{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 7.176287051482059, "eval_steps": 3450, "global_step": 55200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003250130005200208, "grad_norm": 0.17285723984241486, "learning_rate": 1.7391304347826088e-07, "loss": 0.003443165719509125, "step": 25 }, { "epoch": 0.006500260010400416, "grad_norm": 0.16427233815193176, "learning_rate": 3.5507246376811595e-07, "loss": 0.0031772717833518983, "step": 50 }, { "epoch": 0.009750390015600624, "grad_norm": 0.12062286585569382, "learning_rate": 5.36231884057971e-07, "loss": 0.0028067561984062195, "step": 75 }, { "epoch": 0.013000520020800831, "grad_norm": 0.036187898367643356, "learning_rate": 7.17391304347826e-07, "loss": 0.002082071602344513, "step": 100 }, { "epoch": 0.01625065002600104, "grad_norm": 0.07566563785076141, "learning_rate": 8.985507246376812e-07, "loss": 0.0016960065066814424, "step": 125 }, { "epoch": 0.01950078003120125, "grad_norm": 0.0404927060008049, "learning_rate": 1.0797101449275362e-06, "loss": 0.001293088048696518, "step": 150 }, { "epoch": 0.022750910036401457, "grad_norm": 0.02149803936481476, "learning_rate": 1.2608695652173913e-06, "loss": 0.0010677673667669296, "step": 175 }, { "epoch": 0.026001040041601663, "grad_norm": 0.014630273915827274, "learning_rate": 1.4420289855072464e-06, "loss": 0.0008378532528877258, "step": 200 }, { "epoch": 0.02925117004680187, "grad_norm": 0.012398317456245422, "learning_rate": 1.6231884057971016e-06, "loss": 0.0008191241323947906, "step": 225 }, { "epoch": 0.03250130005200208, "grad_norm": 0.006211752071976662, "learning_rate": 1.8043478260869565e-06, "loss": 0.0007002048194408416, "step": 250 }, { "epoch": 0.035751430057202285, "grad_norm": 0.004569601267576218, "learning_rate": 1.9855072463768116e-06, "loss": 0.0007424639165401459, "step": 275 }, { "epoch": 0.0390015600624025, "grad_norm": 0.0053680334240198135, "learning_rate": 2.166666666666667e-06, "loss": 0.0006691357493400574, "step": 300 }, { "epoch": 0.0422516900676027, "grad_norm": 0.005433837883174419, "learning_rate": 2.347826086956522e-06, "loss": 0.0007775794714689255, "step": 325 }, { "epoch": 0.045501820072802915, "grad_norm": 0.005344253499060869, "learning_rate": 2.5289855072463768e-06, "loss": 0.0006336342543363571, "step": 350 }, { "epoch": 0.04875195007800312, "grad_norm": 0.006653524469584227, "learning_rate": 2.710144927536232e-06, "loss": 0.0006941972672939301, "step": 375 }, { "epoch": 0.052002080083203325, "grad_norm": 0.002266584662720561, "learning_rate": 2.8913043478260875e-06, "loss": 0.0006006322428584098, "step": 400 }, { "epoch": 0.05525221008840354, "grad_norm": 0.0035597020760178566, "learning_rate": 3.072463768115942e-06, "loss": 0.0007461020350456237, "step": 425 }, { "epoch": 0.05850234009360374, "grad_norm": 0.005806833505630493, "learning_rate": 3.2536231884057973e-06, "loss": 0.0006669971346855163, "step": 450 }, { "epoch": 0.061752470098803955, "grad_norm": 0.004355548415333033, "learning_rate": 3.4347826086956526e-06, "loss": 0.0007137749344110489, "step": 475 }, { "epoch": 0.06500260010400416, "grad_norm": 0.003757717553526163, "learning_rate": 3.6159420289855076e-06, "loss": 0.000681799128651619, "step": 500 }, { "epoch": 0.06825273010920437, "grad_norm": 0.0034986482933163643, "learning_rate": 3.797101449275362e-06, "loss": 0.0006944525241851806, "step": 525 }, { "epoch": 0.07150286011440457, "grad_norm": 0.0026165375020354986, "learning_rate": 3.978260869565217e-06, "loss": 0.0006353378295898438, "step": 550 }, { "epoch": 0.07475299011960479, "grad_norm": 0.004414152819663286, "learning_rate": 4.159420289855073e-06, "loss": 0.0006701602041721344, "step": 575 }, { "epoch": 0.078003120124805, "grad_norm": 0.0028373319655656815, "learning_rate": 4.340579710144928e-06, "loss": 0.0006536580622196198, "step": 600 }, { "epoch": 0.0812532501300052, "grad_norm": 0.003998955246061087, "learning_rate": 4.5217391304347826e-06, "loss": 0.0006748034805059433, "step": 625 }, { "epoch": 0.0845033801352054, "grad_norm": 0.0053115058690309525, "learning_rate": 4.702898550724638e-06, "loss": 0.0005269774794578552, "step": 650 }, { "epoch": 0.08775351014040561, "grad_norm": 0.002853003330528736, "learning_rate": 4.884057971014493e-06, "loss": 0.0006208278983831406, "step": 675 }, { "epoch": 0.09100364014560583, "grad_norm": 0.002200072631239891, "learning_rate": 5.065217391304348e-06, "loss": 0.0005327824130654335, "step": 700 }, { "epoch": 0.09425377015080603, "grad_norm": 0.0036399802193045616, "learning_rate": 5.246376811594203e-06, "loss": 0.000596022792160511, "step": 725 }, { "epoch": 0.09750390015600624, "grad_norm": 0.002803057199344039, "learning_rate": 5.427536231884058e-06, "loss": 0.0006214606761932373, "step": 750 }, { "epoch": 0.10075403016120645, "grad_norm": 0.0016377355204895139, "learning_rate": 5.608695652173914e-06, "loss": 0.0005090900138020515, "step": 775 }, { "epoch": 0.10400416016640665, "grad_norm": 0.0022944787051528692, "learning_rate": 5.789855072463768e-06, "loss": 0.0005760033056139946, "step": 800 }, { "epoch": 0.10725429017160687, "grad_norm": 0.003916461952030659, "learning_rate": 5.9710144927536236e-06, "loss": 0.0005986005067825318, "step": 825 }, { "epoch": 0.11050442017680707, "grad_norm": 0.00359009625390172, "learning_rate": 6.152173913043478e-06, "loss": 0.0005693147704005241, "step": 850 }, { "epoch": 0.11375455018200728, "grad_norm": 0.0059497179463505745, "learning_rate": 6.333333333333334e-06, "loss": 0.0005642465874552727, "step": 875 }, { "epoch": 0.11700468018720749, "grad_norm": 0.0013701318530365825, "learning_rate": 6.514492753623189e-06, "loss": 0.0005200594663619995, "step": 900 }, { "epoch": 0.12025481019240769, "grad_norm": 0.0031415170524269342, "learning_rate": 6.695652173913043e-06, "loss": 0.0005143824592232704, "step": 925 }, { "epoch": 0.12350494019760791, "grad_norm": 0.0034513864666223526, "learning_rate": 6.876811594202899e-06, "loss": 0.0005369628965854645, "step": 950 }, { "epoch": 0.1267550702028081, "grad_norm": 0.0037151614669710398, "learning_rate": 7.057971014492754e-06, "loss": 0.000499497763812542, "step": 975 }, { "epoch": 0.13000520020800832, "grad_norm": 0.0036164678167551756, "learning_rate": 7.239130434782609e-06, "loss": 0.0005703026056289673, "step": 1000 }, { "epoch": 0.13325533021320854, "grad_norm": 0.0007839290192350745, "learning_rate": 7.420289855072464e-06, "loss": 0.0005447989702224731, "step": 1025 }, { "epoch": 0.13650546021840873, "grad_norm": 0.0009723713155835867, "learning_rate": 7.60144927536232e-06, "loss": 0.00040120664983987807, "step": 1050 }, { "epoch": 0.13975559022360895, "grad_norm": 0.0060493540950119495, "learning_rate": 7.782608695652174e-06, "loss": 0.000505555048584938, "step": 1075 }, { "epoch": 0.14300572022880914, "grad_norm": 0.0019169203005731106, "learning_rate": 7.963768115942028e-06, "loss": 0.0005860131233930588, "step": 1100 }, { "epoch": 0.14625585023400936, "grad_norm": 0.0017371033318340778, "learning_rate": 8.144927536231884e-06, "loss": 0.0005623264610767364, "step": 1125 }, { "epoch": 0.14950598023920958, "grad_norm": 0.0028496291488409042, "learning_rate": 8.326086956521739e-06, "loss": 0.0005109354481101036, "step": 1150 }, { "epoch": 0.15275611024440977, "grad_norm": 0.0014431331073865294, "learning_rate": 8.507246376811595e-06, "loss": 0.0005302329733967781, "step": 1175 }, { "epoch": 0.15600624024961, "grad_norm": 0.0023162339348345995, "learning_rate": 8.68840579710145e-06, "loss": 0.000517817810177803, "step": 1200 }, { "epoch": 0.15925637025481018, "grad_norm": 0.0029457092750817537, "learning_rate": 8.869565217391304e-06, "loss": 0.0005169714242219925, "step": 1225 }, { "epoch": 0.1625065002600104, "grad_norm": 0.0017235144041478634, "learning_rate": 9.05072463768116e-06, "loss": 0.0005387067794799805, "step": 1250 }, { "epoch": 0.16575663026521062, "grad_norm": 0.0014493406051769853, "learning_rate": 9.231884057971015e-06, "loss": 0.0004893744364380837, "step": 1275 }, { "epoch": 0.1690067602704108, "grad_norm": 0.0021185707300901413, "learning_rate": 9.41304347826087e-06, "loss": 0.0004978740215301514, "step": 1300 }, { "epoch": 0.17225689027561103, "grad_norm": 0.002453757682815194, "learning_rate": 9.594202898550725e-06, "loss": 0.0005677514523267746, "step": 1325 }, { "epoch": 0.17550702028081122, "grad_norm": 0.0008572939550504088, "learning_rate": 9.775362318840581e-06, "loss": 0.000497000552713871, "step": 1350 }, { "epoch": 0.17875715028601144, "grad_norm": 0.0018615953158587217, "learning_rate": 9.956521739130436e-06, "loss": 0.0005274380370974541, "step": 1375 }, { "epoch": 0.18200728029121166, "grad_norm": 0.002548182150349021, "learning_rate": 1.013768115942029e-05, "loss": 0.0004912593960762024, "step": 1400 }, { "epoch": 0.18525741029641185, "grad_norm": 0.002343876985833049, "learning_rate": 1.0318840579710145e-05, "loss": 0.0005362540483474732, "step": 1425 }, { "epoch": 0.18850754030161207, "grad_norm": 0.0014049322344362736, "learning_rate": 1.05e-05, "loss": 0.00045400157570838926, "step": 1450 }, { "epoch": 0.19175767030681226, "grad_norm": 0.00521356426179409, "learning_rate": 1.0681159420289856e-05, "loss": 0.0005186598747968674, "step": 1475 }, { "epoch": 0.19500780031201248, "grad_norm": 0.0024857220705598593, "learning_rate": 1.086231884057971e-05, "loss": 0.000503481850028038, "step": 1500 }, { "epoch": 0.1982579303172127, "grad_norm": 0.0017878555227071047, "learning_rate": 1.1043478260869566e-05, "loss": 0.00044301837682724, "step": 1525 }, { "epoch": 0.2015080603224129, "grad_norm": 0.0029132412746548653, "learning_rate": 1.122463768115942e-05, "loss": 0.0005477859079837799, "step": 1550 }, { "epoch": 0.2047581903276131, "grad_norm": 0.003274207701906562, "learning_rate": 1.1405797101449275e-05, "loss": 0.0005001088976860046, "step": 1575 }, { "epoch": 0.2080083203328133, "grad_norm": 0.0017230460653081536, "learning_rate": 1.1586956521739131e-05, "loss": 0.0005191057920455932, "step": 1600 }, { "epoch": 0.21125845033801352, "grad_norm": 0.0017725358484312892, "learning_rate": 1.1768115942028986e-05, "loss": 0.0005417963117361069, "step": 