 }, { "epoch": 5.864798235370443, "grad_norm": 0.000527910073287785, "learning_rate": 1.6036078531129218e-05, "loss": 3.513500792905688e-05, "step": 45200 }, { "epoch": 5.868042039704165, "grad_norm": 0.0004249147605150938, "learning_rate": 1.6006569790961686e-05, "loss": 3.152108518406749e-05, "step": 45225 }, { "epoch": 5.871285844037888, "grad_norm": 0.0004717546689789742, "learning_rate": 1.5977075436191866e-05, "loss": 4.131568595767021e-05, "step": 45250 }, { "epoch": 5.8745296483716105, "grad_norm": 0.000815700797829777, "learning_rate": 1.594759551399731e-05, "loss": 3.5693817771971225e-05, "step": 45275 }, { "epoch": 5.877773452705333, "grad_norm": 0.00047599695972166955, "learning_rate": 1.5918130071532483e-05, "loss": 3.238001139834523e-05, "step": 45300 }, { "epoch": 5.881017257039056, "grad_norm": 0.0005944319418631494, "learning_rate": 1.5888679155928694e-05, "loss": 3.251458518207073e-05, "step": 45325 }, { "epoch": 5.884261061372778, "grad_norm": 0.0007618462550453842, "learning_rate": 1.5859242814294013e-05, "loss": 3.184906207025051e-05, "step": 45350 }, { "epoch": 5.8875048657065, "grad_norm": 0.0018432227661833167, "learning_rate": 1.5829821093713187e-05, "loss": 3.480345010757446e-05, "step": 45375 }, { "epoch": 5.890748670040223, "grad_norm": 0.0007652795175090432, "learning_rate": 1.58004140412476e-05, "loss": 2.8768894262611867e-05, "step": 45400 }, { "epoch": 5.893992474373945, "grad_norm": 0.000382307858671993, "learning_rate": 1.5771021703935156e-05, "loss": 3.7980189081281427e-05, "step": 45425 }, { "epoch": 5.897236278707668, "grad_norm": 0.0010898476466536522, "learning_rate": 1.5741644128790223e-05, "loss": 3.459723899140954e-05, "step": 45450 }, { "epoch": 5.900480083041391, "grad_norm": 0.0005142231239005923, "learning_rate": 1.571228136280356e-05, "loss": 3.220941172912717e-05, "step": 45475 }, { "epoch": 5.903723887375113, "grad_norm": 0.0013309153728187084, "learning_rate": 1.5682933452942238e-05, "loss": 3.462026594206691e-05, "step": 45500 }, { "epoch": 5.906967691708836, "grad_norm": 0.0017370145069435239, "learning_rate": 1.5653600446149562e-05, "loss": 3.835540264844895e-05, "step": 45525 }, { "epoch": 5.9102114960425585, "grad_norm": 0.0038244782481342554, "learning_rate": 1.5624282389345002e-05, "loss": 3.6551000084728004e-05, "step": 45550 }, { "epoch": 5.913455300376281, "grad_norm": 0.0006413344526663423, "learning_rate": 1.5594979329424115e-05, "loss": 3.1448560766875746e-05, "step": 45575 }, { "epoch": 5.916699104710004, "grad_norm": 0.0009520295425318182, "learning_rate": 1.5565691313258467e-05, "loss": 3.369493409991265e-05, "step": 45600 }, { "epoch": 5.919942909043726, "grad_norm": 0.0011243218323215842, "learning_rate": 1.553641838769556e-05, "loss": 3.5142465494573114e-05, "step": 45625 }, { "epoch": 5.923186713377449, "grad_norm": 0.0011861774837598205, "learning_rate": 1.5507160599558767e-05, "loss": 3.3344095572829244e-05, "step": 45650 }, { "epoch": 5.926430517711172, "grad_norm": 0.001267214654944837, "learning_rate": 1.547791799564724e-05, "loss": 3.485758788883686e-05, "step": 45675 }, { "epoch": 5.929674322044894, "grad_norm": 0.0005917752278037369, "learning_rate": 1.544869062273584e-05, "loss": 3.6499400157481434e-05, "step": 45700 }, { "epoch": 5.932918126378617, "grad_norm": 0.00128300697542727, "learning_rate": 1.5419478527575068e-05, "loss": 3.858827752992511e-05, "step": 45725 }, { "epoch": 5.936161930712339, "grad_norm": 0.0005879078526049852, "learning_rate": 1.5390281756890995e-05, "loss": 3.244355088099837e-05, "step": 45750 }, { "epoch": 5.939405735046062, "grad_norm": 0.0004470401327125728, "learning_rate": 1.5361100357385174e-05, "loss": 3.628800623118877e-05, "step": 45775 }, { "epoch": 5.942649539379785, "grad_norm": 0.0007120918016880751, "learning_rate": 1.533193437573457e-05, "loss": 3.3827286679297685e-05, "step": 45800 }, { "epoch": 5.945893343713507, "grad_norm": 0.0007360204472206533, "learning_rate": 1.530278385859148e-05, "loss": 3.7734196521341804e-05, "step": 45825 }, { "epoch": 5.94913714804723, "grad_norm": 0.0009063103352673352, "learning_rate": 1.5273648852583483e-05, "loss": 3.809068584814668e-05, "step": 45850 }, { "epoch": 5.9523809523809526, "grad_norm": 0.0008287334349006414, "learning_rate": 1.5244529404313334e-05, "loss": 3.5677959676831964e-05, "step": 45875 }, { "epoch": 5.955624756714675, "grad_norm": 0.0008198232972063124, "learning_rate": 1.5215425560358904e-05, "loss": 3.9064944721758366e-05, "step": 45900 }, { "epoch": 5.958868561048398, "grad_norm": 0.0013911109417676926, "learning_rate": 1.5186337367273105e-05, "loss": 3.432693891227245e-05, "step": 45925 }, { "epoch": 5.96211236538212, "grad_norm": 0.0009716664208099246, "learning_rate": 1.5157264871583816e-05, "loss": 3.191046416759491e-05, "step": 45950 }, { "epoch": 5.965356169715843, "grad_norm": 0.000951513007748872, "learning_rate": 1.5128208119793805e-05, "loss": 2.8861556202173234e-05, "step": 45975 }, { "epoch": 5.968599974049566, "grad_norm": 0.0009489060030318797, "learning_rate": 1.509916715838066e-05, "loss": 3.757012076675892e-05, "step": 46000 }, { "epoch": 5.971843778383288, "grad_norm": 0.001566333812661469, "learning_rate": 1.5070142033796714e-05, "loss": 3.012740518897772e-05, "step": 46025 }, { "epoch": 5.975087582717011, "grad_norm": 0.001427917741239071, "learning_rate": 1.504113279246896e-05, "loss": 3.863052697852254e-05, "step": 46050 }, { "epoch": 5.9783313870507335, "grad_norm": 0.0011537569807842374, "learning_rate": 1.5012139480798987e-05, "loss": 3.803008468821645e-05, "step": 46075 }, { "epoch": 5.981575191384456, "grad_norm": 0.0007726160110905766, "learning_rate": 1.4983162145162911e-05, "loss": 3.0990862287580965e-05, "step": 46100 }, { "epoch": 5.984818995718179, "grad_norm": 0.0005740344058722258, "learning_rate": 1.4954200831911286e-05, "loss": 3.851939458400011e-05, "step": 46125 }, { "epoch": 5.9880628000519005, "grad_norm": 0.0008155530667863786, "learning_rate": 1.4925255587369035e-05, "loss": 3.236535005271435e-05, "step": 46150 }, { "epoch": 5.991306604385623, "grad_norm": 0.00035951321478933096, "learning_rate": 1.4896326457835397e-05, "loss": 2.9391401913017035e-05, "step": 46175 }, { "epoch": 5.994550408719346, "grad_norm": 0.000635889417026192, "learning_rate": 1.4867413489583815e-05, "loss": 3.717451589182019e-05, "step": 46200 }, { "epoch": 5.997794213053068, "grad_norm": 0.0014487823937088251, "learning_rate": 1.4838516728861884e-05, "loss": 3.512491704896092e-05, "step": 46225 }, { "epoch": 6.001038017386791, "grad_norm": 0.000466677185613662, "learning_rate": 1.480963622189128e-05, "loss": 3.236630000174046e-05, "step": 46250 }, { "epoch": 6.004281821720514, "grad_norm": 0.0008806605474092066, "learning_rate": 1.4780772014867677e-05, "loss": 3.394711297005415e-05, "step": 46275 }, { "epoch": 6.007525626054236, "grad_norm": 0.0004290637152735144, "learning_rate": 1.475192415396068e-05, "loss": 3.550802357494831e-05, "step": 46300 }, { "epoch": 6.010769430387959, "grad_norm": 0.001193337026052177, "learning_rate": 1.4723092685313744e-05, "loss": 3.35747143253684e-05, "step": 46325 }, { "epoch": 6.0140132347216815, "grad_norm": 0.001257724012248218, "learning_rate": 1.4694277655044103e-05, "loss": 2.9976502992212774e-05, "step": 46350 }, { "epoch": 6.017257039055404, "grad_norm": 0.0015596778830513358, "learning_rate": 1.4665479109242696e-05, "loss": 3.591163549572229e-05, "step": 46375 }, { "epoch": 6.020500843389127, "grad_norm": 0.0003701039240695536, "learning_rate": 1.4636697093974108e-05, "loss": 3.0851224437355995e-05, "step": 46400 }, { "epoch": 6.023744647722849, "grad_norm": 0.00038183334982022643, "learning_rate": 1.4607931655276463e-05, "loss": 3.17784957587719e-05, "step": 46425 }, { "epoch": 6.026988452056572, "grad_norm": 0.0005719358450733125, "learning_rate": 1.4579182839161379e-05, "loss": 3.638681024312973e-05, "step": 46450 }, { "epoch": 6.030232256390295, "grad_norm": 0.0006942269974388182, "learning_rate": 1.4550450691613898e-05, "loss": 3.245818195864558e-05, "step": 46475 }, { "epoch": 6.033476060724017, "grad_norm": 0.00039803230902180076, "learning_rate": 1.4521735258592365e-05, "loss": 2.771601779386401e-05, "step": 46500 }, { "epoch": 6.03671986505774, "grad_norm": 0.0007030270644463599, "learning_rate": 1.4493036586028435e-05, "loss": 2.7555897831916807e-05, "step": 46525 }, { "epoch": 6.0399636693914625, "grad_norm": 0.00043949190876446664, "learning_rate": 1.446435471982691e-05, "loss": 3.129759104922414e-05, "step": 46550 }, { "epoch": 6.043207473725185, "grad_norm": 0.0006810384220443666, "learning_rate": 1.4435689705865751e-05, "loss": 3.428698517382145e-05, "step": 46575 }, { "epoch": 6.046451278058908, "grad_norm": 0.0011600630823522806, "learning_rate": 1.4407041589995924e-05, "loss": 3.1168048735708e-05, "step": 46600 }, { "epoch": 6.04969508239263, "grad_norm": 0.0014279145980253816, "learning_rate": 1.437841041804141e-05, "loss": 3.2299065496772526e-05, "step": 46625 }, { "epoch": 6.052938886726353, "grad_norm": 0.001775419688783586, "learning_rate": 1.434979623579902e-05, "loss": 3.628251375630498e-05, "step": 46650 }, { "epoch": 6.056182691060076, "grad_norm": 0.00085779360961169, "learning_rate": 1.4321199089038467e-05, "loss": 3.428159281611443e-05, "step": 46675 }, { "epoch": 6.059426495393798, "grad_norm": 0.0005448206211440265, "learning_rate": 1.4292619023502152e-05, "loss": 3.095287131145597e-05, "step": 46700 }, { "epoch": 6.062670299727521, "grad_norm": 0.0010302771115675569, "learning_rate": 1.4264056084905203e-05, "loss": 3.147097304463386e-05, "step": 46725 }, { "epoch": 6.065914104061243, "grad_norm": 0.0005972165381535888, "learning_rate": 1.4235510318935311e-05, "loss": 3.1322943978011606e-05, "step": 46750 }, { "epoch": 6.069157908394966, "grad_norm": 0.0009796064114198089, "learning_rate": 1.4206981771252726e-05, "loss": 3.5204105079174044e-05, "step": 46775 }, { "epoch": 6.072401712728688, "grad_norm": 0.0007404080242849886, "learning_rate": 1.417847048749016e-05, "loss": 3.298030002042651e-05, "step": 46800 }, { "epoch": 6.07564551706241, "grad_norm": 0.0009542989428155124, "learning_rate": 1.4149976513252677e-05, "loss": 3.2983210403472185e-05, "step": 46825 }, { "epoch": 6.078889321396133, "grad_norm": 0.0006964030908420682, "learning_rate": 1.4121499894117695e-05, "loss": 2.8705373406410217e-05, "step": 46850 }, { "epoch": 6.082133125729856, "grad_norm": 0.0004948629066348076, "learning_rate": 1.4093040675634832e-05, "loss": 3.448543371632695e-05, "step": 46875 }, { "epoch": 6.085376930063578, "grad_norm": 0.0005246940418146551, "learning_rate": 1.406459890332592e-05, "loss": 2.9877719935029746e-05, "step": 46900 }, { "epoch": 6.088620734397301, "grad_norm": 0.0005641674506478012, "learning_rate": 1.4036174622684828e-05, "loss": 3.2586690504103897e-05, "step": 46925 }, { "epoch": 6.0918645387310235, "grad_norm": 0.0009122518822550774, "learning_rate": 1.4007767879177502e-05, "loss": 3.292194800451398e-05, "step": 46950 }, { "epoch": 6.095108343064746, "grad_norm": 0.0006746149156242609, "learning_rate": 1.3979378718241793e-05, "loss": 3.323203418403864e-05, "step": 46975 }, { "epoch": 6.098352147398469, "grad_norm": 0.0007972855819389224, "learning_rate": 1.3951007185287458e-05, "loss": 3.053450491279364e-05, "step": 47000 }, { "epoch": 6.101595951732191, "grad_norm": 0.0005279877805151045, "learning_rate": 1.3922653325696028e-05, "loss": 3.3134585246443747e-05, "step": 47025 }, { "epoch": 6.104839756065914, "grad_norm": 0.0006025381735526025, "learning_rate": 1.3894317184820807e-05, "loss": 3.189675509929657e-05, "step": 47050 }, { "epoch": 6.108083560399637, "grad_norm": 0.0005669245147146285, "learning_rate": 1.3865998807986707e-05, "loss": 3.4934410359710454e-05, "step": 47075 }, { "epoch": 6.111327364733359, "grad_norm": 0.0007629585452377796, "learning_rate": 1.3837698240490271e-05, "loss": 3.1008664518594745e-05, "step": 47100 }, { "epoch": 6.114571169067082, "grad_norm": 0.0011303108185529709, "learning_rate": 1.3809415527599518e-05, "loss": 3.664224874228239e-05, "step": 47125 }, { "epoch": 6.1178149734008045, "grad_norm": 0.000965476268902421, "learning_rate": 1.3781150714553936e-05, "loss": 3.37607366964221e-05, "step": 47150 }, { "epoch": 6.121058777734527, "grad_norm": 0.00045176816638559103, "learning_rate": 1.375290384656436e-05, "loss": 3.3416671212762596e-05, "step": 47175 }, { "epoch": 6.12430258206825, "grad_norm": 0.0009548590169288218, "learning_rate": 1.3724674968812946e-05, "loss": 3.009058302268386e-05, "step": 47200 }, { "epoch": 6.127546386401972, "grad_norm": 0.0012125027133151889, "learning_rate": 1.3696464126453035e-05, "loss": 3.3013233914971354e-05, "step": 47225 }, { "epoch": 6.130790190735695, "grad_norm": 0.0005806962726637721, "learning_rate": 1.3668271364609169e-05, "loss": 3.175693331286311e-05, "step": 47250 }, { "epoch": 6.134033995069418, "grad_norm": 0.0008557441760785878, "learning_rate": 1.3640096728376922e-05, "loss": 3.175299149006605e-05, "step": 47275 }, { "epoch": 6.13727779940314, "grad_norm": 0.0009762627887539566, "learning_rate": 1.3611940262822902e-05, "loss": 3.688215278089047e-05, "step": 47300 }, { "epoch": 6.140521603736863, "grad_norm": 0.0008632392273284495, "learning_rate": 1.358380201298467e-05, "loss": 3.351107705384493e-05, "step": 47325 }, { "epoch": 6.1437654080705855, "grad_norm": 0.0009192005381919444, "learning_rate": 1.3555682023870592e-05, "loss": 3.21381795220077e-05, "step": 47350 }, { "epoch": 6.147009212404308, "grad_norm": 0.0007463544025085866, "learning_rate": 1.3527580340459888e-05, "loss": 3.0925353057682515e-05, "step": 47375 }, { "epoch": 6.150253016738031, "grad_norm": 0.0004646479501388967, "learning_rate": 1.349949700770245e-05, "loss": 3.480815794318914e-05, "step": 47400 }, { "epoch": 6.153496821071753, "grad_norm": 0.0007695214590057731, "learning_rate": 1.3471432070518853e-05, "loss": 3.392907325178385e-05, "step": 47425 }, { "epoch": 6.156740625405476, "grad_norm": 0.0008760461350902915, "learning_rate": 1.3443385573800215e-05, "loss": 3.597337985411286e-05, "step": 47450 }, { "epoch": 6.159984429739199, "grad_norm": 0.0006573197897523642, "learning_rate": 1.341535756240819e-05, "loss": 3.51758673787117e-05, "step": 47475 }, { "epoch": 6.16322823407292, "grad_norm": 0.0009562613558955491, "learning_rate": 1.3387348081174833e-05, "loss": 3.547722939401865e-05, "step": 47500 }, { "epoch": 6.166472038406643, "grad_norm": 0.0008474667556583881, "learning_rate": 1.335935717490259e-05, "loss": 3.544654930010438e-05, "step": 47525 }, { "epoch": 6.1697158427403656, "grad_norm": 0.000476845889352262, "learning_rate": 1.3331384888364163e-05, "loss": 3.449972486123443e-05, "step": 47550 }, { "epoch": 6.172959647074088, "grad_norm": 0.0007508983253501356, "learning_rate": 1.3303431266302502e-05, "loss": 3.3022675197571515e-05, "step": 47575 }, { "epoch": 6.176203451407811, "grad_norm": 0.0007221046835184097, "learning_rate": 1.3275496353430671e-05, "loss": 3.0088925268501043e-05, "step": 47600 }, { "epoch": 6.179447255741533, "grad_norm": 0.0006469798390753567, "learning_rate": 1.3247580194431844e-05, "loss": 2.9589009936898947e-05, "step": 47625 }, { "epoch": 6.182691060075256, "grad_norm": 0.0005260767647996545, "learning_rate": 1.321968283395916e-05, "loss": 3.481176216155291e-05, "step": 47650 }, { "epoch": 6.185934864408979, "grad_norm": 0.0006878729327581823, "learning_rate": 1.3191804316635726e-05, "loss": 3.5235844552516935e-05, "step": 47675 }, { "epoch": 6.189178668742701, "grad_norm": 0.0006947733927518129, "learning_rate": 1.3163944687054463e-05, "loss": 3.4187689889222386e-05, "step": 47700 }, { "epoch": 6.192422473076424, "grad_norm": 0.0006754788337275386, "learning_rate": 1.3136103989778137e-05, "loss": 2.7757259085774423e-05, "step": 47725 }, { "epoch": 6.1956662774101465, "grad_norm": 0.00037221130332909524, "learning_rate": 1.3108282269339173e-05, "loss": 3.551849396899342e-05, "step": 47750 }, { "epoch": 6.198910081743869, "grad_norm": 0.0006897260900586843, "learning_rate": 1.308047957023969e-05, "loss": 2.8810633812099694e-05, "step": 47775 }, { "epoch": 6.202153886077592, "grad_norm": 0.0005391192389652133, "learning_rate": 1.3052695936951342e-05, "loss": 2.990865148603916e-05, "step": 47800 }, { "epoch": 6.205397690411314, "grad_norm": 0.0008229200029745698, "learning_rate": 1.3024931413915317e-05, "loss": 3.1493317801505325e-05, "step": 47825 }, { "epoch": 6.208641494745037, "grad_norm": 0.0005570146022364497, "learning_rate": 1.299718604554223e-05, "loss": 3.65044386126101e-05, "step": 47850 }, { "epoch": 6.21188529907876, "grad_norm": 0.000724551675375551, "learning_rate": 1.296945987621203e-05, "loss": 2.986515639349818e-05, "step": 47875 }, { "epoch": 6.215129103412482, "grad_norm": 0.00029484438709914684, "learning_rate": 1.2941752950274003e-05, "loss": 2.804826945066452e-05, "step": 47900 }, { "epoch": 6.218372907746205, "grad_norm": 0.0013117181370034814, "learning_rate": 1.2914065312046602e-05, "loss": 3.337288973852992e-05, "step": 47925 }, { "epoch": 6.2216167120799275, "grad_norm": 0.0006208893610164523, "learning_rate": 1.2886397005817474e-05, "loss": 3.438360523432493e-05, "step": 47950 }, { "epoch": 6.22486051641365, "grad_norm": 0.00040102002094499767, "learning_rate": 1.2858748075843307e-05, "loss": 3.365342505276203e-05, "step": 47975 }, { "epoch": 6.228104320747373, "grad_norm": 0.0006150325061753392, "learning_rate": 1.2831118566349834e-05, "loss": 3.628710051998496e-05, "step": 48000 }, { "epoch": 6.231348125081095, "grad_norm": 0.0007724507595412433, "learning_rate": 1.280350852153168e-05, "loss": 3.073385450989008e-05, "step": 48025 }, { "epoch": 6.234591929414818, "grad_norm": 0.0012440565042197704, "learning_rate": 1.277591798555238e-05, "loss": 3.431160701438785e-05, "step": 48050 }, { "epoch": 6.237835733748541, "grad_norm": 0.0014835803303867579, "learning_rate": 1.2748347002544219e-05, "loss": 3.335978137329221e-05, "step": 48075 }, { "epoch": 6.241079538082263, "grad_norm": 0.0007604006095789373, "learning_rate": 1.2720795616608256e-05, "loss": 3.170258831232786e-05, "step": 48100 }, { "epoch": 6.244323342415986, "grad_norm": 0.001386372372508049, "learning_rate": 1.2693263871814155e-05, "loss": 3.1279108952730894e-05, "step": 48125 }, { "epoch": 6.2475671467497085, "grad_norm": 0.0006077290745452046, "learning_rate": 1.2665751812200197e-05, "loss": 3.096666419878602e-05, "step": 48150 }, { "epoch": 6.25081095108343, "grad_norm": 0.0007948587299324572, "learning_rate": 1.2638259481773162e-05, "loss": 3.1897653825581075e-05, "step": 48175 }, { "epoch": 6.254054755417153, "grad_norm": 0.0011580775026232004, "learning_rate": 1.261078692450826e-05, "loss": 3.5365838557481765e-05, "step": 48200 }, { "epoch": 6.2572985597508755, "grad_norm": 0.0008148067281581461, "learning_rate": 1.2583334184349111e-05, "loss": 3.114370396360755e-05, "step": 48225 }, { "epoch": 6.260542364084598, "grad_norm": 0.0008683883352205157, "learning_rate": 