1625 }, { "epoch": 0.21450858034321374, "grad_norm": 0.0017839234787970781, "learning_rate": 1.1949275362318842e-05, "loss": 0.0004936951398849487, "step": 1650 }, { "epoch": 0.21775871034841393, "grad_norm": 0.0019156673224642873, "learning_rate": 1.2130434782608697e-05, "loss": 0.00043773382902145385, "step": 1675 }, { "epoch": 0.22100884035361415, "grad_norm": 0.0025115245953202248, "learning_rate": 1.2311594202898551e-05, "loss": 0.0005085283890366554, "step": 1700 }, { "epoch": 0.22425897035881434, "grad_norm": 0.002715683775022626, "learning_rate": 1.2492753623188407e-05, "loss": 0.00047373753041028975, "step": 1725 }, { "epoch": 0.22750910036401456, "grad_norm": 0.003488801419734955, "learning_rate": 1.2673913043478262e-05, "loss": 0.0004893385618925095, "step": 1750 }, { "epoch": 0.23075923036921478, "grad_norm": 0.0053019351325929165, "learning_rate": 1.2855072463768116e-05, "loss": 0.0004813239723443985, "step": 1775 }, { "epoch": 0.23400936037441497, "grad_norm": 0.005336040630936623, "learning_rate": 1.3036231884057972e-05, "loss": 0.00048693574965000155, "step": 1800 }, { "epoch": 0.2372594903796152, "grad_norm": 0.0017795194871723652, "learning_rate": 1.3217391304347825e-05, "loss": 0.0004995526745915413, "step": 1825 }, { "epoch": 0.24050962038481538, "grad_norm": 0.0011278062593191862, "learning_rate": 1.3398550724637681e-05, "loss": 0.00046038780361413957, "step": 1850 }, { "epoch": 0.2437597503900156, "grad_norm": 0.002104923827573657, "learning_rate": 1.3579710144927538e-05, "loss": 0.00047762546688318253, "step": 1875 }, { "epoch": 0.24700988039521582, "grad_norm": 0.0019306123722344637, "learning_rate": 1.376086956521739e-05, "loss": 0.000521504357457161, "step": 1900 }, { "epoch": 0.250260010400416, "grad_norm": 0.002995668677613139, "learning_rate": 1.3942028985507247e-05, "loss": 0.000536748543381691, "step": 1925 }, { "epoch": 0.2535101404056162, "grad_norm": 0.0014928326709195971, "learning_rate": 1.4123188405797103e-05, "loss": 0.00046544995158910753, "step": 1950 }, { "epoch": 0.25676027041081645, "grad_norm": 0.0018402858404442668, "learning_rate": 1.4304347826086959e-05, "loss": 0.00046654198318719865, "step": 1975 }, { "epoch": 0.26001040041601664, "grad_norm": 0.004148806910961866, "learning_rate": 1.4485507246376812e-05, "loss": 0.0005035639926791191, "step": 2000 }, { "epoch": 0.26326053042121683, "grad_norm": 0.0056002759374678135, "learning_rate": 1.4666666666666668e-05, "loss": 0.00047159191220998766, "step": 2025 }, { "epoch": 0.2665106604264171, "grad_norm": 0.00518020149320364, "learning_rate": 1.4847826086956524e-05, "loss": 0.0005678045004606246, "step": 2050 }, { "epoch": 0.26976079043161727, "grad_norm": 0.0023816865868866444, "learning_rate": 1.5028985507246377e-05, "loss": 0.0004457936435937882, "step": 2075 }, { "epoch": 0.27301092043681746, "grad_norm": 0.00243125157430768, "learning_rate": 1.5210144927536233e-05, "loss": 0.00046467509120702745, "step": 2100 }, { "epoch": 0.2762610504420177, "grad_norm": 0.0009784717112779617, "learning_rate": 1.5391304347826088e-05, "loss": 0.0004520739614963531, "step": 2125 }, { "epoch": 0.2795111804472179, "grad_norm": 0.0021698814816772938, "learning_rate": 1.5572463768115944e-05, "loss": 0.00043580066412687304, "step": 2150 }, { "epoch": 0.2827613104524181, "grad_norm": 0.000734630273655057, "learning_rate": 1.5753623188405797e-05, "loss": 0.0004298238828778267, "step": 2175 }, { "epoch": 0.2860114404576183, "grad_norm": 0.0020142493303865194, "learning_rate": 1.5934782608695653e-05, "loss": 0.0005486938357353211, "step": 2200 }, { "epoch": 0.28926157046281853, "grad_norm": 0.0026363793294876814, "learning_rate": 1.611594202898551e-05, "loss": 0.00046887725591659545, "step": 2225 }, { "epoch": 0.2925117004680187, "grad_norm": 0.00481174373999238, "learning_rate": 1.6297101449275362e-05, "loss": 0.00042210947722196577, "step": 2250 }, { "epoch": 0.2957618304732189, "grad_norm": 0.0007976884953677654, "learning_rate": 1.6478260869565218e-05, "loss": 0.00042526666074991224, "step": 2275 }, { "epoch": 0.29901196047841916, "grad_norm": 0.0022998733911663294, "learning_rate": 1.6659420289855074e-05, "loss": 0.00047022908926010133, "step": 2300 }, { "epoch": 0.30226209048361935, "grad_norm": 0.0029255158733576536, "learning_rate": 1.6840579710144927e-05, "loss": 0.000418592244386673, "step": 2325 }, { "epoch": 0.30551222048881954, "grad_norm": 0.0019420625176280737, "learning_rate": 1.7021739130434783e-05, "loss": 0.0004478084295988083, "step": 2350 }, { "epoch": 0.3087623504940198, "grad_norm": 0.0022736522369086742, "learning_rate": 1.720289855072464e-05, "loss": 0.0004615306109189987, "step": 2375 }, { "epoch": 0.31201248049922, "grad_norm": 0.0010760062141343951, "learning_rate": 1.7384057971014496e-05, "loss": 0.0004631573334336281, "step": 2400 }, { "epoch": 0.31526261050442017, "grad_norm": 0.0044555943459272385, "learning_rate": 1.756521739130435e-05, "loss": 0.0004210951179265976, "step": 2425 }, { "epoch": 0.31851274050962036, "grad_norm": 0.003932526335120201, "learning_rate": 1.7746376811594205e-05, "loss": 0.000449698381125927, "step": 2450 }, { "epoch": 0.3217628705148206, "grad_norm": 0.002491120947524905, "learning_rate": 1.792753623188406e-05, "loss": 0.00045762836933135984, "step": 2475 }, { "epoch": 0.3250130005200208, "grad_norm": 0.0024895304813981056, "learning_rate": 1.8108695652173913e-05, "loss": 0.0004615296423435211, "step": 2500 }, { "epoch": 0.328263130525221, "grad_norm": 0.00346749578602612, "learning_rate": 1.828985507246377e-05, "loss": 0.0004106666520237923, "step": 2525 }, { "epoch": 0.33151326053042124, "grad_norm": 0.0021729774307459593, "learning_rate": 1.8471014492753626e-05, "loss": 0.00039652612060308456, "step": 2550 }, { "epoch": 0.33476339053562143, "grad_norm": 0.0037798353005200624, "learning_rate": 1.865217391304348e-05, "loss": 0.00044131282716989515, "step": 2575 }, { "epoch": 0.3380135205408216, "grad_norm": 0.005481760948896408, "learning_rate": 1.8833333333333335e-05, "loss": 0.0004480358213186264, "step": 2600 }, { "epoch": 0.34126365054602187, "grad_norm": 0.0019796863198280334, "learning_rate": 1.9014492753623188e-05, "loss": 0.0004559497907757759, "step": 2625 }, { "epoch": 0.34451378055122206, "grad_norm": 0.0025186336133629084, "learning_rate": 1.9195652173913044e-05, "loss": 0.0004142383486032486, "step": 2650 }, { "epoch": 0.34776391055642225, "grad_norm": 0.0019014193676412106, "learning_rate": 1.9376811594202897e-05, "loss": 0.0004085032269358635, "step": 2675 }, { "epoch": 0.35101404056162244, "grad_norm": 0.003675377694889903, "learning_rate": 1.9557971014492753e-05, "loss": 0.00044845666736364364, "step": 2700 }, { "epoch": 0.3542641705668227, "grad_norm": 0.0008569825440645218, "learning_rate": 