1.255590130520759e-05, "loss": 2.9402787331491708e-05, "step": 48250 }, { "epoch": 6.263786168418321, "grad_norm": 0.0007982244133017957, "learning_rate": 1.2528488330963844e-05, "loss": 3.758278908208013e-05, "step": 48275 }, { "epoch": 6.267029972752043, "grad_norm": 0.0006112566916272044, "learning_rate": 1.2501095305466143e-05, "loss": 3.572792047634721e-05, "step": 48300 }, { "epoch": 6.267029972752043, "eval_loss": 0.00016492747818119824, "eval_runtime": 6.8532, "eval_samples_per_second": 729.587, "eval_steps_per_second": 5.837, "step": 48300 }, { "epoch": 6.267029972752043, "eval_holdout_avg_strict_f1": 0.2648946637146208, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.8075838295205264, "eval_holdout_nemotron_pii_strict_f1": 0.7539032307930128, "eval_holdout_open_pii_masking_500k_strict_f1": 0.6679420606723149, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.6844121798749748, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 48300 }, { "epoch": 6.270273777085766, "grad_norm": 0.000793366227298975, "learning_rate": 1.2473722272530893e-05, "loss": 3.326559904962778e-05, "step": 48325 }, { "epoch": 6.273517581419489, "grad_norm": 0.00039231940172612667, "learning_rate": 1.2446369275942474e-05, "loss": 3.273384878411889e-05, "step": 48350 }, { "epoch": 6.276761385753211, "grad_norm": 0.0011914424831047654, "learning_rate": 1.2419036359453257e-05, "loss": 3.2896334305405615e-05, "step": 48375 }, { "epoch": 6.280005190086934, "grad_norm": 0.00036132862442173064, "learning_rate": 1.2391723566783458e-05, "loss": 3.235634183511138e-05, "step": 48400 }, { "epoch": 6.283248994420656, "grad_norm": 0.0017029147129505873, "learning_rate": 1.2364430941621142e-05, "loss": 3.517436096444726e-05, "step": 48425 }, { "epoch": 6.286492798754379, "grad_norm": 0.00041788251837715507, "learning_rate": 1.2337158527622072e-05, "loss": 2.9858467169106006e-05, "step": 48450 }, { "epoch": 6.289736603088102, "grad_norm": 0.001329645048826933, "learning_rate": 1.2309906368409732e-05, "loss": 3.224387532100082e-05, "step": 48475 }, { "epoch": 6.292980407421824, "grad_norm": 0.0006018900312483311, "learning_rate": 1.2282674507575157e-05, "loss": 3.2408302649855615e-05, "step": 48500 }, { "epoch": 6.296224211755547, "grad_norm": 0.0007687225588597357, "learning_rate": 1.2255462988676959e-05, "loss": 3.4158907365053895e-05, "step": 48525 }, { "epoch": 6.2994680160892695, "grad_norm": 0.0007394814165309072, "learning_rate": 1.222827185524117e-05, "loss": 3.4373768139630554e-05, "step": 48550 }, { "epoch": 6.302711820422992, "grad_norm": 0.00058964011259377, "learning_rate": 1.2201101150761257e-05, "loss": 3.615105524659157e-05, "step": 48575 }, { "epoch": 6.305955624756715, "grad_norm": 0.0007642036071047187, "learning_rate": 1.2173950918697968e-05, "loss": 2.9972181655466555e-05, "step": 48600 }, { "epoch": 6.309199429090437, "grad_norm": 0.0007939196657389402, "learning_rate": 1.2146821202479348e-05, "loss": 3.062651725485921e-05, "step": 48625 }, { "epoch": 6.31244323342416, "grad_norm": 0.0008266252698376775, "learning_rate": 1.211971204550058e-05, "loss": 3.56217147782445e-05, "step": 48650 }, { "epoch": 6.315687037757883, "grad_norm": 0.000898878846783191, "learning_rate": 1.2092623491123994e-05, "loss": 3.289288375526666e-05, "step": 48675 }, { "epoch": 6.318930842091605, "grad_norm": 0.0009319267119280994, "learning_rate": 1.2065555582678969e-05, "loss": 3.1909679528325796e-05, "step": 48700 }, { "epoch": 6.322174646425328, "grad_norm": 0.0006444407626986504, "learning_rate": 1.2038508363461826e-05, "loss": 3.230354515835643e-05, "step": 48725 }, { "epoch": 6.3254184507590505, "grad_norm": 0.0006838018889538944, "learning_rate": 1.2011481876735831e-05, "loss": 3.478020895272493e-05, "step": 48750 }, { "epoch": 6.328662255092773, "grad_norm": 0.0005646591307595372, "learning_rate": 1.198447616573105e-05, "loss": 3.112643957138062e-05, "step": 48775 }, { "epoch": 6.331906059426496, "grad_norm": 0.0002795820764731616, "learning_rate": 1.1957491273644362e-05, "loss": 2.70323664881289e-05, "step": 48800 }, { "epoch": 6.335149863760218, "grad_norm": 0.0003791324270423502, "learning_rate": 1.1930527243639294e-05, "loss": 3.069079481065273e-05, "step": 48825 }, { "epoch": 6.338393668093941, "grad_norm": 0.0005632281536236405, "learning_rate": 1.1903584118846053e-05, "loss": 3.0912172514945266e-05, "step": 48850 }, { "epoch": 6.341637472427664, "grad_norm": 0.0011256136931478977, "learning_rate": 1.1876661942361363e-05, "loss": 3.456914331763983e-05, "step": 48875 }, { "epoch": 6.344881276761385, "grad_norm": 0.0006034586112946272, "learning_rate": 1.1849760757248482e-05, "loss": 3.100156085565686e-05, "step": 48900 }, { "epoch": 6.348125081095108, "grad_norm": 0.00042966645560227334, "learning_rate": 1.1822880606537051e-05, "loss": 3.16122267395258e-05, "step": 48925 }, { "epoch": 6.351368885428831, "grad_norm": 0.0023085144348442554, "learning_rate": 1.1796021533223101e-05, "loss": 3.076269989833236e-05, "step": 48950 }, { "epoch": 6.354612689762553, "grad_norm": 0.0004225082229822874, "learning_rate": 1.1769183580268917e-05, "loss": 3.26783349737525e-05, "step": 48975 }, { "epoch": 6.357856494096276, "grad_norm": 0.0012427469482645392, "learning_rate": 1.1742366790603033e-05, "loss": 2.9921371024101972e-05, "step": 49000 }, { "epoch": 6.3611002984299985, "grad_norm": 0.0021490000654011965, "learning_rate": 1.1715571207120097e-05, "loss": 3.3084163442254065e-05, "step": 49025 }, { "epoch": 6.364344102763721, "grad_norm": 0.001459784572944045, "learning_rate": 1.1688796872680874e-05, "loss": 3.408887190744281e-05, "step": 49050 }, { "epoch": 6.367587907097444, "grad_norm": 0.0009092218824662268, "learning_rate": 1.16620438301121e-05, "loss": 3.592707449570298e-05, "step": 49075 }, { "epoch": 6.370831711431166, "grad_norm": 0.0016672448255121708, "learning_rate": 1.1635312122206496e-05, "loss": 3.523331601172686e-05, "step": 49100 }, { "epoch": 6.374075515764889, "grad_norm": 0.0004084856773260981, "learning_rate": 1.1608601791722614e-05, "loss": 3.441400127485395e-05, "step": 49125 }, { "epoch": 6.377319320098612, "grad_norm": 0.0003406385949347168, "learning_rate": 1.158191288138486e-05, "loss": 3.258585464209318e-05, "step": 49150 }, { "epoch": 6.380563124432334, "grad_norm": 0.001275703078135848, "learning_rate": 1.1555245433883322e-05, "loss": 3.70823685079813e-05, "step": 49175 }, { "epoch": 6.383806928766057, "grad_norm": 0.0008233269909396768, "learning_rate": 1.1528599491873812e-05, "loss": 3.351493738591671e-05, "step": 49200 }, { "epoch": 6.387050733099779, "grad_norm": 0.0004646510351449251, "learning_rate": 1.1501975097977696e-05, "loss": 2.8680290561169387e-05, "step": 49225 }, { "epoch": 6.390294537433502, "grad_norm": 0.000564984162338078, "learning_rate": 1.1475372294781905e-05, "loss": 3.232806688174605e-05, "step": 49250 }, { "epoch": 6.393538341767225, "grad_norm": 0.00042036533704958856, "learning_rate": 1.1448791124838834e-05, "loss": 3.072394523769617e-05, "step": 49275 }, { "epoch": 6.396782146100947, "grad_norm": 0.0006687360000796616, "learning_rate": 1.1422231630666243e-05, "loss": 3.6256592720746995e-05, "step": 49300 }, { "epoch": 6.40002595043467, "grad_norm": 0.0006560826441273093, "learning_rate": 1.1395693854747263e-05, "loss": 3.04907513782382e-05, "step": 49325 }, { "epoch": 6.4032697547683926, "grad_norm": 0.00048376127961091697, "learning_rate": 1.1369177839530248e-05, "loss": 2.953343093395233e-05, "step": 49350 }, { "epoch": 6.406513559102115, "grad_norm": 0.00044781118049286306, "learning_rate": 1.1342683627428777e-05, "loss": 3.253550967201591e-05, "step": 49375 }, { "epoch": 6.409757363435838, "grad_norm": 0.0007373791886493564, "learning_rate": 1.131621126082152e-05, "loss": 3.26714082621038e-05, "step": 49400 }, { "epoch": 6.41300116776956, "grad_norm": 0.00038288297946564853, "learning_rate": 1.1289760782052241e-05, "loss": 3.096178639680147e-05, "step": 49425 }, { "epoch": 6.416244972103283, "grad_norm": 0.0002929171605501324, "learning_rate": 1.126333223342966e-05, "loss": 2.971787005662918e-05, "step": 49450 }, { "epoch": 6.419488776437006, "grad_norm": 0.0007181468536145985, "learning_rate": 1.123692565722745e-05, "loss": 3.369871526956558e-05, "step": 49475 }, { "epoch": 6.422732580770728, "grad_norm": 0.0009867926128208637, "learning_rate": 1.1210541095684104e-05, "loss": 3.5123385023325684e-05, "step": 49500 }, { "epoch": 6.425976385104451, "grad_norm": 0.0007504912791773677, "learning_rate": 1.1184178591002936e-05, "loss": 3.4073390997946264e-05, "step": 49525 }, { "epoch": 6.429220189438173, "grad_norm": 0.0003239849756937474, "learning_rate": 1.1157838185351948e-05, "loss": 3.3612903207540514e-05, "step": 49550 }, { "epoch": 6.432463993771895, "grad_norm": 0.0005211979150772095, "learning_rate": 1.1131519920863826e-05, "loss": 2.6343869976699352e-05, "step": 49575 }, { "epoch": 6.435707798105618, "grad_norm": 0.000757347559556365, "learning_rate": 1.1105223839635801e-05, "loss": 3.269813256338239e-05, "step": 49600 }, { "epoch": 6.4389516024393405, "grad_norm": 0.0004384601197671145, "learning_rate": 1.1078949983729661e-05, "loss": 3.428191412240267e-05, "step": 49625 }, { "epoch": 6.442195406773063, "grad_norm": 0.0010004249634221196, "learning_rate": 1.105269839517161e-05, "loss": 2.728072460740805e-05, "step": 49650 }, { "epoch": 6.445439211106786, "grad_norm": 0.00035578382085077465, "learning_rate": 1.1026469115952265e-05, "loss": 3.777066711336374e-05, "step": 49675 }, { "epoch": 6.448683015440508, "grad_norm": 0.0009010219946503639, "learning_rate": 1.1000262188026525e-05, "loss": 3.202190855517983e-05, "step": 49700 }, { "epoch": 6.451926819774231, "grad_norm": 0.00033786898711696267, "learning_rate": 1.0974077653313572e-05, "loss": 3.2261740416288375e-05, "step": 49725 }, { "epoch": 6.455170624107954, "grad_norm": 0.000806304975412786, "learning_rate": 1.0947915553696742e-05, "loss": 3.380962647497654e-05, "step": 49750 }, { "epoch": 6.458414428441676, "grad_norm": 0.0007762509630993009, "learning_rate": 1.092177593102349e-05, "loss": 3.24121699668467e-05, "step": 49775 }, { "epoch": 6.461658232775399, "grad_norm": 0.0014051003381609917, "learning_rate": 1.0895658827105335e-05, "loss": 3.122237045317888e-05, "step": 49800 }, { "epoch": 6.4649020371091215, "grad_norm": 0.0005473931669257581, "learning_rate": 1.0869564283717748e-05, "loss": 3.1494032591581344e-05, "step": 49825 }, { "epoch": 6.468145841442844, "grad_norm": 0.001536838710308075, "learning_rate": 1.0843492342600148e-05, "loss": 3.1855497509241106e-05, "step": 49850 }, { "epoch": 6.471389645776567, "grad_norm": 0.0007475445163436234, "learning_rate": 1.0817443045455766e-05, "loss": 3.543734317645431e-05, "step": 49875 }, { "epoch": 6.474633450110289, "grad_norm": 0.0013004641514271498, "learning_rate": 1.0791416433951642e-05, "loss": 3.0185382347553967e-05, "step": 49900 }, { "epoch": 6.477877254444012, "grad_norm": 0.000465719640487805, "learning_rate": 1.0765412549718506e-05, "loss": 2.909005153924227e-05, "step": 49925 }, { "epoch": 6.481121058777735, "grad_norm": 0.0008285137009806931, "learning_rate": 1.0739431434350756e-05, "loss": 2.987043233588338e-05, "step": 49950 }, { "epoch": 6.484364863111457, "grad_norm": 0.001080264337360859, "learning_rate": 1.0713473129406342e-05, "loss": 3.377262037247419e-05, "step": 49975 }, { "epoch": 6.48760866744518, "grad_norm": 0.0011258942540735006, "learning_rate": 1.0687537676406768e-05, "loss": 3.416587132960558e-05, "step": 50000 }, { "epoch": 6.4908524717789025, "grad_norm": 0.0013046242529526353, "learning_rate": 1.0661625116836938e-05, "loss": 3.116306615993381e-05, "step": 50025 }, { "epoch": 6.494096276112625, "grad_norm": 0.0007645949372090399, "learning_rate": 1.0635735492145171e-05, "loss": 2.814890118315816e-05, "step": 50050 }, { "epoch": 6.497340080446348, "grad_norm": 0.001336298300884664, "learning_rate": 1.0609868843743104e-05, "loss": 3.0500523280352354e-05, "step": 50075 }, { "epoch": 6.50058388478007, "grad_norm": 0.0005841896054334939, "learning_rate": 1.0584025213005588e-05, "loss": 3.2638644333928824e-05, "step": 50100 }, { "epoch": 6.503827689113793, "grad_norm": 0.000899741891771555, "learning_rate": 1.0558204641270697e-05, "loss": 3.3679639454931023e-05, "step": 50125 }, { "epoch": 6.507071493447516, "grad_norm": 0.0004998478689230978, "learning_rate": 1.0532407169839581e-05, "loss": 3.079703310504556e-05, "step": 50150 }, { "epoch": 6.510315297781238, "grad_norm": 0.0007487700204364955, "learning_rate": 1.050663283997648e-05, "loss": 3.346915589645505e-05, "step": 50175 }, { "epoch": 6.513559102114961, "grad_norm": 0.0006929758237674832, "learning_rate": 1.0480881692908582e-05, "loss": 2.9200324788689614e-05, "step": 50200 }, { "epoch": 6.516802906448683, "grad_norm": 0.0003644691896624863, "learning_rate": 1.045515376982602e-05, "loss": 2.8894718270748853e-05, "step": 50225 }, { "epoch": 6.520046710782406, "grad_norm": 0.0004091216833330691, "learning_rate": 1.0429449111881761e-05, "loss": 3.1814079266041516e-05, "step": 50250 }, { "epoch": 6.523290515116129, "grad_norm": 0.0004192984488327056, "learning_rate": 1.0403767760191579e-05, "loss": 2.8520789928734303e-05, "step": 50275 }, { "epoch": 6.52653431944985, "grad_norm": 0.0006730161840096116, "learning_rate": 1.0378109755833938e-05, "loss": 3.3487610053271056e-05, "step": 50300 }, { "epoch": 6.529778123783573, "grad_norm": 0.0008994614472612739, "learning_rate": 1.0352475139849993e-05, "loss": 3.3167137298732994e-05, "step": 50325 }, { "epoch": 6.533021928117296, "grad_norm": 0.0011543073924258351, "learning_rate": 1.0326863953243448e-05, "loss": 3.002344397827983e-05, "step": 50350 }, { "epoch": 6.536265732451018, "grad_norm": 0.0016868870006874204, "learning_rate": 1.0301276236980578e-05, "loss": 2.8371098451316357e-05, "step": 50375 }, { "epoch": 6.539509536784741, "grad_norm": 0.0004590325988829136, "learning_rate": 1.0275712031990068e-05, "loss": 3.3507205080240966e-05, "step": 50400 }, { "epoch": 6.5427533411184635, "grad_norm": 0.0004217988171149045, "learning_rate": 1.0250171379163035e-05, "loss": 3.16071417182684e-05, "step": 50425 }, { "epoch": 6.545997145452186, "grad_norm": 0.0003850350040011108, "learning_rate": 1.0224654319352888e-05, "loss": 3.0399099923670292e-05, "step": 50450 }, { "epoch": 6.549240949785909, "grad_norm": 0.0007027434185147285, "learning_rate": 1.0199160893375339e-05, "loss": 2.6039315853267907e-05, "step": 50475 }, { "epoch": 6.552484754119631, "grad_norm": 0.0009371816413477063, "learning_rate": 1.0173691142008254e-05, "loss": 3.188950940966606e-05, "step": 50500 }, { "epoch": 6.555728558453354, "grad_norm": 0.0012951120734214783, "learning_rate": 1.0148245105991666e-05, "loss": 3.230151021853089e-05, "step": 50525 }, { "epoch": 6.558972362787077, "grad_norm": 0.00034559814957901835, "learning_rate": 1.0122822826027644e-05, "loss": 2.8687461744993927e-05, "step": 50550 }, { "epoch": 6.562216167120799, "grad_norm": 0.0019057758618146181, "learning_rate": 1.0097424342780288e-05, "loss": 3.129196586087346e-05, "step": 50575 }, { "epoch": 6.565459971454522, "grad_norm": 0.0004426291270647198, "learning_rate": 1.0072049696875602e-05, "loss": 3.409693483263254e-05, "step": 50600 }, { "epoch": 6.5687037757882445, "grad_norm": 0.0009000202408060431, "learning_rate": 1.0046698928901488e-05, "loss": 3.114958060905337e-05, "step": 50625 }, { "epoch": 6.571947580121967, "grad_norm": 0.0005703611532226205, "learning_rate": 1.002137207940765e-05, "loss": 3.5687489435076715e-05, "step": 50650 }, { "epoch": 6.57519138445569, "grad_norm": 0.001556078321300447, "learning_rate": 9.996069188905512e-06, "loss": 3.428514115512371e-05, "step": 50675 }, { "epoch": 6.578435188789412, "grad_norm": 0.0005040951655246317, "learning_rate": 9.970790297868206e-06, "loss": 3.3791107125580314e-05, "step": 50700 }, { "epoch": 6.581678993123135, "grad_norm": 0.0004180797841399908, "learning_rate": 9.945535446730447e-06, "loss": 2.9100512620061636e-05, "step": 50725 }, { "epoch": 6.584922797456858, "grad_norm": 0.0008105558226816356, "learning_rate": 9.92030467588852e-06, "loss": 3.6592979449778794e-05, "step": 50750 }, { "epoch": 6.58816660179058, "grad_norm": 0.0008715322474017739, "learning_rate": 9.89509802570017e-06, "loss": 3.027169033885002e-05, "step": 50775 }, { "epoch": 6.591410406124303, "grad_norm": 0.0021021717693656683, "learning_rate": 9.869915536484586e-06, "loss": 2.8923051431775093e-05, "step": 50800 }, { "epoch": 6.5946542104580255, "grad_norm": 0.001391604426316917, "learning_rate": 9.844757248522279e-06, "loss": 3.547706175595522e-05, "step": 50825 }, { "epoch": 6.597898014791748, "grad_norm": 0.0017008165596053004, "learning_rate": 9.81962320205509e-06, "loss": 2.9494359623640775e-05, "step": 50850 }, { "epoch": 6.601141819125471, "grad_norm": 0.0007998186047188938, "learning_rate": 9.794513437286037e-06, "loss": 2.9080521780997515e-05, "step": 50875 }, { "epoch": 6.6043856234591924, "grad_norm": 0.0008290862897410989, "learning_rate": 9.769427994379343e-06, "loss": 3.146659582853317e-05, "step": 50900 }, { "epoch": 6.607629427792915, "grad_norm": 0.0007268668850883842, "learning_rate": 9.74436691346029e-06, "loss": 3.001285484060645e-05, "step": 50925 }, { "epoch": 6.610873232126638, "grad_norm": 0.000749928702134639, "learning_rate": 9.719330234615227e-06, "loss": 3.646424738690257e-05, "step": 50950 }, { "epoch": 6.61411703646036, "grad_norm": 0.0004146505962125957, "learning_rate": 9.694317997891427e-06, "loss": 3.033313201740384e-05, "step": 50975 }, { "epoch": 6.617360840794083, "grad_norm": 0.0014520641416311264, "learning_rate": 9.66933024329712e-06, "loss": 3.342896234244108e-05, "step": 51000 }, { "epoch": 6.6206046451278056, "grad_norm": 0.0008226827485486865, "learning_rate": 9.644367010801325e-06, "loss": 3.354861401021481e-05, "step": 51025 }, { "epoch": 6.623848449461528, "grad_norm": 0.0009321268298663199, "learning_rate": 9.619428340333875e-06, "loss": 3.010600805282593e-05, "step": 51050 }, { "epoch": 6.627092253795251, "grad_norm": 0.000464844488305971, "learning_rate": 9.594514271785288e-06, "loss": 2.703182166442275e-05, "step": 51075 }, { "epoch": 6.630336058128973, "grad_norm": 0.0005650771781802177, "learning_rate": 9.569624845006753e-06, "loss": 2.919851103797555e-05, "step": 51100 }, { "epoch": 6.633579862462696, "grad_norm": 0.0007878138567321002, "learning_rate": 9.544760099810018e-06, "loss": 3.350342623889446e-05, "step": 51125 }, { "epoch": 6.636823666796419, "grad_norm": 0.0011268560774624348, "learning_rate": 9.519920075967376e-06, "loss": 3.083531046286225e-05, "step": 51150 }, { "epoch": 6.640067471130141, "grad_norm": 0.000646922446321696, "learning_rate": 9.49510481321157e-06, "loss": 3.527589607983828e-05, "step": 51175 }, { "epoch": 6.643311275463864, "grad_norm": 0.00041552793118171394, "learning_rate": 9.47031435123572e-06, "loss": 3.3710196148604155e-05, "step": 51200 }, { "epoch": 6.6465550797975865, "grad_norm": 