1.973913043478261e-05, "loss": 0.0004178711771965027, "step": 2725 }, { "epoch": 0.3575143005720229, "grad_norm": 0.0027375146746635437, "learning_rate": 1.9920289855072465e-05, "loss": 0.000369691476225853, "step": 2750 }, { "epoch": 0.36076443057722307, "grad_norm": 0.0021465872414410114, "learning_rate": 2.0101449275362318e-05, "loss": 0.00041070599108934404, "step": 2775 }, { "epoch": 0.3640145605824233, "grad_norm": 0.0017981152050197124, "learning_rate": 2.0282608695652174e-05, "loss": 0.00043407246470451356, "step": 2800 }, { "epoch": 0.3672646905876235, "grad_norm": 0.0034601977095007896, "learning_rate": 2.046376811594203e-05, "loss": 0.00042522311210632327, "step": 2825 }, { "epoch": 0.3705148205928237, "grad_norm": 0.0035561842378228903, "learning_rate": 2.0644927536231883e-05, "loss": 0.0003913164883852005, "step": 2850 }, { "epoch": 0.37376495059802395, "grad_norm": 0.005427898373454809, "learning_rate": 2.082608695652174e-05, "loss": 0.00041633348912000655, "step": 2875 }, { "epoch": 0.37701508060322414, "grad_norm": 0.001540972269140184, "learning_rate": 2.1007246376811596e-05, "loss": 0.000437643900513649, "step": 2900 }, { "epoch": 0.38026521060842433, "grad_norm": 0.008584934286773205, "learning_rate": 2.1188405797101452e-05, "loss": 0.0004209858551621437, "step": 2925 }, { "epoch": 0.3835153406136245, "grad_norm": 0.003871705150231719, "learning_rate": 2.1369565217391305e-05, "loss": 0.0004569174721837044, "step": 2950 }, { "epoch": 0.38676547061882477, "grad_norm": 0.003933009225875139, "learning_rate": 2.155072463768116e-05, "loss": 0.00039284847676754, "step": 2975 }, { "epoch": 0.39001560062402496, "grad_norm": 0.0023773452267050743, "learning_rate": 2.1731884057971017e-05, "loss": 0.0003957047685980797, "step": 3000 }, { "epoch": 0.39326573062922515, "grad_norm": 0.0013754197861999273, "learning_rate": 2.191304347826087e-05, "loss": 0.00040918096899986264, "step": 3025 }, { "epoch": 0.3965158606344254, "grad_norm": 0.0013438657624647021, "learning_rate": 2.2094202898550726e-05, "loss": 0.00042451847344636916, "step": 3050 }, { "epoch": 0.3997659906396256, "grad_norm": 0.0018076892010867596, "learning_rate": 2.2275362318840582e-05, "loss": 0.000429234579205513, "step": 3075 }, { "epoch": 0.4030161206448258, "grad_norm": 0.002512214705348015, "learning_rate": 2.2456521739130438e-05, "loss": 0.00044652506709098817, "step": 3100 }, { "epoch": 0.40626625065002603, "grad_norm": 0.002839904511347413, "learning_rate": 2.263768115942029e-05, "loss": 0.00040985174477100374, "step": 3125 }, { "epoch": 0.4095163806552262, "grad_norm": 0.0019431107211858034, "learning_rate": 2.2818840579710147e-05, "loss": 0.0003903954103589058, "step": 3150 }, { "epoch": 0.4127665106604264, "grad_norm": 0.0020985049195587635, "learning_rate": 2.3000000000000003e-05, "loss": 0.00038104344159364703, "step": 3175 }, { "epoch": 0.4160166406656266, "grad_norm": 0.0028055645525455475, "learning_rate": 2.3181159420289856e-05, "loss": 0.0003827373683452606, "step": 3200 }, { "epoch": 0.41926677067082685, "grad_norm": 0.0014860191149637103, "learning_rate": 2.3362318840579712e-05, "loss": 0.00043064661324024203, "step": 3225 }, { "epoch": 0.42251690067602704, "grad_norm": 0.0033869794569909573, "learning_rate": 2.354347826086957e-05, "loss": 0.00044150054454803465, "step": 3250 }, { "epoch": 0.42576703068122723, "grad_norm": 0.001350346370600164, "learning_rate": 2.372463768115942e-05, "loss": 0.00036799222230911256, "step": 3275 }, { "epoch": 0.4290171606864275, "grad_norm": 0.0018407037714496255, "learning_rate": 2.3905797101449278e-05, "loss": 0.00041019417345523836, "step": 3300 }, { "epoch": 0.43226729069162767, "grad_norm": 0.0030828621238470078, "learning_rate": 2.408695652173913e-05, "loss": 0.00040250256657600405, "step": 3325 }, { "epoch": 0.43551742069682786, "grad_norm": 0.005468167830258608, "learning_rate": 2.4268115942028987e-05, "loss": 0.0003616174682974815, "step": 3350 }, { "epoch": 0.4387675507020281, "grad_norm": 0.001769745722413063, "learning_rate": 2.444927536231884e-05, "loss": 0.0003935152292251587, "step": 3375 }, { "epoch": 0.4420176807072283, "grad_norm": 0.004243707749992609, "learning_rate": 2.4630434782608696e-05, "loss": 0.0003487700968980789, "step": 3400 }, { "epoch": 0.4452678107124285, "grad_norm": 0.001457527163438499, "learning_rate": 2.4811594202898552e-05, "loss": 0.00038313735276460645, "step": 3425 }, { "epoch": 0.4485179407176287, "grad_norm": 0.004237140994518995, "learning_rate": 2.4992753623188405e-05, "loss": 0.00040549322962760923, "step": 3450 }, { "epoch": 0.4485179407176287, "eval_loss": 0.0014288317179307342, "eval_runtime": 9.4821, "eval_samples_per_second": 527.308, "eval_steps_per_second": 4.218, "step": 3450 }, { "epoch": 0.4485179407176287, "eval_holdout_avg_strict_f1": 0.016948437606658096, "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": 0.04347826086956522, "eval_holdout_nemotron_pii_strict_f1": 0.028890015205271163, "eval_holdout_open_pii_masking_500k_strict_f1": 0.07240773286467486, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.04165680473372781, "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": 0.45176807072282893, "grad_norm": 0.0014306495431810617, "learning_rate": 2.5173913043478264e-05, "loss": 0.0003895667567849159, "step": 3475 }, { "epoch": 0.4550182007280291, "grad_norm": 0.0033567098435014486, "learning_rate": 2.5355072463768113e-05, "loss": 0.0003654065728187561, "step": 3500 }, { "epoch": 0.4582683307332293, "grad_norm": 0.0033907731994986534, "learning_rate": 2.553623188405797e-05, "loss": 0.0004192650318145752, "step": 3525 }, { "epoch": 0.46151846073842956, "grad_norm": 0.002767309546470642, "learning_rate": 2.5717391304347826e-05, "loss": 0.00045176178216934206, "step": 3550 }, { "epoch": 0.46476859074362975, "grad_norm": 0.0033274965826421976, "learning_rate": 2.5898550724637682e-05, "loss": 0.00036267347633838653, "step": 3575 }, { "epoch": 0.46801872074882994, "grad_norm": 0.0012526543578132987, "learning_rate": 2.6079710144927538e-05, "loss": 0.0003706477209925652, "step": 3600 }, { "epoch": 0.4712688507540302, "grad_norm": 0.0025104728993028402, "learning_rate": 2.6260869565217394e-05, "loss": 0.0003582199662923813, "step": 3625 }, { "epoch": 0.4745189807592304, "grad_norm": 0.001733158016577363, "learning_rate": 2.644202898550725e-05, "loss": 0.00037459593266248704, "step": 3650 }, { "epoch": 0.47776911076443057, "grad_norm": 0.014838664792478085, "learning_rate": 2.66231884057971e-05, "loss": 0.000381452776491642, "step": 3675 }, { "epoch": 0.48101924076963076, "grad_norm": 0.0015709763392806053, "learning_rate": 2.6804347826086956e-05, "loss": 0.000379287488758564, "step": 3700 }, { "epoch": 0.484269370774831, "grad_norm": 