0.0004397784359753132, "learning_rate": 9.445548729693306e-06, "loss": 3.246300620958209e-05, "step": 51225 }, { "epoch": 6.649798884131309, "grad_norm": 0.0008316222811117768, "learning_rate": 9.42080798819804e-06, "loss": 3.0059765558689834e-05, "step": 51250 }, { "epoch": 6.653042688465032, "grad_norm": 0.001210985705256462, "learning_rate": 9.396092166323884e-06, "loss": 3.6949729546904565e-05, "step": 51275 }, { "epoch": 6.656286492798754, "grad_norm": 0.0008025387651287019, "learning_rate": 9.371401303604871e-06, "loss": 3.6391899921e-05, "step": 51300 }, { "epoch": 6.659530297132477, "grad_norm": 0.0007273557712323964, "learning_rate": 9.346735439535182e-06, "loss": 3.3257640898227694e-05, "step": 51325 }, { "epoch": 6.6627741014662, "grad_norm": 0.0009887616615742445, "learning_rate": 9.322094613568958e-06, "loss": 3.1998036429286e-05, "step": 51350 }, { "epoch": 6.666017905799922, "grad_norm": 0.00048113963566720486, "learning_rate": 9.297478865120335e-06, "loss": 3.0987821519374846e-05, "step": 51375 }, { "epoch": 6.669261710133645, "grad_norm": 0.0016869987593963742, "learning_rate": 9.272888233563292e-06, "loss": 3.9717108011245726e-05, "step": 51400 }, { "epoch": 6.6725055144673675, "grad_norm": 0.001560039701871574, "learning_rate": 9.248322758231678e-06, "loss": 3.055969486013055e-05, "step": 51425 }, { "epoch": 6.67574931880109, "grad_norm": 0.0012041726149618626, "learning_rate": 9.223782478419061e-06, "loss": 3.177972976118326e-05, "step": 51450 }, { "epoch": 6.678993123134813, "grad_norm": 0.0007875518640503287, "learning_rate": 9.199267433378727e-06, "loss": 3.5135422367602585e-05, "step": 51475 }, { "epoch": 6.682236927468535, "grad_norm": 0.0003869103384204209, "learning_rate": 9.17477766232362e-06, "loss": 3.221480874344706e-05, "step": 51500 }, { "epoch": 6.685480731802258, "grad_norm": 0.0010716336546465755, "learning_rate": 9.150313204426206e-06, "loss": 3.0713712330907586e-05, "step": 51525 }, { "epoch": 6.688724536135981, "grad_norm": 0.0006697351927869022, "learning_rate": 9.125874098818513e-06, "loss": 2.943150931969285e-05, "step": 51550 }, { "epoch": 6.691968340469703, "grad_norm": 0.0007109700818546116, "learning_rate": 9.101460384591972e-06, "loss": 3.1706534791737795e-05, "step": 51575 }, { "epoch": 6.695212144803426, "grad_norm": 0.0006762899574823678, "learning_rate": 9.077072100797446e-06, "loss": 3.149626776576042e-05, "step": 51600 }, { "epoch": 6.6984559491371485, "grad_norm": 0.0007334169931709766, "learning_rate": 9.05270928644507e-06, "loss": 3.334073815494776e-05, "step": 51625 }, { "epoch": 6.701699753470871, "grad_norm": 0.0008001743699423969, "learning_rate": 9.028371980504291e-06, "loss": 2.957704709842801e-05, "step": 51650 }, { "epoch": 6.704943557804594, "grad_norm": 0.0005185720510780811, "learning_rate": 9.004060221903707e-06, "loss": 3.437022911384702e-05, "step": 51675 }, { "epoch": 6.7081873621383155, "grad_norm": 0.0005706448573619127, "learning_rate": 8.979774049531092e-06, "loss": 3.0921983998268844e-05, "step": 51700 }, { "epoch": 6.711431166472038, "grad_norm": 0.0007691014907322824, "learning_rate": 8.95551350223326e-06, "loss": 3.483499633148313e-05, "step": 51725 }, { "epoch": 6.714674970805761, "grad_norm": 0.0014923388371244073, "learning_rate": 8.931278618816064e-06, "loss": 3.060603514313698e-05, "step": 51750 }, { "epoch": 6.714674970805761, "eval_loss": 0.00015658939082641155, "eval_runtime": 7.0347, "eval_samples_per_second": 710.766, "eval_steps_per_second": 5.686, "step": 51750 }, { "epoch": 6.714674970805761, "eval_holdout_avg_strict_f1": 0.2711238323751052, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.8117443868739206, "eval_holdout_nemotron_pii_strict_f1": 0.7743212221958363, "eval_holdout_open_pii_masking_500k_strict_f1": 0.6990675332014693, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.6972290138549307, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 51750 }, { "epoch": 6.717918775139483, "grad_norm": 0.0006630606367252767, "learning_rate": 8.907069438044283e-06, "loss": 3.237602533772588e-05, "step": 51775 }, { "epoch": 6.721162579473206, "grad_norm": 0.0010293187806382775, "learning_rate": 8.882885998641607e-06, "loss": 3.1467555090785025e-05, "step": 51800 }, { "epoch": 6.724406383806929, "grad_norm": 0.0004751516389660537, "learning_rate": 8.858728339290526e-06, "loss": 3.3683744259178635e-05, "step": 51825 }, { "epoch": 6.727650188140651, "grad_norm": 0.001387056545354426, "learning_rate": 8.834596498632322e-06, "loss": 3.6577086430042985e-05, "step": 51850 }, { "epoch": 6.730893992474374, "grad_norm": 0.0011032128240913153, "learning_rate": 8.810490515266948e-06, "loss": 3.2131730113178494e-05, "step": 51875 }, { "epoch": 6.734137796808096, "grad_norm": 0.0016129582654684782, "learning_rate": 8.786410427753028e-06, "loss": 3.352197352796793e-05, "step": 51900 }, { "epoch": 6.737381601141819, "grad_norm": 0.0008458471857011318, "learning_rate": 8.762356274607733e-06, "loss": 2.9129565227776766e-05, "step": 51925 }, { "epoch": 6.740625405475542, "grad_norm": 0.0004023287328891456, "learning_rate": 8.738328094306785e-06, "loss": 2.9766997322440147e-05, "step": 51950 }, { "epoch": 6.743869209809264, "grad_norm": 0.001227142638526857, "learning_rate": 8.714325925284325e-06, "loss": 3.018585965037346e-05, "step": 51975 }, { "epoch": 6.747113014142987, "grad_norm": 0.0005253354902379215, "learning_rate": 8.690349805932918e-06, "loss": 2.8105585370212795e-05, "step": 52000 }, { "epoch": 6.7503568184767095, "grad_norm": 0.0011749948607757688, "learning_rate": 8.666399774603454e-06, "loss": 3.180632833391428e-05, "step": 52025 }, { "epoch": 6.753600622810432, "grad_norm": 0.0003420524299144745, "learning_rate": 8.642475869605073e-06, "loss": 2.7252412401139736e-05, "step": 52050 }, { "epoch": 6.756844427144155, "grad_norm": 0.0012184324441477656, "learning_rate": 8.61857812920516e-06, "loss": 3.285014303401113e-05, "step": 52075 }, { "epoch": 6.760088231477877, "grad_norm": 0.0010352248791605234, "learning_rate": 8.594706591629214e-06, "loss": 3.5510112065821884e-05, "step": 52100 }, { "epoch": 6.7633320358116, "grad_norm": 0.0012608579127117991, "learning_rate": 8.57086129506085e-06, "loss": 3.551085712388158e-05, "step": 52125 }, { "epoch": 6.766575840145323, "grad_norm": 0.0011357672046869993, "learning_rate": 8.547042277641684e-06, "loss": 2.8951126150786877e-05, "step": 52150 }, { "epoch": 6.769819644479045, "grad_norm": 0.000338361511239782, "learning_rate": 8.523249577471323e-06, "loss": 3.274692455306649e-05, "step": 52175 }, { "epoch": 6.773063448812768, "grad_norm": 0.00039710954297333956, "learning_rate": 8.499483232607252e-06, "loss": 3.003678284585476e-05, "step": 52200 }, { "epoch": 6.7763072531464905, "grad_norm": 0.0009550594841130078, "learning_rate": 8.475743281064829e-06, "loss": 3.277395851910114e-05, "step": 52225 }, { "epoch": 6.779551057480213, "grad_norm": 0.0009028652566485107, "learning_rate": 8.452029760817159e-06, "loss": 2.8996877372264862e-05, "step": 52250 }, { "epoch": 6.782794861813936, "grad_norm": 0.0007722849259153008, "learning_rate": 8.428342709795106e-06, "loss": 3.063852433115244e-05, "step": 52275 }, { "epoch": 6.7860386661476575, "grad_norm": 0.0012233381858095527, "learning_rate": 8.404682165887164e-06, "loss": 3.1098041217774154e-05, "step": 52300 }, { "epoch": 6.78928247048138, "grad_norm": 0.0008827653946354985, "learning_rate": 8.381048166939453e-06, "loss": 2.9478943906724454e-05, "step": 52325 }, { "epoch": 6.792526274815103, "grad_norm": 0.0005400741938501596, "learning_rate": 8.35744075075561e-06, "loss": 2.9128126334398986e-05, "step": 52350 }, { "epoch": 6.795770079148825, "grad_norm": 0.0008425097912549973, "learning_rate": 8.333859955096777e-06, "loss": 3.0941038858145475e-05, "step": 52375 }, { "epoch": 6.799013883482548, "grad_norm": 0.000817539228592068, "learning_rate": 8.310305817681485e-06, "loss": 2.8997203335165976e-05, "step": 52400 }, { "epoch": 6.802257687816271, "grad_norm": 0.0007784414337947965, "learning_rate": 8.286778376185658e-06, "loss": 2.9041145462542773e-05, "step": 52425 }, { "epoch": 6.805501492149993, "grad_norm": 0.0009604282677173615, "learning_rate": 8.263277668242481e-06, "loss": 3.196008037775755e-05, "step": 52450 }, { "epoch": 6.808745296483716, "grad_norm": 0.0006334100617095828, "learning_rate": 8.23980373144242e-06, "loss": 3.049264894798398e-05, "step": 52475 }, { "epoch": 6.8119891008174385, "grad_norm": 0.0020298687741160393, "learning_rate": 8.216356603333072e-06, "loss": 2.8853507246822118e-05, "step": 52500 }, { "epoch": 6.815232905151161, "grad_norm": 0.0004731161461677402, "learning_rate": 8.192936321419196e-06, "loss": 2.8390754014253616e-05, "step": 52525 }, { "epoch": 6.818476709484884, "grad_norm": 0.0006978557794354856, "learning_rate": 8.16954292316259e-06, "loss": 3.205123357474804e-05, "step": 52550 }, { "epoch": 6.821720513818606, "grad_norm": 0.0004212254425510764, "learning_rate": 8.146176445982036e-06, "loss": 3.174337791278958e-05, "step": 52575 }, { "epoch": 6.824964318152329, "grad_norm": 0.00037168568815104663, "learning_rate": 8.122836927253291e-06, "loss": 2.9324276838451623e-05, "step": 52600 }, { "epoch": 6.828208122486052, "grad_norm": 0.0005683236522600055, "learning_rate": 8.099524404308948e-06, "loss": 2.9917038045823573e-05, "step": 52625 }, { "epoch": 6.831451926819774, "grad_norm": 0.0011629984946921468, "learning_rate": 8.076238914438458e-06, "loss": 3.0867867171764376e-05, "step": 52650 }, { "epoch": 6.834695731153497, "grad_norm": 0.0006173274014145136, "learning_rate": 8.052980494887996e-06, "loss": 3.262587124481797e-05, "step": 52675 }, { "epoch": 6.8379395354872194, "grad_norm": 0.0008071320480667055, "learning_rate": 8.029749182860469e-06, "loss": 2.7557353023439644e-05, "step": 52700 }, { "epoch": 6.841183339820942, "grad_norm": 0.0009839785052463412, "learning_rate": 8.006545015515399e-06, "loss": 3.221268299967051e-05, "step": 52725 }, { "epoch": 6.844427144154665, "grad_norm": 0.0013795953709632158, "learning_rate": 7.98336802996891e-06, "loss": 3.245075698941946e-05, "step": 52750 }, { "epoch": 6.847670948488387, "grad_norm": 0.0006722672842442989, "learning_rate": 7.960218263293623e-06, "loss": 3.289447631686926e-05, "step": 52775 }, { "epoch": 6.85091475282211, "grad_norm": 0.0007302165031433105, "learning_rate": 7.93709575251865e-06, "loss": 2.8813837561756374e-05, "step": 52800 }, { "epoch": 6.8541585571558326, "grad_norm": 0.000450146704679355, "learning_rate": 7.914000534629487e-06, "loss": 3.171441610902548e-05, "step": 52825 }, { "epoch": 6.857402361489555, "grad_norm": 0.0005569426575675607, "learning_rate": 7.890932646567964e-06, "loss": 3.157611936330795e-05, "step": 52850 }, { "epoch": 6.860646165823278, "grad_norm": 0.0012934074038639665, "learning_rate": 7.867892125232228e-06, "loss": 3.5479990765452384e-05, "step": 52875 }, { "epoch": 6.863889970157, "grad_norm": 0.002232837490737438, "learning_rate": 7.844879007476622e-06, "loss": 2.998345997184515e-05, "step": 52900 }, { "epoch": 6.867133774490723, "grad_norm": 0.0005994952516630292, "learning_rate": 7.821893330111677e-06, "loss": 2.9314146377146245e-05, "step": 52925 }, { "epoch": 6.870377578824446, "grad_norm": 0.0007389461388811469, "learning_rate": 7.798935129904005e-06, "loss": 3.165558679029345e-05, "step": 52950 }, { "epoch": 6.873621383158168, "grad_norm": 0.0011645337799564004, "learning_rate": 7.776004443576307e-06, "loss": 2.7924173045903445e-05, "step": 52975 }, { "epoch": 6.876865187491891, "grad_norm": 0.0005178650608286262, "learning_rate": 7.753101307807228e-06, "loss": 3.259273013100028e-05, "step": 53000 }, { "epoch": 6.8801089918256135, "grad_norm": 0.0008579592686146498, "learning_rate": 7.730225759231388e-06, "loss": 2.576947212219238e-05, "step": 53025 }, { "epoch": 6.883352796159336, "grad_norm": 0.0004032120923511684, "learning_rate": 7.707377834439242e-06, "loss": 3.441025968641043e-05, "step": 53050 }, { "epoch": 6.886596600493058, "grad_norm": 0.0006340277031995356, "learning_rate": 7.684557569977095e-06, "loss": 3.0018943361938e-05, "step": 53075 }, { "epoch": 6.8898404048267805, "grad_norm": 0.0008830344886519015, "learning_rate": 7.661765002346968e-06, "loss": 3.045404329895973e-05, "step": 53100 }, { "epoch": 6.893084209160503, "grad_norm": 0.00047926066326908767, "learning_rate": 7.63900016800663e-06, "loss": 2.9477644711732865e-05, "step": 53125 }, { "epoch": 6.896328013494226, "grad_norm": 0.00045182928442955017, "learning_rate": 7.616263103369433e-06, "loss": 2.9013443272560833e-05, "step": 53150 }, { "epoch": 6.899571817827948, "grad_norm": 0.0006891056546010077, "learning_rate": 7.593553844804366e-06, "loss": 3.263052785769105e-05, "step": 53175 }, { "epoch": 6.902815622161671, "grad_norm": 0.001760450191795826, "learning_rate": 7.570872428635889e-06, "loss": 3.0470830388367176e-05, "step": 53200 }, { "epoch": 6.906059426495394, "grad_norm": 0.0012817132519558072, "learning_rate": 7.548218891143971e-06, "loss": 3.459181869402528e-05, "step": 53225 }, { "epoch": 6.909303230829116, "grad_norm": 0.0009210032294504344, "learning_rate": 7.525593268563949e-06, "loss": 2.969395136460662e-05, "step": 53250 }, { "epoch": 6.912547035162839, "grad_norm": 0.00049095373833552, "learning_rate": 7.502995597086548e-06, "loss": 3.112454200163484e-05, "step": 53275 }, { "epoch": 6.9157908394965615, "grad_norm": 0.0006793983047828078, "learning_rate": 7.480425912857747e-06, "loss": 3.147834213450551e-05, "step": 53300 }, { "epoch": 6.919034643830284, "grad_norm": 0.0004430602421052754, "learning_rate": 7.457884251978791e-06, "loss": 3.19511815905571e-05, "step": 53325 }, { "epoch": 6.922278448164007, "grad_norm": 0.0005238777957856655, "learning_rate": 7.435370650506066e-06, "loss": 3.016478382050991e-05, "step": 53350 }, { "epoch": 6.925522252497729, "grad_norm": 0.0007620568503625691, "learning_rate": 7.412885144451104e-06, "loss": 3.1435820274055006e-05, "step": 53375 }, { "epoch": 6.928766056831452, "grad_norm": 0.000744034128729254, "learning_rate": 7.3904277697804975e-06, "loss": 3.2793863210827114e-05, "step": 53400 }, { "epoch": 6.932009861165175, "grad_norm": 0.00043922229087911546, "learning_rate": 7.367998562415809e-06, "loss": 3.532294649630785e-05, "step": 53425 }, { "epoch": 6.935253665498897, "grad_norm": 0.0007761261076666415, "learning_rate": 7.345597558233591e-06, "loss": 3.516577882692218e-05, "step": 53450 }, { "epoch": 6.93849746983262, "grad_norm": 0.0005849080625921488, "learning_rate": 7.323224793065242e-06, "loss": 2.8577274642884733e-05, "step": 53475 }, { "epoch": 6.9417412741663425, "grad_norm": 0.0005068023456260562, "learning_rate": 7.300880302697027e-06, "loss": 2.983213635161519e-05, "step": 53500 }, { "epoch": 6.944985078500065, "grad_norm": 0.0007545113912783563, "learning_rate": 7.278564122869949e-06, "loss": 3.588881809264421e-05, "step": 53525 }, { "epoch": 6.948228882833788, "grad_norm": 0.00081396265886724, "learning_rate": 7.256276289279765e-06, "loss": 2.7725526597350835e-05, "step": 53550 }, { "epoch": 6.95147268716751, "grad_norm": 0.0006242765812203288, "learning_rate": 7.2340168375768545e-06, "loss": 3.365695010870695e-05, "step": 53575 }, { "epoch": 6.954716491501233, "grad_norm": 0.0011526938760653138, "learning_rate": 7.21178580336623e-06, "loss": 3.146707778796554e-05, "step": 53600 }, { "epoch": 6.957960295834956, "grad_norm": 0.0006116559961810708, "learning_rate": 7.189583222207419e-06, "loss": 2.859649248421192e-05, "step": 53625 }, { "epoch": 6.961204100168678, "grad_norm": 0.0012697330676019192, "learning_rate": 7.167409129614466e-06, "loss": 3.3668056130409243e-05, "step": 53650 }, { "epoch": 6.9644479045024, "grad_norm": 0.0005520904087461531, "learning_rate": 7.145263561055823e-06, "loss": 2.9978533275425436e-05, "step": 53675 }, { "epoch": 6.9676917088361225, "grad_norm": 0.000698549731168896, "learning_rate": 7.123146551954341e-06, "loss": 3.204667242243886e-05, "step": 53700 }, { "epoch": 6.970935513169845, "grad_norm": 0.0006467479979619384, "learning_rate": 7.101058137687155e-06, "loss": 3.4681421238929035e-05, "step": 53725 }, { "epoch": 6.974179317503568, "grad_norm": 0.0009432610822841525, "learning_rate": 7.078998353585703e-06, "loss": 3.521422389894724e-05, "step": 53750 }, { "epoch": 6.97742312183729, "grad_norm": 0.0006904614274390042, "learning_rate": 7.0569672349355825e-06, "loss": 2.8934315778315068e-05, "step": 53775 }, { "epoch": 6.980666926171013, "grad_norm": 0.0007124669500626624, "learning_rate": 7.034964816976586e-06, "loss": 3.126487135887146e-05, "step": 53800 }, { "epoch": 6.983910730504736, "grad_norm": 0.00051860511302948, "learning_rate": 7.012991134902552e-06, "loss": 3.2295414712280035e-05, "step": 53825 }, { "epoch": 6.987154534838458, "grad_norm": 0.001382339047268033, "learning_rate": 6.9910462238614e-06, "loss": 3.339500864967704e-05, "step": 53850 }, { "epoch": 6.990398339172181, "grad_norm": 0.0009648092673160136, "learning_rate": 6.969130118954983e-06, "loss": 3.0558244325220586e-05, "step": 53875 }, { "epoch": 6.9936421435059035, "grad_norm": 0.0006444489699788392, "learning_rate": 6.947242855239122e-06, "loss": 2.8224452398717405e-05, "step": 53900 }, { "epoch": 6.996885947839626, "grad_norm": 0.0009811833733692765, "learning_rate": 6.925384467723464e-06, "loss": 2.9203058220446108e-05, "step": 53925 }, { "epoch": 7.000129752173349, "grad_norm": 0.0004778947331942618, "learning_rate": 6.903554991371497e-06, "loss": 3.340416355058551e-05, "step": 53950 }, { "epoch": 7.003373556507071, "grad_norm": 0.0006845594616606832, "learning_rate": 6.881754461100462e-06, "loss": 3.1183070968836544e-05, "step": 53975 }, { "epoch": 7.006617360840794, "grad_norm": 0.0007340831216424704, "learning_rate": 6.8599829117812735e-06, "loss": 3.087193705141544e-05, "step": 54000 }, { "epoch": 7.009861165174517, "grad_norm": 0.000547253352124244, "learning_rate": 6.838240378238528e-06, "loss": 3.3360007219016555e-05, "step": 54025 }, { "epoch": 7.013104969508239, "grad_norm": 0.0006496721762232482, "learning_rate": 6.8165268952503666e-06, "loss": 3.572450950741768e-05, "step": 54050 }, { "epoch": 7.016348773841962, "grad_norm": 0.0005187249043956399, "learning_rate": 6.794842497548509e-06, "loss": 2.7958911377936602e-05, "step": 54075 }, { "epoch": 7.0195925781756845, "grad_norm": 0.0004100596415810287, "learning_rate": 6.773187219818109e-06, "loss": 3.270774148404598e-05, "step": 54100 }, { "epoch": 7.022836382509407, "grad_norm": 0.00047722147428430617, "learning_rate": 6.751561096697778e-06, "loss": 3.186118789017201e-05, "step": 54125 }, { "epoch": 7.02608018684313, "grad_norm": 0.0004757825518026948, "learning_rate": 6.729964162779459e-06, "loss": 3.187072928994894e-05, "step": 54150 }, { "epoch": 7.029323991176852, "grad_norm": 0.0004751025408040732, "learning_rate": 6.70839645260844e-06, "loss": 3.070515347644687e-05, "step": 54175 }, { "epoch": 7.032567795510575, "grad_norm": 0.0008568274788558483, "learning_rate": 6.6868580006832324e-06, "loss": 