0.0009885560721158981, "learning_rate": 2.6985507246376812e-05, "loss": 0.0003702220320701599, "step": 3725 }, { "epoch": 0.4875195007800312, "grad_norm": 0.003496927907690406, "learning_rate": 2.716666666666667e-05, "loss": 0.00037388518452644346, "step": 3750 }, { "epoch": 0.4907696307852314, "grad_norm": 0.0013370664091780782, "learning_rate": 2.7347826086956525e-05, "loss": 0.00038881190121173856, "step": 3775 }, { "epoch": 0.49401976079043164, "grad_norm": 0.0019693628419190645, "learning_rate": 2.752898550724638e-05, "loss": 0.00037656128406524656, "step": 3800 }, { "epoch": 0.49726989079563183, "grad_norm": 0.001666913041844964, "learning_rate": 2.7710144927536237e-05, "loss": 0.0004192305356264114, "step": 3825 }, { "epoch": 0.500520020800832, "grad_norm": 0.004715986084192991, "learning_rate": 2.7891304347826087e-05, "loss": 0.0003989679366350174, "step": 3850 }, { "epoch": 0.5037701508060323, "grad_norm": 0.004425929393619299, "learning_rate": 2.8072463768115943e-05, "loss": 0.0003500617295503616, "step": 3875 }, { "epoch": 0.5070202808112324, "grad_norm": 0.002427851315587759, "learning_rate": 2.82536231884058e-05, "loss": 0.0003932202234864235, "step": 3900 }, { "epoch": 0.5102704108164327, "grad_norm": 0.0017338527832180262, "learning_rate": 2.8434782608695655e-05, "loss": 0.0003991245478391647, "step": 3925 }, { "epoch": 0.5135205408216329, "grad_norm": 0.0019661737605929375, "learning_rate": 2.8615942028985508e-05, "loss": 0.0004087170585989952, "step": 3950 }, { "epoch": 0.516770670826833, "grad_norm": 0.004153737332671881, "learning_rate": 2.8797101449275364e-05, "loss": 0.00037440124899148944, "step": 3975 }, { "epoch": 0.5200208008320333, "grad_norm": 0.0021952821407467127, "learning_rate": 2.897826086956522e-05, "loss": 0.00032810430973768235, "step": 4000 }, { "epoch": 0.5232709308372335, "grad_norm": 0.00245103077031672, "learning_rate": 2.9159420289855073e-05, "loss": 0.00035349562764167784, "step": 4025 }, { "epoch": 0.5265210608424337, "grad_norm": 0.0019252462079748511, "learning_rate": 2.934057971014493e-05, "loss": 0.0003406635299324989, "step": 4050 }, { "epoch": 0.5297711908476339, "grad_norm": 0.0033155896235257387, "learning_rate": 2.9521739130434782e-05, "loss": 0.0003747899085283279, "step": 4075 }, { "epoch": 0.5330213208528342, "grad_norm": 0.0012676240876317024, "learning_rate": 2.9702898550724638e-05, "loss": 0.00034757569432258606, "step": 4100 }, { "epoch": 0.5362714508580343, "grad_norm": 0.0037625425029546022, "learning_rate": 2.9884057971014494e-05, "loss": 0.0003790777549147606, "step": 4125 }, { "epoch": 0.5395215808632345, "grad_norm": 0.005746638402342796, "learning_rate": 3.006521739130435e-05, "loss": 0.000355856865644455, "step": 4150 }, { "epoch": 0.5427717108684348, "grad_norm": 0.002143938560038805, "learning_rate": 3.0246376811594207e-05, "loss": 0.0004532543942332268, "step": 4175 }, { "epoch": 0.5460218408736349, "grad_norm": 0.0009120068280026317, "learning_rate": 3.0427536231884056e-05, "loss": 0.0003795912489295006, "step": 4200 }, { "epoch": 0.5492719708788352, "grad_norm": 0.002007429488003254, "learning_rate": 3.0608695652173916e-05, "loss": 0.0003673683106899261, "step": 4225 }, { "epoch": 0.5525221008840354, "grad_norm": 0.002023761859163642, "learning_rate": 3.078985507246377e-05, "loss": 0.00035739000886678694, "step": 4250 }, { "epoch": 0.