3.162509761750698e-05, "step": 54200 }, { "epoch": 7.035811599844298, "grad_norm": 0.0007411285769194365, "learning_rate": 6.665348841455577e-06, "loss": 2.7316694613546132e-05, "step": 54225 }, { "epoch": 7.03905540417802, "grad_norm": 0.0003311776672489941, "learning_rate": 6.643869009330331e-06, "loss": 3.489016788080335e-05, "step": 54250 }, { "epoch": 7.042299208511743, "grad_norm": 0.000744120217859745, "learning_rate": 6.622418538665468e-06, "loss": 2.9764268547296524e-05, "step": 54275 }, { "epoch": 7.0455430128454655, "grad_norm": 0.0005030246102251112, "learning_rate": 6.600997463771974e-06, "loss": 3.531304420903325e-05, "step": 54300 }, { "epoch": 7.048786817179188, "grad_norm": 0.001013111905194819, "learning_rate": 6.579605818913837e-06, "loss": 3.431231481954455e-05, "step": 54325 }, { "epoch": 7.052030621512911, "grad_norm": 0.001257265917956829, "learning_rate": 6.5582436383079425e-06, "loss": 3.209817223250866e-05, "step": 54350 }, { "epoch": 7.055274425846633, "grad_norm": 0.0006518318550661206, "learning_rate": 6.536910956124084e-06, "loss": 3.102303482592106e-05, "step": 54375 }, { "epoch": 7.058518230180356, "grad_norm": 0.000709163083229214, "learning_rate": 6.515607806484839e-06, "loss": 3.4035423304885626e-05, "step": 54400 }, { "epoch": 7.061762034514078, "grad_norm": 0.0005106076132506132, "learning_rate": 6.494334223465545e-06, "loss": 2.8168135322630406e-05, "step": 54425 }, { "epoch": 7.0650058388478, "grad_norm": 0.0006699887453578413, "learning_rate": 6.473090241094282e-06, "loss": 3.159171901643276e-05, "step": 54450 }, { "epoch": 7.068249643181523, "grad_norm": 0.0013413967099040747, "learning_rate": 6.451875893351741e-06, "loss": 2.8859400190412997e-05, "step": 54475 }, { "epoch": 7.071493447515246, "grad_norm": 0.0006514009437523782, "learning_rate": 6.430691214171242e-06, "loss": 2.991518937051296e-05, "step": 54500 }, { "epoch": 7.074737251848968, "grad_norm": 0.0008354633464477956, "learning_rate": 6.409536237438621e-06, "loss": 2.960603917017579e-05, "step": 54525 }, { "epoch": 7.077981056182691, "grad_norm": 0.0005963948206044734, "learning_rate": 6.388410996992237e-06, "loss": 2.96210334636271e-05, "step": 54550 }, { "epoch": 7.081224860516413, "grad_norm": 0.000810871715657413, "learning_rate": 6.367315526622849e-06, "loss": 3.221135586500168e-05, "step": 54575 }, { "epoch": 7.084468664850136, "grad_norm": 0.0008493372588418424, "learning_rate": 6.346249860073628e-06, "loss": 3.095197724178434e-05, "step": 54600 }, { "epoch": 7.087712469183859, "grad_norm": 0.0006028738571330905, "learning_rate": 6.325214031040044e-06, "loss": 3.075253451243043e-05, "step": 54625 }, { "epoch": 7.090956273517581, "grad_norm": 0.0012554278364405036, "learning_rate": 6.304208073169873e-06, "loss": 2.9082796536386014e-05, "step": 54650 }, { "epoch": 7.094200077851304, "grad_norm": 0.0008951826021075249, "learning_rate": 6.283232020063079e-06, "loss": 3.1977954786270854e-05, "step": 54675 }, { "epoch": 7.0974438821850265, "grad_norm": 0.0013905389932915568, "learning_rate": 6.262285905271814e-06, "loss": 2.983429003506899e-05, "step": 54700 }, { "epoch": 7.100687686518749, "grad_norm": 0.0011013394687324762, "learning_rate": 6.2413697623003285e-06, "loss": 3.364760428667068e-05, "step": 54725 }, { "epoch": 7.103931490852472, "grad_norm": 0.0006471216329373419, "learning_rate": 6.220483624604945e-06, "loss": 3.370043588802218e-05, "step": 54750 }, { "epoch": 7.107175295186194, "grad_norm": 0.0011858808575198054, "learning_rate": 6.199627525593973e-06, "loss": 3.583506215363741e-05, "step": 54775 }, { "epoch": 7.110419099519917, "grad_norm": 0.000603158725425601, "learning_rate": 6.178801498627692e-06, "loss": 3.606767626479268e-05, "step": 54800 }, { "epoch": 7.11366290385364, "grad_norm": 0.00036229926627129316, "learning_rate": 6.15800557701828e-06, "loss": 3.174392739310861e-05, "step": 54825 }, { "epoch": 7.116906708187362, "grad_norm": 0.0004152697219979018, "learning_rate": 6.137239794029736e-06, "loss": 2.8653715271502734e-05, "step": 54850 }, { "epoch": 7.120150512521085, "grad_norm": 0.0007545107509940863, "learning_rate": 6.116504182877883e-06, "loss": 2.9651199001818894e-05, "step": 54875 }, { "epoch": 7.1233943168548075, "grad_norm": 0.0021577912848442793, "learning_rate": 6.0957987767302525e-06, "loss": 2.96894577331841e-05, "step": 54900 }, { "epoch": 7.12663812118853, "grad_norm": 0.0010389010421931744, "learning_rate": 6.075123608706093e-06, "loss": 2.8865528292953968e-05, "step": 54925 }, { "epoch": 7.129881925522253, "grad_norm": 0.0003853553789667785, "learning_rate": 6.054478711876252e-06, "loss": 3.1854636035859584e-05, "step": 54950 }, { "epoch": 7.133125729855975, "grad_norm": 0.0009502809843979776, "learning_rate": 6.033864119263191e-06, "loss": 3.423230489715934e-05, "step": 54975 }, { "epoch": 7.136369534189698, "grad_norm": 0.0006822927971370518, "learning_rate": 6.013279863840867e-06, "loss": 3.2679340802133086e-05, "step": 55000 }, { "epoch": 7.139613338523421, "grad_norm": 0.0004222654097247869, "learning_rate": 5.992725978534738e-06, "loss": 2.8362900484353303e-05, "step": 55025 }, { "epoch": 7.142857142857143, "grad_norm": 0.0005433803307823837, "learning_rate": 5.9722024962216625e-06, "loss": 2.6336601004004478e-05, "step": 55050 }, { "epoch": 7.146100947190866, "grad_norm": 0.001231854548677802, "learning_rate": 5.951709449729884e-06, "loss": 3.0436520464718342e-05, "step": 55075 }, { "epoch": 7.149344751524588, "grad_norm": 0.0002432300098007545, "learning_rate": 5.931246871838947e-06, "loss": 3.2233288511633876e-05, "step": 55100 }, { "epoch": 7.15258855585831, "grad_norm": 0.0009028833010233939, "learning_rate": 5.910814795279684e-06, "loss": 3.3035490196198226e-05, "step": 55125 }, { "epoch": 7.155832360192033, "grad_norm": 0.0007134227198548615, "learning_rate": 5.890413252734103e-06, "loss": 3.130696713924408e-05, "step": 55150 }, { "epoch": 7.1590761645257555, "grad_norm": 0.0010729209752753377, "learning_rate": 5.8700422768354135e-06, "loss": 2.6387320831418036e-05, "step": 55175 }, { "epoch": 7.162319968859478, "grad_norm": 0.0010258599650114775, "learning_rate": 5.849701900167895e-06, "loss": 3.0213198624551296e-05, "step": 55200 }, { "epoch": 7.162319968859478, "eval_loss": 0.00016240258992183954, "eval_runtime": 7.1103, "eval_samples_per_second": 703.2, "eval_steps_per_second": 5.626, "step": 55200 }, { "epoch": 7.162319968859478, "eval_holdout_avg_strict_f1": 0.27027175471999354, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7995018679950188, "eval_holdout_nemotron_pii_strict_f1": 0.788766395751187, "eval_holdout_open_pii_masking_500k_strict_f1": 0.7075873827791986, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.677133655394525, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 55200 }, { "epoch": 7.165563773193201, "grad_norm": 0.0005401122034527361, "learning_rate": 5.829392155266914e-06, "loss": 2.8261544648557902e-05, "step": 55225 }, { "epoch": 7.168807577526923, "grad_norm": 0.0005792956217192113, "learning_rate": 5.809113074618805e-06, "loss": 3.014218062162399e-05, "step": 55250 }, { "epoch": 7.172051381860646, "grad_norm": 0.0008677198202349246, "learning_rate": 5.788864690660894e-06, "loss": 2.9857668559998275e-05, "step": 55275 }, { "epoch": 7.175295186194369, "grad_norm": 0.0006581780617125332, "learning_rate": 5.768647035781366e-06, "loss": 2.831489313393831e-05, "step": 55300 }, { "epoch": 7.178538990528091, "grad_norm": 0.0010304006282240152, "learning_rate": 5.748460142319284e-06, "loss": 2.9868229757994415e-05, "step": 55325 }, { "epoch": 7.181782794861814, "grad_norm": 0.0007801263709552586, "learning_rate": 5.7283040425645e-06, "loss": 2.8266410809010267e-05, "step": 55350 }, { "epoch": 7.185026599195536, "grad_norm": 0.00040466219070367515, "learning_rate": 5.708178768757594e-06, "loss": 3.056906629353762e-05, "step": 55375 }, { "epoch": 7.188270403529259, "grad_norm": 0.0008539750706404448, "learning_rate": 5.688084353089862e-06, "loss": 2.9542322736233472e-05, "step": 55400 }, { "epoch": 7.191514207862982, "grad_norm": 0.0016860984032973647, "learning_rate": 5.668020827703216e-06, "loss": 2.9040786903351544e-05, "step": 55425 }, { "epoch": 7.194758012196704, "grad_norm": 0.00037862418685108423, "learning_rate": 5.647988224690184e-06, "loss": 3.0146378558129074e-05, "step": 55450 }, { "epoch": 7.198001816530427, "grad_norm": 0.0012698310893028975, "learning_rate": 5.627986576093808e-06, "loss": 3.2575817313045265e-05, "step": 55475 }, { "epoch": 7.2012456208641495, "grad_norm": 0.0004101961967535317, "learning_rate": 5.608015913907638e-06, "loss": 2.9886036645621062e-05, "step": 55500 }, { "epoch": 7.204489425197872, "grad_norm": 0.0005023861303925514, "learning_rate": 5.588076270075637e-06, "loss": 3.101048059761524e-05, "step": 55525 }, { "epoch": 7.207733229531595, "grad_norm": 0.0007202292908914387, "learning_rate": 5.568167676492183e-06, "loss": 3.038632683455944e-05, "step": 55550 }, { "epoch": 7.210977033865317, "grad_norm": 0.0008139288402162492, "learning_rate": 5.548290165001954e-06, "loss": 2.8685240540653467e-05, "step": 55575 }, { "epoch": 7.21422083819904, "grad_norm": 0.00030754992621950805, "learning_rate": 5.5284437673999405e-06, "loss": 2.4629866238683462e-05, "step": 55600 }, { "epoch": 7.217464642532763, "grad_norm": 0.0008148898486979306, "learning_rate": 5.508628515431338e-06, "loss": 3.068778198212385e-05, "step": 55625 }, { "epoch": 7.220708446866485, "grad_norm": 0.0007210280164144933, "learning_rate": 5.4888444407915516e-06, "loss": 3.192630130797625e-05, "step": 55650 }, { "epoch": 7.223952251200208, "grad_norm": 0.00041905161924660206, "learning_rate": 5.469091575126087e-06, "loss": 3.289227373898029e-05, "step": 55675 }, { "epoch": 7.2271960555339305, "grad_norm": 0.0009578230092301965, "learning_rate": 5.449369950030559e-06, "loss": 3.09354835189879e-05, "step": 55700 }, { "epoch": 7.230439859867653, "grad_norm": 0.0012072590179741383, "learning_rate": 5.429679597050585e-06, "loss": 3.0439947731792927e-05, "step": 55725 }, { "epoch": 7.233683664201376, "grad_norm": 0.0009624030790291727, "learning_rate": 5.410020547681785e-06, "loss": 3.135222010314465e-05, "step": 55750 }, { "epoch": 7.236927468535098, "grad_norm": 0.001061532530002296, "learning_rate": 5.390392833369684e-06, "loss": 3.2596585806459186e-05, "step": 55775 }, { "epoch": 7.240171272868821, "grad_norm": 0.00044869116391055286, "learning_rate": 5.370796485509711e-06, "loss": 3.08937206864357e-05, "step": 55800 }, { "epoch": 7.243415077202543, "grad_norm": 0.0006147156818769872, "learning_rate": 5.351231535447096e-06, "loss": 3.314969828352332e-05, "step": 55825 }, { "epoch": 7.246658881536265, "grad_norm": 0.0006316466606222093, "learning_rate": 5.331698014476863e-06, "loss": 2.804699121043086e-05, "step": 55850 }, { "epoch": 7.249902685869988, "grad_norm": 0.0005475491634570062, "learning_rate": 5.312195953843774e-06, "loss": 3.2425394747406246e-05, "step": 55875 }, { "epoch": 7.253146490203711, "grad_norm": 0.0007941272342577577, "learning_rate": 5.29272538474224e-06, "loss": 2.8892867267131805e-05, "step": 55900 }, { "epoch": 7.256390294537433, "grad_norm": 0.0006504007615149021, "learning_rate": 5.273286338316325e-06, "loss": 2.8862948529422283e-05, "step": 55925 }, { "epoch": 7.259634098871156, "grad_norm": 0.0005180260050110519, "learning_rate": 5.2538788456596574e-06, "loss": 3.530332120135426e-05, "step": 55950 }, { "epoch": 7.2628779032048785, "grad_norm": 0.0002359598147450015, "learning_rate": 5.2345029378154e-06, "loss": 3.12002026475966e-05, "step": 55975 }, { "epoch": 7.266121707538601, "grad_norm": 0.00045146889169700444, "learning_rate": 5.215158645776183e-06, "loss": 2.6608114130795e-05, "step": 56000 }, { "epoch": 7.269365511872324, "grad_norm": 0.0008349592098966241, "learning_rate": 5.195846000484089e-06, "loss": 3.224940272048116e-05, "step": 56025 }, { "epoch": 7.272609316206046, "grad_norm": 0.0004881212371401489, "learning_rate": 5.176565032830552e-06, "loss": 3.1529495026916264e-05, "step": 56050 }, { "epoch": 7.275853120539769, "grad_norm": 0.0005261751939542592, "learning_rate": 5.1573157736563685e-06, "loss": 3.25531791895628e-05, "step": 56075 }, { "epoch": 7.279096924873492, "grad_norm": 0.0005340432398952544, "learning_rate": 5.138098253751578e-06, "loss": 3.255143295973539e-05, "step": 56100 }, { "epoch": 7.282340729207214, "grad_norm": 0.0008619322907179594, "learning_rate": 5.118912503855486e-06, "loss": 3.2873761374503377e-05, "step": 56125 }, { "epoch": 7.285584533540937, "grad_norm": 0.001078384229913354, "learning_rate": 5.099758554656556e-06, "loss": 3.0998317524790766e-05, "step": 56150 }, { "epoch": 7.2888283378746594, "grad_norm": 0.0004515987238846719, "learning_rate": 5.0806364367923965e-06, "loss": 3.157262457534671e-05, "step": 56175 }, { "epoch": 7.292072142208382, "grad_norm": 0.0006215850589796901, "learning_rate": 5.06154618084971e-06, "loss": 3.081661649048328e-05, "step": 56200 }, { "epoch": 7.295315946542105, "grad_norm": 0.0006250146543607116, "learning_rate": 5.042487817364208e-06, "loss": 2.916564466431737e-05, "step": 56225 }, { "epoch": 7.298559750875827, "grad_norm": 0.0004554158076643944, "learning_rate": 5.023461376820612e-06, "loss": 3.48333059810102e-05, "step": 56250 }, { "epoch": 7.30180355520955, "grad_norm": 0.0006555641884915531, "learning_rate": 5.0044668896525675e-06, "loss": 3.117443528026342e-05, "step": 56275 }, { "epoch": 7.305047359543273, "grad_norm": 0.000833856116514653, "learning_rate": 4.985504386242623e-06, "loss": 3.2822636421769856e-05, "step": 56300 }, { "epoch": 7.308291163876995, "grad_norm": 0.0005123824230395257, "learning_rate": 4.966573896922145e-06, "loss": 3.04239708930254e-05, "step": 56325 }, { "epoch": 7.311534968210718, "grad_norm": 0.0016211020993068814, "learning_rate": 4.947675451971323e-06, "loss": 3.0105733312666416e-05, "step": 56350 }, { "epoch": 7.31477877254444, "grad_norm": 0.0018620297778397799, "learning_rate": 4.928809081619054e-06, "loss": 3.0018750112503768e-05, "step": 56375 }, { "epoch": 7.318022576878163, "grad_norm": 0.0007791253738105297, "learning_rate": 4.90997481604297e-06, "loss": 2.7024869341403244e-05, "step": 56400 }, { "epoch": 7.321266381211886, "grad_norm": 0.001185939647257328, "learning_rate": 4.891172685369308e-06, "loss": 2.9128922615200282e-05, "step": 56425 }, { "epoch": 7.324510185545608, "grad_norm": 0.001380518195219338, "learning_rate": 4.872402719672944e-06, "loss": 2.8011577669531106e-05, "step": 56450 }, { "epoch": 7.32775398987933, "grad_norm": 0.0006261465605348349, "learning_rate": 4.853664948977271e-06, "loss": 2.8948294930160045e-05, "step": 56475 }, { "epoch": 7.330997794213053, "grad_norm": 0.0005162999150343239, "learning_rate": 4.83495940325421e-06, "loss": 3.440576838329434e-05, "step": 56500 }, { "epoch": 7.334241598546775, "grad_norm": 0.0014552101492881775, "learning_rate": 4.816286112424117e-06, "loss": 3.144738031551242e-05, "step": 56525 }, { "epoch": 7.337485402880498, "grad_norm": 0.0008833386236801744, "learning_rate": 4.7976451063557745e-06, "loss": 2.9565144795924426e-05, "step": 56550 }, { "epoch": 7.3407292072142205, "grad_norm": 0.0005753789446316659, "learning_rate": 4.7790364148663e-06, "loss": 3.260873956605792e-05, "step": 56575 }, { "epoch": 7.343973011547943, "grad_norm": 0.0007353774853982031, "learning_rate": 4.760460067721151e-06, "loss": 3.059020731598139e-05, "step": 56600 }, { "epoch": 7.347216815881666, "grad_norm": 0.0009832524228841066, "learning_rate": 4.741916094634019e-06, "loss": 3.061054740101099e-05, "step": 56625 }, { "epoch": 7.350460620215388, "grad_norm": 0.00043144053779542446, "learning_rate": 4.723404525266839e-06, "loss": 3.114707302302122e-05, "step": 56650 }, { "epoch": 7.353704424549111, "grad_norm": 0.00047760512097738683, "learning_rate": 4.704925389229689e-06, "loss": 3.1001977622509005e-05, "step": 56675 }, { "epoch": 7.356948228882834, "grad_norm": 0.0005445010610856116, "learning_rate": 4.6864787160807885e-06, "loss": 3.551681758835912e-05, "step": 56700 }, { "epoch": 7.360192033216556, "grad_norm": 0.0014761778293177485, "learning_rate": 4.668064535326433e-06, "loss": 3.0459023546427487e-05, "step": 56725 }, { "epoch": 7.363435837550279, "grad_norm": 0.0008656695135869086, "learning_rate": 4.6496828764209185e-06, "loss": 2.853970043361187e-05, "step": 56750 }, { "epoch": 7.3666796418840015, "grad_norm": 0.0007133664330467582, "learning_rate": 4.631333768766555e-06, "loss": 3.0087551567703486e-05, "step": 56775 }, { "epoch": 7.369923446217724, "grad_norm": 0.0008190685184672475, "learning_rate": 4.613017241713552e-06, "loss": 2.9706640634685755e-05, "step": 56800 }, { "epoch": 7.373167250551447, "grad_norm": 0.001684527494944632, "learning_rate": 4.594733324560041e-06, "loss": 3.071740735322237e-05, "step": 56825 }, { "epoch": 7.376411054885169, "grad_norm": 0.0004567577561829239, "learning_rate": 4.5764820465519525e-06, "loss": 3.0713824089616536e-05, "step": 56850 }, { "epoch": 7.379654859218892, "grad_norm": 0.00041684965253807604, "learning_rate": 4.558263436883048e-06, "loss": 3.0096923001110554e-05, "step": 56875 }, { "epoch": 7.382898663552615, "grad_norm": 0.0008419897640123963, "learning_rate": 4.540077524694803e-06, "loss": 2.8848655056208372e-05, "step": 56900 }, { "epoch": 7.386142467886337, "grad_norm": 0.0007691522478125989, "learning_rate": 4.521924339076417e-06, "loss": 2.604119246825576e-05, "step": 56925 }, { "epoch": 7.38938627222006, "grad_norm": 0.000775771273765713, "learning_rate": 4.503803909064713e-06, "loss": 2.8593670576810838e-05, "step": 56950 }, { "epoch": 7.3926300765537825, "grad_norm": 0.0008992834482342005, "learning_rate": 4.485716263644157e-06, "loss": 3.1744956504553554e-05, "step": 56975 }, { "epoch": 7.395873880887505, "grad_norm": 0.00037082392373122275, "learning_rate": 4.467661431746739e-06, "loss": 2.6298202574253082e-05, "step": 57000 }, { "epoch": 7.399117685221228, "grad_norm": 0.0009002891601994634, "learning_rate": 4.449639442251991e-06, "loss": 2.68175033852458e-05, "step": 57025 }, { "epoch": 7.40236148955495, "grad_norm": 0.00035872607259079814, "learning_rate": 4.4316503239868855e-06, "loss": 3.1749852932989594e-05, "step": 57050 }, { "epoch": 7.405605293888673, "grad_norm": 0.0008143033483065665, "learning_rate": 4.413694105725841e-06, "loss": 2.9877088963985442e-05, "step": 57075 }, { "epoch": 7.408849098222396, "grad_norm": 0.0011936610098928213, "learning_rate": 4.395770816190628e-06, "loss": 3.0794462654739616e-05, "step": 57100 }, { "epoch": 7.412092902556118, "grad_norm": 0.00073219183832407, "learning_rate": 4.3778804840503705e-06, "loss": 2.7959174476563932e-05, "step": 57125 }, { "epoch": 7.415336706889841, "grad_norm": 0.0016457352321594954, "learning_rate": 4.360023137921451e-06, "loss": 3.190257353708148e-05, "step": 57150 }, { "epoch": 7.418580511223563, "grad_norm": 0.0008000028319656849, "learning_rate": 4.342198806367512e-06, "loss": 3.093251259997487e-05, "step": 57175 }, { "epoch": 7.421824315557286, "grad_norm": 0.0010476793395355344, "learning_rate": 4.324407517899362e-06, "loss": 2.742001786828041e-05, "step": 57200 }, { "epoch": 7.425068119891008, "grad_norm": 0.0005573015660047531, "learning_rate": 4.306649300974985e-06, "loss": 2.975484821945429e-05, "step": 57225 }, { "epoch": 7.42831192422473, "grad_norm": 0.001141621614806354, "learning_rate": 4.28892418399944e-06, "loss": 2.8471979312598706e-05, "step": 57250 }, { "epoch": 7.431555728558453, "grad_norm": 0.0005301169585436583, "learning_rate": 4.2712321953248565e-06, "loss": 3.0973220709711314e-05, "step": 57275 }, { "epoch": 7.434799532892176, "grad_norm": 0.0004922398366034031, "learning_rate": 4.2535733632503764e-06, "loss": 2.8482705820351838e-05, "step": 57300 }, { "epoch": 7.438043337225898, "grad_norm": 0.0005790420109406114, "learning_rate": 4.235947716022084e-06, "loss": 2.9645462054759263e-05, "step": 57325 }, { "epoch": 7.441287141559621, "grad_norm": 0.00049067527288571, "learning_rate": 4.218355281833011e-06, "loss": 2.7392669580876826e-05, "step": 57350 }, { "epoch": 7.4445309458933435, "grad_norm": 0.0004304159083403647, "learning_rate": 4.2007960888230415e-06, "loss": 2.9611734207719563e-05, "step": 57375 }, { "epoch": 7.447774750227066, "grad_norm": 0.0007949221762828529, "learning_rate": 4.1832701650789065e-06, "loss": 2.970017958432436e-05, "step": 57400 }, { "epoch": 7.451018554560789, "grad_norm": 0.0007842883351258934, "learning_rate": 4.165777538634103e-06, "loss": 3.2955866772681474e-05, "step": 57425 }, { "epoch": 7.454262358894511, "grad_norm": 0.0008068425231613219, "learning_rate": 4.148318237468882e-06, "loss": 3.117372747510672e-05, "step": 57450 }, { "epoch": 7.457506163228234, "grad_norm": 0.0009515131823718548, "learning_rate": 4.13089228951018e-06, "loss": 2.6591536588966846e-05, "step": 57475 }, { "epoch": 7.460749967561957, "grad_norm": 0.0014647155767306685, "learning_rate": 4.113499722631603e-06, "loss": 3.3305312972515824e-05, "step": 57500 }, { "epoch": 7.463993771895679, "grad_norm": 0.0006787348538637161, "learning_rate": 4.096140564653322e-06, "loss": 2.941866870969534e-05, "step": 57525 }, { "epoch": 7.467237576229402, "grad_norm": 0.0009636909235268831, "learning_rate": 4.078814843342108e-06, "loss": 3.271440044045448e-05, "step": 57550 }, { "epoch": 7.4704813805631245, "grad_norm": 0.0017434253823012114, "learning_rate": 4.0615225864112374e-06, "loss": 3.0704231467098e-05, "step": 57575 }, { "epoch": 7.473725184896847, "grad_norm": 0.0005882417899556458, "learning_rate": 4.044263821520447e-06, "loss": 2.9544178396463394e-05, "step": 57600 }, { "epoch": 7.47696898923057, "grad_norm": 0.0006475699483416975, "learning_rate": 4.027038576275921e-06, "loss": 2.6102873962372543e-05, "step": 57625 }, { "epoch": 7.480212793564292, "grad_norm": 0.0005724892835132778, "learning_rate": 4.009846878230206e-06, "loss": 2.884536515921354e-05, "step": 57650 }, { "epoch": 7.483456597898015, "grad_norm": 0.0005867668660357594, "learning_rate": 3.99268875488221e-06, "loss": 2.780701266601682e-05, "step": 57675 }, { "epoch": 7.486700402231738, "grad_norm": 0.00105752213858068, "learning_rate": 3.975564233677112e-06, "loss": 2.810284262523055e-05, "step": 57700 }, { "epoch": 7.48994420656546, "grad_norm": 0.0004584334965329617, "learning_rate": 3.958473342006374e-06, "loss": 2.9905298724770546e-05, "step": 57725 }, { "epoch": 7.493188010899183, "grad_norm": 0.0004577064246404916, "learning_rate": 3.941416107207638e-06, "loss": 3.207814181223512e-05, "step": 57750 }, { "epoch": 7.4964318152329055, "grad_norm": 0.0005401363596320152, "learning_rate": 3.924392556564727e-06, "loss": 2.9639785643666983e-05, "step": 57775 }, { "epoch": 7.499675619566628, "grad_norm": 0.0004938763449899852, "learning_rate": 3.9074027173075675e-06, "loss": 2.730945823714137e-05, "step": 57800 }, { "epoch": 7.502919423900351, "grad_norm": 0.0007033050642348826, "learning_rate": 3.890446616612192e-06, "loss": 3.0726459808647636e-05, "step": 57825 }, { "epoch": 7.5061632282340724, "grad_norm": 0.0005998477572575212, "learning_rate": 3.8735242816006325e-06, "loss": 2.6561310514807703e-05, "step": 57850 }, { "epoch": 7.509407032567795, "grad_norm": 0.0007337959832511842, "learning_rate": 3.856635739340944e-06, "loss": 2.90592759847641e-05, "step": 57875 }, { "epoch": 7.512650836901518, "grad_norm": 0.0008921536500565708, "learning_rate": 3.839781016847096e-06, "loss": 2.8643517289310694e-05, "step": 57900 }, { "epoch": 7.51589464123524, "grad_norm": 0.0006541276234202087, "learning_rate": 3.822960141078991e-06, "loss": 2.960111014544964e-05, "step": 57925 }, { "epoch": 7.519138445568963, "grad_norm": 0.0005299533950164914, "learning_rate": 3.8061731389423706e-06, "loss": 2.90573644451797e-05, "step": 57950 }, { "epoch": 7.522382249902686, "grad_norm": 0.00030474679078906775, "learning_rate": 3.7894200372888126e-06, "loss": 2.552158897742629e-05, "step": 57975 }, { "epoch": 7.525626054236408, "grad_norm": 0.0010075998725369573, "learning_rate": 3.772700862915646e-06, "loss": 3.139069071039557e-05, "step": 58000 }, { "epoch": 7.528869858570131, "grad_norm": 0.0008111704373732209, "learning_rate": 3.75601564256596e-06, "loss": 3.166574519127607e-05, "step": 58025 }, { "epoch": 7.532113662903853, "grad_norm": 0.0010781452292576432, "learning_rate": 3.739364402928505e-06, "loss": 2.8476731386035682e-05, "step": 58050 }, { "epoch": 7.535357467237576, "grad_norm": 0.0007439548498950899, "learning_rate": 3.7227471706377025e-06, "loss": 3.12680029310286e-05, "step": 58075 }, { "epoch": 7.538601271571299, "grad_norm": 0.00081039679935202, "learning_rate": 3.7061639722735518e-06, "loss": 2.8568876441568136e-05, "step": 58100 }, { "epoch": 7.541845075905021, "grad_norm": 0.0010989760048687458, "learning_rate": 3.6896148343616378e-06, "loss": 3.184813307598233e-05, "step": 58125 }, { "epoch": 7.545088880238744, "grad_norm": 0.00047176668886095285, "learning_rate": 3.6730997833730547e-06, "loss": 3.46767227165401e-05, "step": 58150 }, { "epoch": 7.5483326845724665, "grad_norm": 0.000339658057782799, "learning_rate": 3.656618845724366e-06, "loss": 2.908339723944664e-05, "step": 58175 }, { "epoch": 7.551576488906189, "grad_norm": 0.0009604947408661246, "learning_rate": 3.640172047777582e-06, "loss": 2.967125503346324e-05, "step": 58200 }, { "epoch": 7.554820293239912, "grad_norm": 0.0005066393641754985, "learning_rate": 3.6237594158400917e-06, "loss": 2.7889457996934652e-05, "step": 58225 }, { "epoch": 7.558064097573634, "grad_norm": 0.0010395338758826256, "learning_rate": 3.607380976164651e-06, "loss": 3.181473119184375e-05, "step": 58250 }, { "epoch": 7.561307901907357, "grad_norm": 0.0007048261468298733, "learning_rate": 3.591036754949301e-06, "loss": 3.124364884570241e-05, "step": 58275 }, { "epoch": 7.56455170624108, "grad_norm": 0.000421168195316568, "learning_rate": 3.574726778337373e-06, "loss": 3.11366724781692e-05, "step": 58300 }, { "epoch": 7.567795510574802, "grad_norm": 0.0009839459089562297, "learning_rate": 3.5584510724173986e-06, "loss": 2.96004768460989e-05, "step": 58325 }, { "epoch": 7.571039314908525, "grad_norm": 0.0009195516468025744, "learning_rate": 3.54220966322312e-06, "loss": 3.250130917876959e-05, "step": 58350 }, { "epoch": 7.5742831192422475, "grad_norm": 0.00023111737391445786, "learning_rate": 3.5260025767333893e-06, "loss": 2.666354412212968e-05, "step": 58375 }, { "epoch": 7.57752692357597, "grad_norm": 0.0004932254669256508, "learning_rate": 3.5098298388721863e-06, "loss": 2.985968952998519e-05, "step": 58400 }, { "epoch": 7.580770727909693, "grad_norm": 0.0007809114176779985, "learning_rate": 3.4936914755085232e-06, "loss": 3.132485086098313e-05, "step": 58425 }, { "epoch": 7.584014532243415, "grad_norm": 0.0010805283673107624, "learning_rate": 3.4775875124564537e-06, "loss": 2.8980502393096685e-05, "step": 58450 }, { "epoch": 7.587258336577138, "grad_norm": 0.00044113374315202236, "learning_rate": 3.4615179754749817e-06, "loss": 3.21932602673769e-05, "step": 58475 }, { "epoch": 7.590502140910861, "grad_norm": 0.0009093332919292152, "learning_rate": 3.4454828902680676e-06, "loss": 3.480183891952038e-05, "step": 58500 }, { "epoch": 7.593745945244583, "grad_norm": 0.0008436348871327937, "learning_rate": 3.4294822824845446e-06, "loss": 3.15528828650713e-05, "step": 58525 }, { "epoch": 7.596989749578306, "grad_norm": 0.001520398072898388, "learning_rate": 3.413516177718118e-06, "loss": 2.9757467564195396e-05, "step": 58550 }, { "epoch": 7.6002335539120285, "grad_norm": 0.0003466570342425257, "learning_rate": 3.397584601507281e-06, "loss": 2.855917438864708e-05, "step": 58575 }, { "epoch": 7.603477358245751, "grad_norm": 0.0017931723268702626, "learning_rate": 3.3816875793353214e-06, "loss": 2.8249917086213827e-05, "step": 58600 }, { "epoch": 7.606721162579473, "grad_norm": 0.0005235878634266555, "learning_rate": 3.3658251366302325e-06, "loss": 2.541928319260478e-05, "step": 58625 }, { "epoch": 7.6099649669131955, "grad_norm": 0.00030234039877541363, "learning_rate": 3.349997298764712e-06, "loss": 2.874713623896241e-05, "step": 58650 }, { "epoch": 7.6099649669131955, "eval_loss": 0.00015611642447765917, "eval_runtime": 7.1735, "eval_samples_per_second": 697.013, "eval_steps_per_second": 5.576, "step": 58650 }, { "epoch": 7.6099649669131955, "eval_holdout_avg_strict_f1": 0.257939534918839, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7278131634819534, "eval_holdout_nemotron_pii_strict_f1": 0.7312611540749554, "eval_holdout_open_pii_masking_500k_strict_f1": 0.7100056529112492, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.668254913639071, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 58650 }, { "epoch": 7.613208771246918, "grad_norm": 0.0007035768940113485, "learning_rate": 3.334204091056109e-06, "loss": 3.156593767926097e-05, "step": 58675 }, { "epoch": 7.616452575580641, "grad_norm": 0.0008929967880249023, "learning_rate": 3.3184455387663625e-06, "loss": 3.182070329785347e-05, "step": 58700 }, { "epoch": 7.619696379914363, "grad_norm": 0.0007325185579247773, "learning_rate": 3.302721667101996e-06, "loss": 2.706922125071287e-05, "step": 58725 }, { "epoch": 7.622940184248086, "grad_norm": 0.0010217905510216951, "learning_rate": 3.2870325012140407e-06, "loss": 3.161631990224123e-05, "step": 58750 }, { "epoch": 7.626183988581809, "grad_norm": 0.0003187840338796377, "learning_rate": 3.2713780661980414e-06, "loss": 3.166717942804098e-05, "step": 58775 }, { "epoch": 7.629427792915531, "grad_norm": 0.00118625711183995, "learning_rate": 3.2557583870939603e-06, "loss": 2.9507919680327178e-05, "step": 58800 }, { "epoch": 7.632671597249254, "grad_norm": 0.00039222295163199306, "learning_rate": 3.240173488886189e-06, "loss": 2.8454307466745378e-05, "step": 58825 }, { "epoch": 7.635915401582976, "grad_norm": 0.0008771861321292818, "learning_rate": 3.224623396503465e-06, "loss": 2.9450040310621263e-05, "step": 58850 }, { "epoch": 7.639159205916699, "grad_norm": 0.0009460158180445433, "learning_rate": 3.209108134818878e-06, "loss": 2.7766129933297633e-05, "step": 58875 }, { "epoch": 7.642403010250422, "grad_norm": 0.0004425251972861588, "learning_rate": 3.193627728649773e-06, "loss": 2.8317777905613182e-05, "step": 58900 }, { "epoch": 7.645646814584144, "grad_norm": 0.0005928045720793307, "learning_rate": 3.1781822027577764e-06, "loss": 2.8410330414772034e-05, "step": 58925 }, { "epoch": 7.648890618917867, "grad_norm": 0.0004412206762935966, "learning_rate": 3.1627715818486865e-06, "loss": 2.7760174125432967e-05, "step": 58950 }, { "epoch": 7.6521344232515895, "grad_norm": 0.0006123582134023309, "learning_rate": 3.147395890572502e-06, "loss": 2.9001960065215826e-05, "step": 58975 }, { "epoch": 7.655378227585312, "grad_norm": 0.0014199184952303767, "learning_rate": 3.1320551535233252e-06, "loss": 3.0119947623461485e-05, "step": 59000 }, { "epoch": 7.658622031919035, "grad_norm": 0.0016778395511209965, "learning_rate": 3.1167493952393684e-06, "loss": 3.2470347359776494e-05, "step": 59025 }, { "epoch": 7.661865836252757, "grad_norm": 0.001262235571630299, "learning_rate": 3.101478640202873e-06, "loss": 3.285175655037165e-05, "step": 59050 }, { "epoch": 7.66510964058648, "grad_norm": 0.0006035053520463407, "learning_rate": 3.086242912840101e-06, "loss": 2.678109798580408e-05, "step": 59075 }, { "epoch": 7.668353444920203, "grad_norm": 0.001020268420688808, "learning_rate": 3.071042237521296e-06, "loss": 3.0018610414117574e-05, "step": 59100 }, { "epoch": 7.671597249253925, "grad_norm": 0.00028606245177797973, "learning_rate": 3.0558766385606117e-06, "loss": 2.7814465574920178e-05, "step": 59125 }, { "epoch": 7.674841053587648, "grad_norm": 0.0009291644673794508, "learning_rate": 3.0407461402161218e-06, "loss": 3.005111822858453e-05, "step": 59150 }, { "epoch": 7.6780848579213705, "grad_norm": 0.0021188557147979736, "learning_rate": 3.0256507666897305e-06, "loss": 2.8700255788862706e-05, "step": 59175 }, { "epoch": 7.681328662255093, "grad_norm": 0.0015669817803427577, "learning_rate": 3.0105905421271784e-06, "loss": 2.7488616760820152e-05, "step": 59200 }, { "epoch": 7.684572466588815, "grad_norm": 0.0007798831793479621, "learning_rate": 2.9955654906179657e-06, "loss": 2.5479281321167944e-05, "step": 59225 }, { "epoch": 7.6878162709225375, "grad_norm": 0.0007052512373775244, "learning_rate": 2.9805756361953487e-06, "loss": 2.8311689384281635e-05, "step": 59250 }, { "epoch": 7.69106007525626, "grad_norm": 0.0006690274458378553, "learning_rate": 2.965621002836269e-06, "loss": 2.967750187963247e-05, "step": 59275 }, { "epoch": 7.694303879589983, "grad_norm": 0.0009559484897181392, "learning_rate": 2.9507016144613485e-06, "loss": 3.124128561466932e-05, "step": 59300 }, { "epoch": 7.697547683923705, "grad_norm": 0.00067644112277776, "learning_rate": 2.935817494934809e-06, "loss": 2.6180364657193422e-05, "step": 59325 }, { "epoch": 7.700791488257428, "grad_norm": 0.00043752463534474373, "learning_rate": 2.9209686680644833e-06, "loss": 3.128190757706761e-05, "step": 59350 }, { "epoch": 7.704035292591151, "grad_norm": 0.0004280533466953784, "learning_rate": 2.9061551576017336e-06, "loss": 3.009839914739132e-05, "step": 59375 }, { "epoch": 7.707279096924873, "grad_norm": 0.0018487060442566872, "learning_rate": 2.8913769872414425e-06, "loss": 2.7658403851091862e-05, "step": 59400 }, { "epoch": 7.710522901258596, "grad_norm": 0.000551651930436492, "learning_rate": 2.8766341806219564e-06, "loss": 2.8137690387666227e-05, "step": 59425 }, { "epoch": 7.7137667055923185, "grad_norm": 0.0012191948480904102, "learning_rate": 2.8619267613250706e-06, "loss": 2.9049040749669073e-05, "step": 59450 }, { "epoch": 7.717010509926041, "grad_norm": 0.0004318011342547834, "learning_rate": 2.84725475287595e-06, "loss": 2.937434008345008e-05, "step": 59475 }, { "epoch": 7.720254314259764, "grad_norm": 0.0007280393037945032, "learning_rate": 2.832618178743146e-06, "loss": 3.167336108162999e-05, "step": 59500 }, { "epoch": 7.723498118593486, "grad_norm": 0.0009913684334605932, "learning_rate": 2.818017062338521e-06, "loss": 3.089945530518889e-05, "step": 59525 }, { "epoch": 7.726741922927209, "grad_norm": 0.0006008000345900655, "learning_rate": 2.8034514270172117e-06, "loss": 3.089678473770618e-05, "step": 59550 }, { "epoch": 7.729985727260932, "grad_norm": 0.001095401938073337, "learning_rate": 2.7889212960776207e-06, "loss": 2.9661227017641068e-05, "step": 59575 }, { "epoch": 7.733229531594654, "grad_norm": 0.001202347339130938, "learning_rate": 2.7744266927613364e-06, "loss": 2.9379173647612332e-05, "step": 59600 }, { "epoch": 7.736473335928377, "grad_norm": 0.0007041720673441887, "learning_rate": 2.7599676402531415e-06, "loss": 3.0369732994586228e-05, "step": 59625 }, { "epoch": 7.7397171402620994, "grad_norm": 0.0011109834304079413, "learning_rate": 2.745544161680935e-06, "loss": 3.190988441929221e-05, "step": 59650 }, { "epoch": 7.742960944595822, "grad_norm": 0.0011997534893453121, "learning_rate": 2.7311562801157293e-06, "loss": 2.9389006085693838e-05, "step": 59675 }, { "epoch": 7.746204748929545, "grad_norm": 0.000733245222363621, "learning_rate": 2.7168040185715837e-06, "loss": 3.551604226231575e-05, "step": 59700 }, { "epoch": 7.749448553263267, "grad_norm": 0.00042684763320721686, "learning_rate": 2.702487400005596e-06, "loss": 3.0186052899807692e-05, "step": 59725 }, { "epoch": 7.75269235759699, "grad_norm": 0.0009562341729179025, "learning_rate": 2.688206447317837e-06, "loss": 3.385470947250724e-05, "step": 59750 }, { "epoch": 7.755936161930713, "grad_norm": 0.0006558267632499337, "learning_rate": 2.673961183351342e-06, "loss": 3.295607632026076e-05, "step": 59775 }, { "epoch": 7.759179966264435, "grad_norm": 0.0006195763708092272, "learning_rate": 2.659751630892046e-06, "loss": 2.788100391626358e-05, "step": 59800 }, { "epoch": 7.762423770598158, "grad_norm": 0.0012773778289556503, "learning_rate": 2.645577812668779e-06, "loss": 2.739660209044814e-05, "step": 59825 }, { "epoch": 7.76566757493188, "grad_norm": 0.00038902927190065384, "learning_rate": 2.6314397513531956e-06, "loss": 2.9335729777812958e-05, "step": 59850 }, { "epoch": 7.768911379265603, "grad_norm": 0.0005080652190372348, "learning_rate": 2.617337469559769e-06, "loss": 2.793335122987628e-05, "step": 59875 }, { "epoch": 7.772155183599326, "grad_norm": 0.000522421847563237, "learning_rate": 2.6032709898457296e-06, "loss": 3.082294948399067e-05, "step": 59900 }, { "epoch": 7.775398987933048, "grad_norm": 0.0013000437757000327, "learning_rate": 2.5892403347110546e-06, "loss": 3.077842528000474e-05, "step": 59925 }, { "epoch": 7.778642792266771, "grad_norm": 0.0006516584544442594, "learning_rate": 2.5752455265983992e-06, "loss": 2.8498061001300813e-05, "step": 59950 }, { "epoch": 7.7818865966004935, "grad_norm": 0.000365038140444085, "learning_rate": 2.5612865878931053e-06, "loss": 3.078631358221173e-05, "step": 59975 }, { "epoch": 7.785130400934215, "grad_norm": 0.0006857931148260832, "learning_rate": 2.5473635409231145e-06, "loss": 2.8984884265810252e-05, "step": 60000 }, { "epoch": 7.788374205267938, "grad_norm": 0.0005304475780576468, "learning_rate": 2.5334764079589705e-06, "loss": 2.684429520741105e-05, "step": 60025 }, { "epoch": 7.7916180096016605, "grad_norm": 0.0006053026882000268, "learning_rate": 2.5196252112137776e-06, "loss": 2.6950868777930738e-05, "step": 60050 }, { "epoch": 7.794861813935383, "grad_norm": 0.0006378001999109983, "learning_rate": 2.50580997284314e-06, "loss": 2.49851169064641e-05, "step": 60075 }, { "epoch": 7.798105618269106, "grad_norm": 0.0008724414510652423, "learning_rate": 2.492030714945162e-06, "loss": 3.206246998161078e-05, "step": 60100 }, { "epoch": 7.801349422602828, "grad_norm": 0.0008377624908462167, "learning_rate": 2.4782874595603855e-06, "loss": 2.9878204222768546e-05, "step": 60125 }, { "epoch": 7.804593226936551, "grad_norm": 0.00042597897117957473, "learning_rate": 2.464580228671773e-06, "loss": 2.7569746598601342e-05, "step": 60150 }, { "epoch": 7.807837031270274, "grad_norm": 0.0005963167059235275, "learning_rate": 2.4509090442046494e-06, "loss": 2.570105018094182e-05, "step": 60175 }, { "epoch": 7.811080835603996, "grad_norm": 0.0003872034722007811, "learning_rate": 2.437273928026704e-06, "loss": 2.872746204957366e-05, "step": 60200 }, { "epoch": 7.814324639937719, "grad_norm": 0.0013757625129073858, "learning_rate": 2.4236749019479117e-06, "loss": 3.417798550799489e-05, "step": 60225 }, { "epoch": 7.8175684442714415, "grad_norm": 0.0006258471985347569, "learning_rate": 2.410111987720534e-06, "loss": 2.8147855773568152e-05, "step": 60250 }, { "epoch": 7.820812248605164, "grad_norm": 0.0010281677823513746, "learning_rate": 2.3965852070390566e-06, "loss": 2.830254379659891e-05, "step": 60275 }, { "epoch": 7.824056052938887, "grad_norm": 0.0009954918641597033, "learning_rate": 2.383094581540188e-06, "loss": 3.4631711896508934e-05, "step": 60300 }, { "epoch": 7.827299857272609, "grad_norm": 0.0007176375947892666, "learning_rate": 2.3696401328027806e-06, "loss": 3.217629389837384e-05, "step": 60325 }, { "epoch": 7.830543661606332, "grad_norm": 0.0006163505604490638, "learning_rate": 2.356221882347845e-06, "loss": 2.9807230457663536e-05, "step": 60350 }, { "epoch": 7.833787465940055, "grad_norm": 0.0008052123012021184, "learning_rate": 2.3428398516384647e-06, "loss": 2.9175840318202972e-05, "step": 60375 }, { "epoch": 7.837031270273777, "grad_norm": 0.000650119676720351, "learning_rate": 2.3294940620798178e-06, "loss": 3.0294223688542842e-05, "step": 60400 }, { "epoch": 7.8402750746075, "grad_norm": 0.0006105866050347686, "learning_rate": 2.3161845350190835e-06, "loss": 2.843949943780899e-05, "step": 60425 }, { "epoch": 7.8435188789412225, "grad_norm": 0.0005992742953822017, "learning_rate": 2.3029112917454606e-06, "loss": 2.6884444523602724e-05, "step": 60450 }, { "epoch": 7.846762683274945, "grad_norm": 0.0008874275372363627, "learning_rate": 2.2896743534900927e-06, "loss": 2.857938641682267e-05, "step": 60475 }, { "epoch": 7.850006487608668, "grad_norm": 0.0007620751857757568, "learning_rate": 2.276473741426069e-06, "loss": 3.192539559677243e-05, "step": 60500 }, { "epoch": 7.85325029194239, "grad_norm": 0.0008901011315174401, "learning_rate": 2.2633094766683573e-06, "loss": 3.125506220385432e-05, "step": 60525 }, { "epoch": 7.856494096276113, "grad_norm": 0.00048741488717496395, "learning_rate": 2.2501815802738023e-06, "loss": 3.0611364636570215e-05, "step": 60550 }, { "epoch": 7.859737900609836, "grad_norm": 0.0006303457194007933, "learning_rate": 2.237090073241055e-06, "loss": 2.8309898916631936e-05, "step": 60575 }, { "epoch": 7.862981704943558, "grad_norm": 0.0006736425566487014, "learning_rate": 2.2240349765105835e-06, "loss": 2.9868928249925377e-05, "step": 60600 }, { "epoch": 7.86622550927728, "grad_norm": 0.0011805212125182152, "learning_rate": 2.2110163109646004e-06, "loss": 2.9033762402832508e-05, "step": 60625 }, { "epoch": 7.8694693136110025, "grad_norm": 0.0008291802369058132, "learning_rate": 2.198034097427043e-06, "loss": 2.8551414143294096e-05, "step": 60650 }, { "epoch": 7.872713117944725, "grad_norm": 0.0009516424033790827, "learning_rate": 2.185088356663559e-06, "loss": 2.8224249836057424e-05, "step": 60675 }, { "epoch": 7.875956922278448, "grad_norm": 0.0008838971843943, "learning_rate": 2.172179109381434e-06, "loss": 2.9929408337920905e-05, "step": 60700 }, { "epoch": 7.87920072661217, "grad_norm": 0.0008837844943627715, "learning_rate": 2.1593063762296e-06, "loss": 2.850657096132636e-05, "step": 60725 }, { "epoch": 7.882444530945893, "grad_norm": 0.0011627132771536708, "learning_rate": 2.1464701777985706e-06, "loss": 2.9398491606116294e-05, "step": 60750 }, { "epoch": 7.885688335279616, "grad_norm": 0.0005171240773051977, "learning_rate": 2.13367053462043e-06, "loss": 3.1629009172320365e-05, "step": 60775 }, { "epoch": 7.888932139613338, "grad_norm": 0.0006433556554839015, "learning_rate": 2.1209074671687785e-06, "loss": 2.9274686239659788e-05, "step": 60800 }, { "epoch": 7.892175943947061, "grad_norm": 0.0009107575169764459, "learning_rate": 2.1081809958587273e-06, "loss": 3.075175220146775e-05, "step": 60825 }, { "epoch": 7.8954197482807835, "grad_norm": 0.0006209394778124988, "learning_rate": 2.095491141046832e-06, "loss": 2.7028578333556652e-05, "step": 60850 }, { "epoch": 7.898663552614506, "grad_norm": 0.00036491791252046824, "learning_rate": 2.0828379230310944e-06, "loss": 3.258896991610527e-05, "step": 60875 }, { "epoch": 7.901907356948229, "grad_norm": 0.00047198269749060273, "learning_rate": 2.0702213620509087e-06, "loss": 2.84541305154562e-05, "step": 60900 }, { "epoch": 7.905151161281951, "grad_norm": 0.00148151780012995, "learning_rate": 2.0576414782870314e-06, "loss": 3.3009317703545094e-05, "step": 60925 }, { "epoch": 7.908394965615674, "grad_norm": 0.0008600982837378979, "learning_rate": 2.0450982918615553e-06, "loss": 3.4356992691755296e-05, "step": 60950 }, { "epoch": 7.911638769949397, "grad_norm": 0.0005191646050661802, "learning_rate": 2.032591822837873e-06, "loss": 2.7670045383274556e-05, "step": 60975 }, { "epoch": 7.914882574283119, "grad_norm": 0.0005074518849141896, "learning_rate": 2.0201220912206497e-06, "loss": 2.4669512640684843e-05, "step": 61000 }, { "epoch": 7.918126378616842, "grad_norm": 0.0007482867804355919, "learning_rate": 2.007689116955777e-06, "loss": 2.7177357114851475e-05, "step": 61025 }, { "epoch": 7.9213701829505645, "grad_norm": 0.0009982716292142868, "learning_rate": 1.9952929199303696e-06, "loss": 3.065736498683691e-05, "step": 61050 }, { "epoch": 7.924613987284287, "grad_norm": 0.0005679767346009612, "learning_rate": 1.9829335199726905e-06, "loss": 2.7047055773437023e-05, "step": 61075 }, { "epoch": 7.92785779161801, "grad_norm": 0.000845395668875426, "learning_rate": 1.970610936852174e-06, "loss": 2.8884143102914094e-05, "step": 61100 }, { "epoch": 7.931101595951732, "grad_norm": 0.0006287300493568182, "learning_rate": 1.9583251902793308e-06, "loss": 2.808419521898031e-05, "step": 61125 }, { "epoch": 7.934345400285455, "grad_norm": 0.0004969409201294184, "learning_rate": 1.946076299905783e-06, "loss": 2.5891836266964673e-05, "step": 61150 }, { "epoch": 7.937589204619178, "grad_norm": 0.0010617219377309084, "learning_rate": 1.9338642853241715e-06, "loss": 2.9615857638418674e-05, "step": 61175 }, { "epoch": 7.9408330089529, "grad_norm": 0.0012685711262747645, "learning_rate": 1.9216891660681773e-06, "loss": 3.3230369444936515e-05, "step": 61200 }, { "epoch": 7.944076813286623, "grad_norm": 0.0006532258121296763, "learning_rate": 1.9095509616124385e-06, "loss": 3.0815673526376485e-05, "step": 61225 }, { "epoch": 7.9473206176203455, "grad_norm": 0.0006863688468001783, "learning_rate": 1.897449691372577e-06, "loss": 2.875622361898422e-05, "step": 61250 }, { "epoch": 7.950564421954068, "grad_norm": 0.00039831214235164225, "learning_rate": 1.8853853747051093e-06, "loss": 2.8143234085291625e-05, "step": 61275 }, { "epoch": 7.953808226287791, "grad_norm": 0.0006428117048926651, "learning_rate": 1.87335803090746e-06, "loss": 3.221742808818817e-05, "step": 61300 }, { "epoch": 7.957052030621513, "grad_norm": 0.001042845193296671, "learning_rate": 1.8613676792179041e-06, "loss": 3.3050933852791785e-05, "step": 61325 }, { "epoch": 7.960295834955236, "grad_norm": 0.0005571756628341973, "learning_rate": 1.8494143388155582e-06, "loss": 2.866826020181179e-05, "step": 61350 }, { "epoch": 7.963539639288959, "grad_norm": 0.0005663415649905801, "learning_rate": 1.8374980288203224e-06, "loss": 3.1165934633463624e-05, "step": 61375 }, { "epoch": 7.96678344362268, "grad_norm": 0.00038313542609103024, "learning_rate": 1.8256187682928805e-06, "loss": 3.198102582246065e-05, "step": 61400 }, { "epoch": 7.970027247956403, "grad_norm": 0.0007085010875016451, "learning_rate": 1.8137765762346354e-06, "loss": 3.168303752318024e-05, "step": 61425 }, { "epoch": 7.973271052290126, "grad_norm": 0.0007098246715031564, "learning_rate": 1.8019714715877155e-06, "loss": 3.198208753019571e-05, "step": 61450 }, { "epoch": 7.976514856623848, "grad_norm": 0.001035662367939949, "learning_rate": 1.7902034732349193e-06, "loss": 2.4922406300902366e-05, "step": 61475 }, { "epoch": 7.979758660957571, "grad_norm": 0.000782371440436691, "learning_rate": 1.7784725999996865e-06, "loss": 3.147483104839921e-05, "step": 61500 }, { "epoch": 7.983002465291293, "grad_norm": 0.00028309342451393604, "learning_rate": 1.7667788706460854e-06, "loss": 2.949845977127552e-05, "step": 61525 }, { "epoch": 7.986246269625016, "grad_norm": 0.0018380340188741684, "learning_rate": 1.7551223038787563e-06, "loss": 3.2810531556606294e-05, "step": 61550 }, { "epoch": 7.989490073958739, "grad_norm": 0.0005140802240930498, "learning_rate": 1.7435029183429125e-06, "loss": 2.8340446297079323e-05, "step": 61575 }, { "epoch": 7.992733878292461, "grad_norm": 0.0008447719155810773, "learning_rate": 1.7319207326242787e-06, "loss": 2.7902149595320226e-05, "step": 61600 }, { "epoch": 7.995977682626184, "grad_norm": 0.0004993216716684401, "learning_rate": 1.7203757652490882e-06, "loss": 2.77311890386045e-05, "step": 61625 }, { "epoch": 7.9992214869599065, "grad_norm": 0.0004892786382697523, "learning_rate": 1.708868034684033e-06, "loss": 2.9363958165049554e-05, "step": 61650 }, { "epoch": 8.00246529129363, "grad_norm": 0.001242434373125434, "learning_rate": 1.6973975593362558e-06, "loss": 2.8578708879649638e-05, "step": 61675 }, { "epoch": 8.005709095627351, "grad_norm": 0.0007915363530628383, "learning_rate": 1.6859643575532879e-06, "loss": 2.9141008853912352e-05, "step": 61700 }, { "epoch": 8.008952899961074, "grad_norm": 0.0003694870392791927, "learning_rate": 1.674568447623065e-06, "loss": 3.177159233018756e-05, "step": 61725 }, { "epoch": 8.012196704294796, "grad_norm": 0.0007114773034118116, "learning_rate": 1.66320984777385e-06, "loss": 2.8864985797554254e-05, "step": 61750 }, { "epoch": 8.015440508628519, "grad_norm": 0.0002570650540292263, "learning_rate": 1.651888576174243e-06, "loss": 2.8630162123590708e-05, "step": 61775 }, { "epoch": 8.018684312962241, "grad_norm": 0.0005904339486733079, "learning_rate": 1.6406046509331196e-06, "loss": 2.689769258722663e-05, "step": 61800 }, { "epoch": 8.021928117295964, "grad_norm": 0.0006277205538935959, "learning_rate": 1.629358090099639e-06, "loss": 2.9507705476135017e-05, "step": 61825 }, { "epoch": 8.025171921629687, "grad_norm": 0.0006323136040009558, "learning_rate": 1.6181489116631754e-06, "loss": 3.000140888616443e-05, "step": 61850 }, { "epoch": 8.02841572596341, "grad_norm": 0.0008605141774751246, "learning_rate": 1.6069771335533224e-06, "loss": 3.087865188717842e-05, "step": 61875 }, { "epoch": 8.031659530297132, "grad_norm": 0.001596612622961402, "learning_rate": 1.5958427736398356e-06, "loss": 2.976176096126437e-05, "step": 61900 }, { "epoch": 8.034903334630854, "grad_norm": 0.0007155778585001826, "learning_rate": 1.584745849732633e-06, "loss": 2.9215090908110142e-05, "step": 61925 }, { "epoch": 8.038147138964577, "grad_norm": 0.0004397827142383903, "learning_rate": 1.5736863795817402e-06, "loss": 2.909528324380517e-05, "step": 61950 }, { "epoch": 8.0413909432983, "grad_norm": 0.00043415059917606413, "learning_rate": 1.5626643808772795e-06, "loss": 2.7467028703540565e-05, "step": 61975 }, { "epoch": 8.044634747632022, "grad_norm": 0.0003006460901815444, "learning_rate": 1.551679871249445e-06, "loss": 2.914737444370985e-05, "step": 62000 }, { "epoch": 8.047878551965745, "grad_norm": 0.000867878261487931, "learning_rate": 1.5407328682684435e-06, "loss": 2.700258744880557e-05, "step": 62025 }, { "epoch": 8.051122356299468, "grad_norm": 0.000633187242783606, "learning_rate": 1.5298233894445068e-06, "loss": 3.028122941032052e-05, "step": 62050 }, { "epoch": 8.05436616063319, "grad_norm": 0.000897703692317009, "learning_rate": 1.5189514522278375e-06, "loss": 2.8769795317202807e-05, "step": 62075 }, { "epoch": 8.057609964966913, "grad_norm": 0.00043442012974992394, "learning_rate": 1.5081170740085943e-06, "loss": 3.2013324089348315e-05, "step": 62100 }, { "epoch": 8.057609964966913, "eval_loss": 0.00015410580090247095, "eval_runtime": 6.5381, "eval_samples_per_second": 764.748, "eval_steps_per_second": 6.118, "step": 62100 }, { "epoch": 8.057609964966913, "eval_holdout_avg_strict_f1": 0.25788216335340947, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7012740580103008, "eval_holdout_nemotron_pii_strict_f1": 0.7513040810064435, "eval_holdout_open_pii_masking_500k_strict_f1": 0.7095130237825593, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.6746126340882003, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 62100 }, { "epoch": 8.060853769300635, "grad_norm": 0.000993868918158114, "learning_rate": 1.497320272116845e-06, "loss": 3.093458944931626e-05, "step": 62125 }, { "epoch": 8.064097573634358, "grad_norm": 0.0008649633382447064, "learning_rate": 1.4865610638225753e-06, "loss": 2.9103595297783614e-05, "step": 62150 }, { "epoch": 8.06734137796808, "grad_norm": 0.000752591819036752, "learning_rate": 1.4758394663356073e-06, "loss": 2.8026963118463755e-05, "step": 62175 }, { "epoch": 8.070585182301803, "grad_norm": 0.0002887421869672835, "learning_rate": 1.4651554968056369e-06, "loss": 2.7641248889267443e-05, "step": 62200 }, { "epoch": 8.073828986635526, "grad_norm": 0.0006792889907956123, "learning_rate": 1.454509172322141e-06, "loss": 2.9815672896802425e-05, "step": 62225 }, { "epoch": 8.077072790969249, "grad_norm": 0.0006971962284296751, "learning_rate": 1.4439005099144116e-06, "loss": 3.2979175448417666e-05, "step": 62250 }, { "epoch": 8.080316595302971, "grad_norm": 0.0008797247428447008, "learning_rate": 1.433329526551469e-06, "loss": 3.0462751165032388e-05, "step": 62275 }, { "epoch": 8.083560399636694, "grad_norm": 0.0012217884650453925, "learning_rate": 1.422796239142085e-06, "loss": 2.4460041895508767e-05, "step": 62300 }, { "epoch": 8.086804203970416, "grad_norm": 0.0005153453093953431, "learning_rate": 1.4123006645347326e-06, "loss": 2.4704374372959136e-05, "step": 62325 }, { "epoch": 8.090048008304139, "grad_norm": 0.0007296618423424661, "learning_rate": 1.4018428195175486e-06, "loss": 2.7266559191048144e-05, "step": 62350 }, { "epoch": 8.093291812637862, "grad_norm": 0.0007331704255193472, "learning_rate": 1.3914227208183388e-06, "loss": 2.825091127306223e-05, "step": 62375 }, { "epoch": 8.096535616971584, "grad_norm": 0.00035818538162857294, "learning_rate": 1.3810403851045095e-06, "loss": 3.1903365161269904e-05, "step": 62400 }, { "epoch": 8.099779421305307, "grad_norm": 0.0006435091490857303, "learning_rate": 1.3706958289830874e-06, "loss": 3.0156185384839774e-05, "step": 62425 }, { "epoch": 8.10302322563903, "grad_norm": 0.0009347975137643516, "learning_rate": 1.360389069000645e-06, "loss": 2.8084642253816127e-05, "step": 62450 }, { "epoch": 8.106267029972752, "grad_norm": 0.0008460976532660425, "learning_rate": 1.3501201216433224e-06, "loss": 2.772476989775896e-05, "step": 62475 }, { "epoch": 8.109510834306475, "grad_norm": 0.0006268829456530511, "learning_rate": 1.3398890033367529e-06, "loss": 3.232405055314302e-05, "step": 62500 }, { "epoch": 8.112754638640197, "grad_norm": 0.0007497987826354802, "learning_rate": 1.3296957304460816e-06, "loss": 3.094431711360812e-05, "step": 62525 }, { "epoch": 8.11599844297392, "grad_norm": 0.0012423438020050526, "learning_rate": 1.3195403192759026e-06, "loss": 3.342021023854613e-05, "step": 62550 }, { "epoch": 8.119242247307643, "grad_norm": 0.0011820459039881825, "learning_rate": 1.3094227860702635e-06, "loss": 2.951097209006548e-05, "step": 62575 }, { "epoch": 8.122486051641365, "grad_norm": 0.0011210183147341013, "learning_rate": 1.2993431470126023e-06, "loss": 2.7662911452353e-05, "step": 62600 }, { "epoch": 8.125729855975088, "grad_norm": 0.0013834591954946518, "learning_rate": 1.289301418225769e-06, "loss": 3.058055881410837e-05, "step": 62625 }, { "epoch": 8.12897366030881, "grad_norm": 0.0007690104539506137, "learning_rate": 1.2792976157719516e-06, "loss": 2.660481259226799e-05, "step": 62650 }, { "epoch": 8.132217464642533, "grad_norm": 0.00048450269969180226, "learning_rate": 1.2693317556526945e-06, "loss": 3.091909689828754e-05, "step": 62675 }, { "epoch": 8.135461268976256, "grad_norm": 0.0003938012523576617, "learning_rate": 1.25940385380883e-06, "loss": 2.4576811119914056e-05, "step": 62700 }, { "epoch": 8.138705073309978, "grad_norm": 0.0003814492665696889, "learning_rate": 1.2495139261204963e-06, "loss": 2.8921493794769048e-05, "step": 62725 }, { "epoch": 8.141948877643701, "grad_norm": 0.0006717906799167395, "learning_rate": 1.2396619884070704e-06, "loss": 3.207018366083503e-05, "step": 62750 }, { "epoch": 8.145192681977424, "grad_norm": 0.0005700927576981485, "learning_rate": 1.2298480564271768e-06, "loss": 3.097787266597152e-05, "step": 62775 }, { "epoch": 8.148436486311146, "grad_norm": 0.001700383611023426, "learning_rate": 1.2200721458786396e-06, "loss": 2.884278306737542e-05, "step": 62800 }, { "epoch": 8.151680290644869, "grad_norm": 0.0008952473290264606, "learning_rate": 1.2103342723984724e-06, "loss": 2.8823225293308496e-05, "step": 62825 }, { "epoch": 8.154924094978591, "grad_norm": 0.000786003889515996, "learning_rate": 1.2006344515628431e-06, "loss": 3.0563506297767164e-05, "step": 62850 }, { "epoch": 8.158167899312314, "grad_norm": 0.0007517854101024568, "learning_rate": 1.1909726988870468e-06, "loss": 2.580490428954363e-05, "step": 62875 }, { "epoch": 8.161411703646037, "grad_norm": 0.0010785778285935521, "learning_rate": 1.1813490298255042e-06, "loss": 2.82697519287467e-05, "step": 62900 }, { "epoch": 8.16465550797976, "grad_norm": 0.0004170692409388721, "learning_rate": 1.1717634597716992e-06, "loss": 2.475931774824858e-05, "step": 62925 }, { "epoch": 8.167899312313482, "grad_norm": 0.0007183199049904943, "learning_rate": 1.162216004058192e-06, "loss": 2.804642776027322e-05, "step": 62950 }, { "epoch": 8.171143116647205, "grad_norm": 0.0012583354255184531, "learning_rate": 1.152706677956558e-06, "loss": 2.5020167231559754e-05, "step": 62975 }, { "epoch": 8.174386920980927, "grad_norm": 0.00041752777178771794, "learning_rate": 1.1432354966774056e-06, "loss": 3.3005825243890286e-05, "step": 63000 }, { "epoch": 8.17763072531465, "grad_norm": 0.0009006825275719166, "learning_rate": 1.1338024753703074e-06, "loss": 2.6684575714170934e-05, "step": 63025 }, { "epoch": 8.180874529648372, "grad_norm": 0.0007577663636766374, "learning_rate": 1.1244076291238138e-06, "loss": 2.734657609835267e-05, "step": 63050 }, { "epoch": 8.184118333982095, "grad_norm": 0.0007901584613136947, "learning_rate": 1.1150509729654007e-06, "loss": 2.8706530574709177e-05, "step": 63075 }, { "epoch": 8.187362138315816, "grad_norm": 0.0005501187988556921, "learning_rate": 1.1057325218614662e-06, "loss": 3.003981662914157e-05, "step": 63100 }, { "epoch": 8.190605942649539, "grad_norm": 0.0007956328336149454, "learning_rate": 1.0964522907172897e-06, "loss": 2.324735978618264e-05, "step": 63125 }, { "epoch": 8.193849746983261, "grad_norm": 0.0005283289938233793, "learning_rate": 1.0872102943770252e-06, "loss": 2.6467114221304655e-05, "step": 63150 }, { "epoch": 8.197093551316984, "grad_norm": 0.0008982605650089681, "learning_rate": 1.0780065476236556e-06, "loss": 2.792284591123462e-05, "step": 63175 }, { "epoch": 8.200337355650706, "grad_norm": 0.0005102726281620562, "learning_rate": 1.0688410651789965e-06, "loss": 2.8455741703510283e-05, "step": 63200 }, { "epoch": 8.203581159984429, "grad_norm": 0.0007513919263146818, "learning_rate": 1.0597138617036457e-06, "loss": 3.21285636164248e-05, "step": 63225 }, { "epoch": 8.206824964318152, "grad_norm": 0.0009467607014812529, "learning_rate": 1.050624951796983e-06, "loss": 2.9565971344709397e-05, "step": 63250 }, { "epoch": 8.210068768651874, "grad_norm": 0.0005063483840785921, "learning_rate": 1.0415743499971237e-06, "loss": 2.573508070781827e-05, "step": 63275 }, { "epoch": 8.213312572985597, "grad_norm": 0.0012386675225570798, "learning_rate": 1.0325620707809181e-06, "loss": 2.9284441843628884e-05, "step": 63300 }, { "epoch": 8.21655637731932, "grad_norm": 0.0005684214411303401, "learning_rate": 1.0235881285639126e-06, "loss": 3.538796911016107e-05, "step": 63325 }, { "epoch": 8.219800181653042, "grad_norm": 0.0006427289918065071, "learning_rate": 1.0146525377003335e-06, "loss": 3.1385854817926884e-05, "step": 63350 }, { "epoch": 8.223043985986765, "grad_norm": 0.000787722528912127, "learning_rate": 1.0057553124830642e-06, "loss": 3.033812390640378e-05, "step": 63375 }, { "epoch": 8.226287790320487, "grad_norm": 0.0008833821048028767, "learning_rate": 9.9689646714361e-07, "loss": 2.9541407711803914e-05, "step": 63400 }, { "epoch": 8.22953159465421, "grad_norm": 0.0004898944171145558, "learning_rate": 9.880760158521046e-07, "loss": 2.8342646546661855e-05, "step": 63425 }, { "epoch": 8.232775398987933, "grad_norm": 0.0007001066114753485, "learning_rate": 9.792939727172519e-07, "loss": 3.0772024765610694e-05, "step": 63450 }, { "epoch": 8.236019203321655, "grad_norm": 0.0005498469690792263, "learning_rate": 9.705503517863285e-07, "loss": 2.805503783747554e-05, "step": 63475 }, { "epoch": 8.239263007655378, "grad_norm": 0.000715208298061043, "learning_rate": 9.618451670451472e-07, "loss": 2.650643466040492e-05, "step": 63500 }, { "epoch": 8.2425068119891, "grad_norm": 0.0009614185546524823, "learning_rate": 9.531784324180504e-07, "loss": 3.0736455228179695e-05, "step": 63525 }, { "epoch": 8.245750616322823, "grad_norm": 0.001290511921979487, "learning_rate": 9.445501617678654e-07, "loss": 2.8053256683051588e-05, "step": 63550 }, { "epoch": 8.248994420656546, "grad_norm": 0.001836238312534988, "learning_rate": 9.359603688959051e-07, "loss": 2.8348928317427635e-05, "step": 63575 }, { "epoch": 8.252238224990268, "grad_norm": 0.0015384368598461151, "learning_rate": 9.274090675419289e-07, "loss": 2.891309093683958e-05, "step": 63600 }, { "epoch": 8.255482029323991, "grad_norm": 0.0011957954848185182, "learning_rate": 9.188962713841315e-07, "loss": 2.7457200922071933e-05, "step": 63625 }, { "epoch": 8.258725833657714, "grad_norm": 0.0007084769895300269, "learning_rate": 9.104219940391096e-07, "loss": 3.145975526422262e-05, "step": 63650 }, { "epoch": 8.261969637991436, "grad_norm": 0.0006215617759153247, "learning_rate": 9.019862490618591e-07, "loss": 2.75158672593534e-05, "step": 63675 }, { "epoch": 8.265213442325159, "grad_norm": 0.000818995526060462, "learning_rate": 8.935890499457311e-07, "loss": 2.6702410541474818e-05, "step": 63700 }, { "epoch": 8.268457246658881, "grad_norm": 0.0009900707518681884, "learning_rate": 8.852304101224229e-07, "loss": 3.052844433113933e-05, "step": 63725 }, { "epoch": 8.271701050992604, "grad_norm": 0.0008972735377028584, "learning_rate": 8.769103429619646e-07, "loss": 2.9458438511937856e-05, "step": 63750 }, { "epoch": 8.274944855326327, "grad_norm": 0.0005654357373714447, "learning_rate": 8.686288617726662e-07, "loss": 3.694994142279029e-05, "step": 63775 }, { "epoch": 8.27818865966005, "grad_norm": 0.0013240328989923, "learning_rate": 8.603859798011455e-07, "loss": 3.220536280423403e-05, "step": 63800 }, { "epoch": 8.281432463993772, "grad_norm": 0.0008171448134817183, "learning_rate": 8.521817102322527e-07, "loss": 2.527691423892975e-05, "step": 63825 }, { "epoch": 8.284676268327495, "grad_norm": 0.0009467154159210622, "learning_rate": 8.440160661890934e-07, "loss": 2.8480144683271645e-05, "step": 63850 }, { "epoch": 8.287920072661217, "grad_norm": 0.0004371112445369363, "learning_rate": 8.358890607329805e-07, "loss": 2.8507940005511045e-05, "step": 63875 }, { "epoch": 8.29116387699494, "grad_norm": 0.0004826605727430433, "learning_rate": 8.278007068634325e-07, "loss": 2.973731141537428e-05, "step": 63900 }, { "epoch": 8.294407681328662, "grad_norm": 0.0007160863024182618, "learning_rate": 8.197510175181278e-07, "loss": 2.5697322562336923e-05, "step": 63925 }, { "epoch": 8.297651485662385, "grad_norm": 0.0004936783225275576, "learning_rate": 8.117400055729141e-07, "loss": 2.7760681696236134e-05, "step": 63950 }, { "epoch": 8.300895289996108, "grad_norm": 0.0007274665986187756, "learning_rate": 8.037676838417662e-07, "loss": 3.250884590670466e-05, "step": 63975 }, { "epoch": 8.30413909432983, "grad_norm": 0.0018140216125175357, "learning_rate": 7.958340650767699e-07, "loss": 2.9579049441963435e-05, "step": 64000 }, { "epoch": 8.307382898663553, "grad_norm": 0.0006354146171361208, "learning_rate": 7.879391619681098e-07, "loss": 2.9918649233877658e-05, "step": 64025 }, { "epoch": 8.310626702997276, "grad_norm": 0.00088910898193717, "learning_rate": 7.800829871440374e-07, "loss": 2.8515341691672803e-05, "step": 64050 }, { "epoch": 8.313870507330998, "grad_norm": 0.0009173955768346786, "learning_rate": 7.722655531708617e-07, "loss": 3.234606003388762e-05, "step": 64075 }, { "epoch": 8.31711431166472, "grad_norm": 0.0008164239698089659, "learning_rate": 7.644868725529191e-07, "loss": 2.7630412951111794e-05, "step": 64100 }, { "epoch": 8.320358115998443, "grad_norm": 0.0004176994552835822, "learning_rate": 7.567469577325598e-07, "loss": 2.5066130328923465e-05, "step": 64125 }, { "epoch": 8.323601920332166, "grad_norm": 0.0012510411906987429, "learning_rate": 7.490458210901303e-07, "loss": 2.982893493026495e-05, "step": 64150 }, { "epoch": 8.326845724665889, "grad_norm": 0.0011901056859642267, "learning_rate": 7.413834749439436e-07, "loss": 3.002652432769537e-05, "step": 64175 }, { "epoch": 8.330089528999611, "grad_norm": 0.00037900550523772836, "learning_rate": 7.337599315502681e-07, "loss": 3.246775595471263e-05, "step": 64200 }, { "epoch": 8.333333333333334, "grad_norm": 0.0004566535644698888, "learning_rate": 7.261752031033104e-07, "loss": 3.211612114682794e-05, "step": 64225 }, { "epoch": 8.336577137667057, "grad_norm": 0.0006397904362529516, "learning_rate": 7.186293017351769e-07, "loss": 3.0473803635686637e-05, "step": 64250 }, { "epoch": 8.33982094200078, "grad_norm": 0.001055812812410295, "learning_rate": 7.111222395158907e-07, "loss": 3.1331134960055354e-05, "step": 64275 }, { "epoch": 8.343064746334502, "grad_norm": 0.0006357079255394638, "learning_rate": 7.036540284533238e-07, "loss": 2.5608662981539964e-05, "step": 64300 }, { "epoch": 8.346308550668224, "grad_norm": 0.0006893743411637843, "learning_rate": 6.962246804932237e-07, "loss": 2.8651414904743433e-05, "step": 64325 }, { "epoch": 8.349552355001947, "grad_norm": 0.0007911249413155019, "learning_rate": 6.888342075191679e-07, "loss": 2.7979877777397633e-05, "step": 64350 }, { "epoch": 8.35279615933567, "grad_norm": 0.0009415188687853515, "learning_rate": 6.8148262135255e-07, "loss": 3.1362941954284906e-05, "step": 64375 }, { "epoch": 8.356039963669392, "grad_norm": 0.0006051487871445715, "learning_rate": 6.741699337525636e-07, "loss": 2.9393879231065512e-05, "step": 64400 }, { "epoch": 8.359283768003115, "grad_norm": 0.0005190118681639433, "learning_rate": 6.668961564161858e-07, "loss": 2.6908591389656068e-05, "step": 64425 }, { "epoch": 8.362527572336838, "grad_norm": 0.0021353447809815407, "learning_rate": 6.596613009781483e-07, "loss": 2.8781907167285682e-05, "step": 64450 }, { "epoch": 8.365771376670558, "grad_norm": 0.000552605779375881, "learning_rate": 6.524653790109331e-07, "loss": 3.010736545547843e-05, "step": 64475 }, { "epoch": 8.369015181004281, "grad_norm": 0.00028143709641881287, "learning_rate": 6.453084020247358e-07, "loss": 3.0312661547213793e-05, "step": 64500 }, { "epoch": 8.372258985338004, "grad_norm": 0.00069965492002666, "learning_rate": 6.381903814674712e-07, "loss": 2.873870776966214e-05, "step": 64525 }, { "epoch": 8.375502789671726, "grad_norm": 0.000514635001309216, "learning_rate": 6.311113287247289e-07, "loss": 2.81943310983479e-05, "step": 64550 }, { "epoch": 8.378746594005449, "grad_norm": 0.0007233547512441874, "learning_rate": 6.240712551197791e-07, "loss": 2.7563755866140126e-05, "step": 64575 }, { "epoch": 8.381990398339171, "grad_norm": 0.0004843025526497513, "learning_rate": 6.170701719135336e-07, "loss": 2.7941055595874786e-05, "step": 64600 }, { "epoch": 8.385234202672894, "grad_norm": 0.0006562382914125919, "learning_rate": 6.101080903045426e-07, "loss": 2.699481789022684e-05, "step": 64625 }, { "epoch": 8.388478007006617, "grad_norm": 0.0008782647200860083, "learning_rate": 6.031850214289647e-07, "loss": 2.7464134618639945e-05, "step": 64650 }, { "epoch": 8.39172181134034, "grad_norm": 0.0006454401882365346, "learning_rate": 5.963009763605726e-07, "loss": 2.7319893706589938e-05, "step": 64675 }, { "epoch": 8.394965615674062, "grad_norm": 0.0007847963133826852, "learning_rate": 5.89455966110694e-07, "loss": 2.8176098130643367e-05, "step": 64700 }, { "epoch": 8.398209420007785, "grad_norm": 0.0007202837732620537, "learning_rate": 5.826500016282432e-07, "loss": 2.5258034002035855e-05, "step": 64725 }, { "epoch": 8.401453224341507, "grad_norm": 0.0004567653813865036, "learning_rate": 5.758830937996617e-07, "loss": 2.7746863197535275e-05, "step": 64750 }, { "epoch": 8.40469702867523, "grad_norm": 0.0005199803854338825, "learning_rate": 5.691552534489219e-07, "loss": 3.252854803577065e-05, "step": 64775 }, { "epoch": 8.407940833008952, "grad_norm": 0.0004979029763489962, "learning_rate": 5.624664913375155e-07, "loss": 2.619361272081733e-05, "step": 64800 }, { "epoch": 8.411184637342675, "grad_norm": 0.000865124398842454, "learning_rate": 5.558168181644147e-07, "loss": 2.7562167961150408e-05, "step": 64825 }, { "epoch": 8.414428441676398, "grad_norm": 0.0006865739705972373, "learning_rate": 5.492062445660723e-07, "loss": 3.075527958571911e-05, "step": 64850 }, { "epoch": 8.41767224601012, "grad_norm": 0.0006410976056940854, "learning_rate": 5.426347811163995e-07, "loss": 2.385672880336642e-05, "step": 64875 }, { "epoch": 8.420916050343843, "grad_norm": 0.0006411562790162861, "learning_rate": 5.361024383267521e-07, "loss": 2.803378039970994e-05, "step": 64900 }, { "epoch": 8.424159854677566, "grad_norm": 0.0014569454360753298, "learning_rate": 5.296092266459024e-07, "loss": 2.4905514437705277e-05, "step": 64925 }, { "epoch": 8.427403659011288, "grad_norm": 0.0008095914381556213, "learning_rate": 5.231551564600396e-07, "loss": 2.894979668781161e-05, "step": 64950 }, { "epoch": 8.43064746334501, "grad_norm": 0.0010526998667046428, "learning_rate": 5.167402380927333e-07, "loss": 3.0472474172711372e-05, "step": 64975 }, { "epoch": 8.433891267678733, "grad_norm": 0.0014387039700523019, "learning_rate": 5.103644818049452e-07, "loss": 2.7758157812058927e-05, "step": 65000 }, { "epoch": 8.437135072012456, "grad_norm": 0.0017849844880402088, "learning_rate": 5.040278977949786e-07, "loss": 2.6500546373426913e-05, "step": 65025 }, { "epoch": 8.440378876346179, "grad_norm": 0.0008884842391125858, "learning_rate": 4.977304961984897e-07, "loss": 2.750203711912036e-05, "step": 65050 }, { "epoch": 8.443622680679901, "grad_norm": 0.0005753783043473959, "learning_rate": 4.914722870884513e-07, "loss": 3.0481761787086725e-05, "step": 65075 }, { "epoch": 8.446866485013624, "grad_norm": 0.00031617461354471743, "learning_rate": 4.852532804751592e-07, "loss": 2.5991541333496572e-05, "step": 65100 }, { "epoch": 8.450110289347347, "grad_norm": 0.000828452524729073, "learning_rate": 4.790734863061863e-07, "loss": 3.218995407223701e-05, "step": 65125 }, { "epoch": 8.45335409368107, "grad_norm": 0.0007045766105875373, "learning_rate": 4.7293291446640077e-07, "loss": 3.001271281391382e-05, "step": 65150 }, { "epoch": 8.456597898014792, "grad_norm": 0.0013379281153902411, "learning_rate": 4.668315747779178e-07, "loss": 2.7081964071840046e-05, "step": 65175 }, { "epoch": 8.459841702348514, "grad_norm": 0.000661856378428638, "learning_rate": 4.607694770001114e-07, "loss": 3.0454082880169152e-05, "step": 65200 }, { "epoch": 8.463085506682237, "grad_norm": 0.0010441112099215388, "learning_rate": 4.5474663082957504e-07, "loss": 3.0920011922717095e-05, "step": 65225 }, { "epoch": 8.46632931101596, "grad_norm": 0.0007677100948058069, "learning_rate": 4.487630459001302e-07, "loss": 2.669826615601778e-05, "step": 65250 }, { "epoch": 8.469573115349682, "grad_norm": 0.0006847493932582438, "learning_rate": 4.4281873178278475e-07, "loss": 2.9498457442969085e-05, "step": 65275 }, { "epoch": 8.472816919683405, "grad_norm": 0.0007894596201367676, "learning_rate": 4.3691369798573854e-07, "loss": 2.5603892281651498e-05, "step": 65300 }, { "epoch": 8.476060724017128, "grad_norm": 0.0008850560989230871, "learning_rate": 4.310479539543638e-07, "loss": 2.89169792085886e-05, "step": 65325 }, { "epoch": 8.47930452835085, "grad_norm": 0.0006531463004648685, "learning_rate": 4.252215090711775e-07, "loss": 2.944712061434984e-05, "step": 65350 }, { "epoch": 8.482548332684573, "grad_norm": 0.00037433666875585914, "learning_rate": 4.1943437265584694e-07, "loss": 2.3801950737833978e-05, "step": 65375 }, { "epoch": 8.485792137018295, "grad_norm": 0.0006261112866923213, "learning_rate": 4.136865539651508e-07, "loss": 2.8587260749191047e-05, "step": 65400 }, { "epoch": 8.489035941352018, "grad_norm": 0.0007114526233635843, "learning_rate": 4.0797806219299295e-07, "loss": 3.149113152176142e-05, "step": 65425 }, { "epoch": 8.49227974568574, "grad_norm": 0.0003664169635158032, "learning_rate": 4.0230890647035836e-07, "loss": 3.1251288019120695e-05, "step": 65450 }, { "epoch": 8.495523550019463, "grad_norm": 0.0007439167238771915, "learning_rate": 3.9667909586532105e-07, "loss": 2.9449299909174442e-05, "step": 65475 }, { "epoch": 8.498767354353186, "grad_norm": 0.0005423882394097745, "learning_rate": 3.9108863938301377e-07, "loss": 2.7304927352815867e-05, "step": 65500 }, { "epoch": 8.502011158686908, "grad_norm": 0.0009797143284231424, "learning_rate": 3.8553754596562517e-07, "loss": 2.9264318291097878e-05, "step": 65525 }, { "epoch": 8.505254963020631, "grad_norm": 0.0003104376664850861, "learning_rate": 3.8002582449238045e-07, "loss": 2.722002100199461e-05, "step": 65550 }, { "epoch": 8.505254963020631, "eval_loss": 0.00015141768380999565, "eval_runtime": 7.1275, "eval_samples_per_second": 701.504, "eval_steps_per_second": 5.612, "step": 65550 }, { "epoch": 8.505254963020631, "eval_holdout_avg_strict_f1": 0.26327252083881664, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7451263537906136, "eval_holdout_nemotron_pii_strict_f1": 0.7524965432478108, "eval_holdout_open_pii_masking_500k_strict_f1": 0.7161697247706422, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.6822051074179165, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 65550 }, { "epoch": 8.508498767354354, "grad_norm": 0.0010513331508263946, "learning_rate": 3.7455348377952724e-07, "loss": 2.823983086273074e-05, "step": 65575 }, { "epoch": 8.511742571688076, "grad_norm": 0.00033224408980458975, "learning_rate": 3.691205325803221e-07, "loss": 3.3079518470913174e-05, "step": 65600 }, { "epoch": 8.514986376021799, "grad_norm": 0.0010110142175108194, "learning_rate": 3.6372697958501065e-07, "loss": 2.6257846038788556e-05, "step": 65625 }, { "epoch": 8.518230180355522, "grad_norm": 0.00037963438080623746, "learning_rate": 3.583728334208336e-07, "loss": 2.9422417283058168e-05, "step": 65650 }, { "epoch": 8.521473984689244, "grad_norm": 0.000860546831972897, "learning_rate": 3.530581026519819e-07, "loss": 3.078959183767438e-05, "step": 65675 }, { "epoch": 8.524717789022967, "grad_norm": 0.0011886630672961473, "learning_rate": 3.477827957796137e-07, "loss": 3.0113987158983945e-05, "step": 65700 }, { "epoch": 8.52796159335669, "grad_norm": 0.001138966646976769, "learning_rate": 3.425469212418125e-07, "loss": 3.0315143521875144e-05, "step": 65725 }, { "epoch": 8.531205397690412, "grad_norm": 0.0007637997041456401, "learning_rate": 3.373504874136041e-07, "loss": 2.8987389523535967e-05, "step": 65750 }, { "epoch": 8.534449202024135, "grad_norm": 0.0005321321659721434, "learning_rate": 3.321935026069145e-07, "loss": 2.894502831622958e-05, "step": 65775 }, { "epoch": 8.537693006357856, "grad_norm": 0.0006732043111696839, "learning_rate": 3.270759750705732e-07, "loss": 2.7166190557181834e-05, "step": 65800 }, { "epoch": 8.54093681069158, "grad_norm": 0.0011101565323770046, "learning_rate": 3.2199791299029893e-07, "loss": 3.0608938541263345e-05, "step": 65825 }, { "epoch": 8.5441806150253, "grad_norm": 0.002264350885525346, "learning_rate": 3.1695932448868315e-07, "loss": 2.5456564035266638e-05, "step": 65850 }, { "epoch": 8.547424419359025, "grad_norm": 0.0004242327413521707, "learning_rate": 3.119602176251679e-07, "loss": 2.9566772282123567e-05, "step": 65875 }, { "epoch": 8.550668223692746, "grad_norm": 0.0006717517971992493, "learning_rate": 3.070006003960596e-07, "loss": 2.8133364394307138e-05, "step": 65900 }, { "epoch": 8.553912028026469, "grad_norm": 0.0008004361297935247, "learning_rate": 3.020804807344818e-07, "loss": 2.6432937011122705e-05, "step": 65925 }, { "epoch": 8.557155832360191, "grad_norm": 0.00114620930980891, "learning_rate": 2.971998665103976e-07, "loss": 3.22010857053101e-05, "step": 65950 }, { "epoch": 8.560399636693914, "grad_norm": 0.0008528189500793815, "learning_rate": 2.923587655305593e-07, "loss": 2.8418467845767736e-05, "step": 65975 }, { "epoch": 8.563643441027637, "grad_norm": 0.0004272686201147735, "learning_rate": 2.8755718553853393e-07, "loss": 3.0321783851832153e-05, "step": 66000 }, { "epoch": 8.56688724536136, "grad_norm": 0.000911837094463408, "learning_rate": 2.8279513421466117e-07, "loss": 3.140006680041552e-05, "step": 66025 }, { "epoch": 8.570131049695082, "grad_norm": 0.0009260144433937967, "learning_rate": 2.7807261917606186e-07, "loss": 3.070212667807937e-05, "step": 66050 }, { "epoch": 8.573374854028804, "grad_norm": 0.0009178558830171824, "learning_rate": 2.7338964797660737e-07, "loss": 2.5130328722298146e-05, "step": 66075 }, { "epoch": 8.576618658362527, "grad_norm": 0.0007082484080456197, "learning_rate": 2.687462281069225e-07, "loss": 2.9962898697704076e-05, "step": 66100 }, { "epoch": 8.57986246269625, "grad_norm": 0.0009464691393077374, "learning_rate": 2.6414236699436876e-07, "loss": 2.6118503883481025e-05, "step": 66125 }, { "epoch": 8.583106267029972, "grad_norm": 0.0006070114322938025, "learning_rate": 2.5957807200302777e-07, "loss": 3.0301855877041816e-05, "step": 66150 }, { "epoch": 8.586350071363695, "grad_norm": 0.0003244997060392052, "learning_rate": 2.5505335043370107e-07, "loss": 2.2962212096899747e-05, "step": 66175 }, { "epoch": 8.589593875697418, "grad_norm": 0.0005442538531497121, "learning_rate": 2.5056820952387703e-07, "loss": 3.002409590408206e-05, "step": 66200 }, { "epoch": 8.59283768003114, "grad_norm": 0.0009832787327468395, "learning_rate": 2.461226564477448e-07, "loss": 2.4012248031795026e-05, "step": 66225 }, { "epoch": 8.596081484364863, "grad_norm": 0.0021109674125909805, "learning_rate": 2.4171669831616893e-07, "loss": 3.1843401957303285e-05, "step": 66250 }, { "epoch": 8.599325288698585, "grad_norm": 0.0003591421991586685, "learning_rate": 2.3735034217667595e-07, "loss": 2.899253973737359e-05, "step": 66275 }, { "epoch": 8.602569093032308, "grad_norm": 0.0005713781574741006, "learning_rate": 2.3302359501345128e-07, "loss": 2.555317711085081e-05, "step": 66300 }, { "epoch": 8.60581289736603, "grad_norm": 0.000754582870285958, "learning_rate": 2.2873646374731994e-07, "loss": 2.8917072340846063e-05, "step": 66325 }, { "epoch": 8.609056701699753, "grad_norm": 0.0014236952411010861, "learning_rate": 2.2448895523574376e-07, "loss": 2.768376376479864e-05, "step": 66350 }, { "epoch": 8.612300506033476, "grad_norm": 0.0006043906905688345, "learning_rate": 2.2028107627280747e-07, "loss": 2.895675366744399e-05, "step": 66375 }, { "epoch": 8.615544310367198, "grad_norm": 0.0006463392055593431, "learning_rate": 2.1611283358919654e-07, "loss": 3.132349578663707e-05, "step": 66400 }, { "epoch": 8.618788114700921, "grad_norm": 0.0007046700338833034, "learning_rate": 2.1198423385220824e-07, "loss": 2.747727558016777e-05, "step": 66425 }, { "epoch": 8.622031919034644, "grad_norm": 0.0008835468906909227, "learning_rate": 2.0789528366572387e-07, "loss": 2.5813821703195573e-05, "step": 66450 }, { "epoch": 8.625275723368366, "grad_norm": 0.0006100489990785718, "learning_rate": 2.0384598957020328e-07, "loss": 2.9414142481982708e-05, "step": 66475 }, { "epoch": 8.628519527702089, "grad_norm": 0.0006234540487639606, "learning_rate": 1.9983635804267375e-07, "loss": 2.7505226898938418e-05, "step": 66500 }, { "epoch": 8.631763332035812, "grad_norm": 0.0007676620734855533, "learning_rate": 1.9586639549672436e-07, "loss": 3.8158067036420106e-05, "step": 66525 }, { "epoch": 8.635007136369534, "grad_norm": 0.0011297723976895213, "learning_rate": 1.9193610828248665e-07, "loss": 3.131905570626259e-05, "step": 66550 }, { "epoch": 8.638250940703257, "grad_norm": 0.0013571275630965829, "learning_rate": 1.8804550268663456e-07, "loss": 2.683300757780671e-05, "step": 66575 }, { "epoch": 8.64149474503698, "grad_norm": 0.0008953653741627932, "learning_rate": 1.8419458493236785e-07, "loss": 2.7616748120635748e-05, "step": 66600 }, { "epoch": 8.644738549370702, "grad_norm": 0.00043243804248049855, "learning_rate": 1.803833611794037e-07, "loss": 2.204686403274536e-05, "step": 66625 }, { "epoch": 8.647982353704425, "grad_norm": 0.001757309422828257, "learning_rate": 1.766118375239628e-07, "loss": 2.9408261179924012e-05, "step": 66650 }, { "epoch": 8.651226158038147, "grad_norm": 0.0008109670598059893, "learning_rate": 1.7288001999877235e-07, "loss": 2.941317157819867e-05, "step": 66675 }, { "epoch": 8.65446996237187, "grad_norm": 0.0007287448388524354, "learning_rate": 1.6918791457304074e-07, "loss": 2.9014288447797298e-05, "step": 66700 }, { "epoch": 8.657713766705593, "grad_norm": 0.00043877644930034876, "learning_rate": 1.65535527152455e-07, "loss": 3.4755999222397805e-05, "step": 66725 }, { "epoch": 8.660957571039315, "grad_norm": 0.0005995703977532685, "learning_rate": 1.6192286357917807e-07, "loss": 2.8176899068057537e-05, "step": 66750 }, { "epoch": 8.664201375373038, "grad_norm": 0.0007856583688408136, "learning_rate": 1.5834992963182638e-07, "loss": 3.142779925838113e-05, "step": 66775 }, { "epoch": 8.66744517970676, "grad_norm": 0.0007412737468257546, "learning_rate": 1.5481673102547278e-07, "loss": 2.4431550409644844e-05, "step": 66800 }, { "epoch": 8.670688984040483, "grad_norm": 0.0009226504480466247, "learning_rate": 1.5132327341161878e-07, "loss": 2.610976342111826e-05, "step": 66825 }, { "epoch": 8.673932788374206, "grad_norm": 0.00046171166468411684, "learning_rate": 1.478695623782167e-07, "loss": 2.6210788637399673e-05, "step": 66850 }, { "epoch": 8.677176592707928, "grad_norm": 0.0005648859078064561, "learning_rate": 1.4445560344962806e-07, "loss": 2.8487008530646564e-05, "step": 66875 }, { "epoch": 8.680420397041651, "grad_norm": 0.0007482802029699087, "learning_rate": 1.4108140208663746e-07, "loss": 2.8039661701768635e-05, "step": 66900 }, { "epoch": 8.683664201375374, "grad_norm": 0.0009614796144887805, "learning_rate": 1.3774696368643036e-07, "loss": 3.110948484390974e-05, "step": 66925 }, { "epoch": 8.686908005709096, "grad_norm": 0.0011815710458904505, "learning_rate": 1.3445229358259037e-07, "loss": 2.861598273739219e-05, "step": 66950 }, { "epoch": 8.690151810042819, "grad_norm": 0.0006680138176307082, "learning_rate": 1.3119739704509637e-07, "loss": 3.092663362622261e-05, "step": 66975 }, { "epoch": 8.693395614376541, "grad_norm": 0.0002629356167744845, "learning_rate": 1.2798227928029482e-07, "loss": 3.1381675507873294e-05, "step": 67000 }, { "epoch": 8.696639418710264, "grad_norm": 0.001220876001752913, "learning_rate": 1.248069454309192e-07, "loss": 2.9244821052998305e-05, "step": 67025 }, { "epoch": 8.699883223043987, "grad_norm": 0.0010961538646370173, "learning_rate": 1.2167140057605387e-07, "loss": 3.2668390776962045e-05, "step": 67050 }, { "epoch": 8.70312702737771, "grad_norm": 0.000467295030830428, "learning_rate": 1.1857564973114799e-07, "loss": 2.5451071560382844e-05, "step": 67075 }, { "epoch": 8.706370831711432, "grad_norm": 0.0006419154233299196, "learning_rate": 1.1551969784799333e-07, "loss": 2.5121308863162994e-05, "step": 67100 }, { "epoch": 8.709614636045155, "grad_norm": 0.0008650991367176175, "learning_rate": 1.1250354981472144e-07, "loss": 2.7590957470238208e-05, "step": 67125 }, { "epoch": 8.712858440378877, "grad_norm": 0.0005280972109176219, "learning_rate": 1.0952721045580094e-07, "loss": 3.408963792026043e-05, "step": 67150 }, { "epoch": 8.7161022447126, "grad_norm": 0.0005012511392123997, "learning_rate": 1.0659068453201804e-07, "loss": 2.6347821112722158e-05, "step": 67175 }, { "epoch": 8.719346049046322, "grad_norm": 0.00044498094939626753, "learning_rate": 1.0369397674047932e-07, "loss": 3.207893576472998e-05, "step": 67200 }, { "epoch": 8.722589853380043, "grad_norm": 0.00047140225069597363, "learning_rate": 1.0083709171459788e-07, "loss": 3.093276172876358e-05, "step": 67225 }, { "epoch": 8.725833657713768, "grad_norm": 0.0011543810833245516, "learning_rate": 9.802003402409609e-08, "loss": 2.6828311383724213e-05, "step": 67250 }, { "epoch": 8.729077462047488, "grad_norm": 0.0011210540542379022, "learning_rate": 9.524280817497789e-08, "loss": 2.7270650025457144e-05, "step": 67275 }, { "epoch": 8.732321266381211, "grad_norm": 0.0008836245979182422, "learning_rate": 9.250541860954532e-08, "loss": 2.832544734701514e-05, "step": 67300 }, { "epoch": 8.735565070714934, "grad_norm": 0.0020410397555679083, "learning_rate": 8.980786970637645e-08, "loss": 3.3266909886151554e-05, "step": 67325 }, { "epoch": 8.738808875048656, "grad_norm": 0.0004016412713099271, "learning_rate": 8.715016578032254e-08, "loss": 3.2034071628004314e-05, "step": 67350 }, { "epoch": 8.742052679382379, "grad_norm": 0.0012366676237434149, "learning_rate": 8.453231108249971e-08, "loss": 2.832322847098112e-05, "step": 67375 }, { "epoch": 8.745296483716102, "grad_norm": 0.0005630129599012434, "learning_rate": 8.19543098002834e-08, "loss": 2.6760189794003963e-05, "step": 67400 }, { "epoch": 8.748540288049824, "grad_norm": 0.0010763497557491064, "learning_rate": 7.941616605730839e-08, "loss": 2.761481795459986e-05, "step": 67425 }, { "epoch": 8.751784092383547, "grad_norm": 0.000693769077770412, "learning_rate": 7.691788391344656e-08, "loss": 3.0144634656608105e-05, "step": 67450 }, { "epoch": 8.75502789671727, "grad_norm": 0.00024555702111683786, "learning_rate": 7.445946736481246e-08, "loss": 2.31993873603642e-05, "step": 67475 }, { "epoch": 8.758271701050992, "grad_norm": 0.0011651904787868261, "learning_rate": 7.204092034375498e-08, "loss": 2.8068630490452053e-05, "step": 67500 }, { "epoch": 8.761515505384715, "grad_norm": 0.0006581929046660662, "learning_rate": 6.966224671884903e-08, "loss": 2.871435834094882e-05, "step": 67525 }, { "epoch": 8.764759309718437, "grad_norm": 0.0005720328772440553, "learning_rate": 6.732345029489273e-08, "loss": 2.7881197165697813e-05, "step": 67550 }, { "epoch": 8.76800311405216, "grad_norm": 0.0010014958679676056, "learning_rate": 6.502453481289361e-08, "loss": 2.7356105856597424e-05, "step": 67575 }, { "epoch": 8.771246918385883, "grad_norm": 0.0004482101940084249, "learning_rate": 6.276550395007407e-08, "loss": 2.825787290930748e-05, "step": 67600 }, { "epoch": 8.774490722719605, "grad_norm": 0.0004384055209811777, "learning_rate": 6.054636131985203e-08, "loss": 2.8851400129497053e-05, "step": 67625 }, { "epoch": 8.777734527053328, "grad_norm": 0.0005347413825802505, "learning_rate": 5.836711047184917e-08, "loss": 2.6641569565981626e-05, "step": 67650 }, { "epoch": 8.78097833138705, "grad_norm": 0.0008873855113051832, "learning_rate": 5.6227754891874375e-08, "loss": 2.7976029086858035e-05, "step": 67675 }, { "epoch": 8.784222135720773, "grad_norm": 0.0009923391044139862, "learning_rate": 5.4128298001926427e-08, "loss": 2.8016555588692427e-05, "step": 67700 }, { "epoch": 8.787465940054496, "grad_norm": 0.0005512680509127676, "learning_rate": 5.20687431601774e-08, "loss": 2.5699997786432503e-05, "step": 67725 }, { "epoch": 8.790709744388218, "grad_norm": 0.0006423712475225329, "learning_rate": 5.004909366097821e-08, "loss": 2.6124136056751012e-05, "step": 67750 }, { "epoch": 8.793953548721941, "grad_norm": 0.0006340251420624554, "learning_rate": 4.806935273485303e-08, "loss": 3.6808433942496774e-05, "step": 67775 }, { "epoch": 8.797197353055664, "grad_norm": 0.0003543281927704811, "learning_rate": 4.612952354848266e-08, "loss": 2.8417606372386218e-05, "step": 67800 }, { "epoch": 8.800441157389386, "grad_norm": 0.0004611406766343862, "learning_rate": 4.422960920471564e-08, "loss": 2.4186542723327876e-05, "step": 67825 }, { "epoch": 8.803684961723109, "grad_norm": 0.0005701542249880731, "learning_rate": 4.236961274254603e-08, "loss": 3.019497264176607e-05, "step": 67850 }, { "epoch": 8.806928766056831, "grad_norm": 0.0008654712582938373, "learning_rate": 4.054953713712728e-08, "loss": 2.853110432624817e-05, "step": 67875 }, { "epoch": 8.810172570390554, "grad_norm": 0.0011457513319328427, "learning_rate": 3.876938529975005e-08, "loss": 2.581005450338125e-05, "step": 67900 }, { "epoch": 8.813416374724277, "grad_norm": 0.001324183540418744, "learning_rate": 3.702916007784773e-08, "loss": 3.2649601344019175e-05, "step": 67925 }, { "epoch": 8.816660179058, "grad_norm": 0.0005399116780608892, "learning_rate": 3.532886425498816e-08, "loss": 2.545688534155488e-05, "step": 67950 }, { "epoch": 8.819903983391722, "grad_norm": 0.001911261584609747, "learning_rate": 3.3668500550870784e-08, "loss": 3.1257779337465766e-05, "step": 67975 }, { "epoch": 8.823147787725445, "grad_norm": 0.0009587511303834617, "learning_rate": 3.204807162132673e-08, "loss": 2.941625891253352e-05, "step": 68000 }, { "epoch": 8.826391592059167, "grad_norm": 0.0003079452726524323, "learning_rate": 3.04675800582993e-08, "loss": 2.6129700709134342e-05, "step": 68025 }, { "epoch": 8.82963539639289, "grad_norm": 0.0003769333125092089, "learning_rate": 2.8927028389860722e-08, "loss": 2.7617996092885733e-05, "step": 68050 }, { "epoch": 8.832879200726612, "grad_norm": 0.0006103746127337217, "learning_rate": 2.742641908019261e-08, "loss": 3.2679170835763216e-05, "step": 68075 }, { "epoch": 8.836123005060335, "grad_norm": 0.00038896806654520333, "learning_rate": 2.5965754529583276e-08, "loss": 2.7757687494158745e-05, "step": 68100 }, { "epoch": 8.839366809394058, "grad_norm": 0.0014508896274492145, "learning_rate": 2.4545037074436006e-08, "loss": 3.0175510328263045e-05, "step": 68125 }, { "epoch": 8.84261061372778, "grad_norm": 0.0007758463616482913, "learning_rate": 2.316426898724966e-08, "loss": 2.7090490330010653e-05, "step": 68150 }, { "epoch": 8.845854418061503, "grad_norm": 0.000698442105203867, "learning_rate": 2.1823452476626983e-08, "loss": 2.6699553709477188e-05, "step": 68175 }, { "epoch": 8.849098222395225, "grad_norm": 0.00038179184775799513, "learning_rate": 2.0522589687263504e-08, "loss": 3.053317312151194e-05, "step": 68200 }, { "epoch": 8.852342026728948, "grad_norm": 0.0013476810418069363, "learning_rate": 1.9261682699950323e-08, "loss": 2.8070572298020125e-05, "step": 68225 }, { "epoch": 8.85558583106267, "grad_norm": 0.00027023235452361405, "learning_rate": 1.8040733531560218e-08, "loss": 2.8076609596610068e-05, "step": 68250 }, { "epoch": 8.858829635396393, "grad_norm": 0.00039107093471102417, "learning_rate": 1.685974413506153e-08, "loss": 2.7572908438742162e-05, "step": 68275 }, { "epoch": 8.862073439730116, "grad_norm": 0.00047006004024297, "learning_rate": 1.5718716399495958e-08, "loss": 2.8949198313057423e-05, "step": 68300 }, { "epoch": 8.865317244063839, "grad_norm": 0.0005848923465237021, "learning_rate": 1.4617652149992444e-08, "loss": 2.953891409561038e-05, "step": 68325 }, { "epoch": 8.868561048397561, "grad_norm": 0.0010923037771135569, "learning_rate": 1.3556553147750506e-08, "loss": 2.902914769947529e-05, "step": 68350 }, { "epoch": 8.871804852731284, "grad_norm": 0.0006613485747948289, "learning_rate": 1.2535421090048572e-08, "loss": 2.874650526791811e-05, "step": 68375 }, { "epoch": 8.875048657065006, "grad_norm": 0.0007710965001024306, "learning_rate": 1.1554257610230101e-08, "loss": 2.6874635368585585e-05, "step": 68400 }, { "epoch": 8.878292461398729, "grad_norm": 0.0005168475327081978, "learning_rate": 1.0613064277711916e-08, "loss": 2.7474036905914544e-05, "step": 68425 }, { "epoch": 8.881536265732452, "grad_norm": 0.0008810343570075929, "learning_rate": 9.711842597975862e-09, "loss": 2.870997181162238e-05, "step": 68450 }, { "epoch": 8.884780070066174, "grad_norm": 0.0006918791914358735, "learning_rate": 8.850594012566049e-09, "loss": 2.9606057796627284e-05, "step": 68475 }, { "epoch": 8.888023874399897, "grad_norm": 0.0009445070754736662, "learning_rate": 8.029319899088839e-09, "loss": 2.415493130683899e-05, "step": 68500 }, { "epoch": 8.89126767873362, "grad_norm": 0.00045082729775458574, "learning_rate": 7.248021571210073e-09, "loss": 2.779516624286771e-05, "step": 68525 }, { "epoch": 8.894511483067342, "grad_norm": 0.000992100453004241, "learning_rate": 6.506700278649525e-09, "loss": 2.9565689619630575e-05, "step": 68550 }, { "epoch": 8.897755287401065, "grad_norm": 0.00042371326708234847, "learning_rate": 5.805357207186446e-09, "loss": 2.7906838804483415e-05, "step": 68575 }, { "epoch": 8.900999091734786, "grad_norm": 0.000573065597563982, "learning_rate": 5.1439934786484675e-09, "loss": 2.752277534455061e-05, "step": 68600 }, { "epoch": 8.90424289606851, "grad_norm": 0.0014237138675525784, "learning_rate": 4.5226101509171506e-09, "loss": 2.8843407053500415e-05, "step": 68625 }, { "epoch": 8.907486700402231, "grad_norm": 0.0006092404364608228, "learning_rate": 3.941208217925207e-09, "loss": 2.6626528706401588e-05, "step": 68650 }, { "epoch": 8.910730504735954, "grad_norm": 0.0007740124128758907, "learning_rate": 3.3997886096509555e-09, "loss": 2.8484258800745012e-05, "step": 68675 }, { "epoch": 8.913974309069676, "grad_norm": 0.0005159799475222826, "learning_rate": 2.898352192115539e-09, "loss": 2.911307383328676e-05, "step": 68700 }, { "epoch": 8.917218113403399, "grad_norm": 0.000546394323464483, "learning_rate": 2.4368997673940297e-09, "loss": 3.059984650462866e-05, "step": 68725 }, { "epoch": 8.920461917737121, "grad_norm": 0.0009173674043267965, "learning_rate": 2.0154320735987773e-09, "loss": 3.1873690895736216e-05, "step": 68750 }, { "epoch": 8.923705722070844, "grad_norm": 0.0004797989095095545, "learning_rate": 1.6339497848849583e-09, "loss": 3.145432798191905e-05, "step": 68775 }, { "epoch": 8.926949526404567, "grad_norm": 0.000409701227908954, "learning_rate": 1.292453511453351e-09, "loss": 2.7162542100995778e-05, "step": 68800 }, { "epoch": 8.93019333073829, "grad_norm": 0.0010030888952314854, "learning_rate": 9.909437995392346e-10, "loss": 2.626386471092701e-05, "step": 68825 }, { "epoch": 8.933437135072012, "grad_norm": 0.000737784372176975, "learning_rate": 7.294211314262667e-10, "loss": 2.7195473667234182e-05, "step": 68850 }, { "epoch": 8.936680939405734, "grad_norm": 0.0008178842253983021, "learning_rate": 5.078859254242784e-10, "loss": 2.8572108130902053e-05, "step": 68875 }, { "epoch": 8.939924743739457, "grad_norm": 0.00048015962238423526, "learning_rate": 3.2633853589703056e-10, "loss": 2.9165809974074363e-05, "step": 68900 }, { "epoch": 8.94316854807318, "grad_norm": 0.0010477156611159444, "learning_rate": 1.8477925323168167e-10, "loss": 2.9892073944211005e-05, "step": 68925 }, { "epoch": 8.946412352406902, "grad_norm": 0.0007026988896541297, "learning_rate": 8.320830386099321e-11, "loss": 2.7925085742026568e-05, "step": 68950 }, { "epoch": 8.949656156740625, "grad_norm": 0.0007548880530521274, "learning_rate": 2.162585024945152e-11, "loss": 3.126847092062235e-05, "step": 68975 }, { "epoch": 8.952899961074348, "grad_norm": 0.0007356173591688275, "learning_rate": 3.199090714556263e-14, "loss": 2.615391043946147e-05, "step": 69000 }, { "epoch": 8.952899961074348, "eval_loss": 0.00015727317077107728, "eval_runtime": 7.1856, "eval_samples_per_second": 695.838, "eval_steps_per_second": 5.567, "step": 69000 }, { "epoch": 8.952899961074348, "eval_holdout_avg_strict_f1": 0.2622510497899543, "eval_holdout_enron_spam_bvk_strict_f1": 0.0, "eval_holdout_enron_spam_setfit_strict_f1": 0.0, "eval_holdout_gliner2_pii_ptbr_reward_split_strict_f1": 0.7407088534940451, "eval_holdout_nemotron_pii_strict_f1": 0.7486835075936807, "eval_holdout_open_pii_masking_500k_strict_f1": 0.7167762217776507, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.6785929648241206, "eval_holdout_sms_spam_multilingual_strict_f1": 0.0, "eval_holdout_spam_messages_mshenoda_strict_f1": 0.0, "eval_holdout_spamassassin_strict_f1": 0.0, "step": 69000 } ], "logging_steps": 25, "max_steps": 69000, "num_input_tokens_seen": 0, "num_train_epochs": 9, "save_steps": 3450, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }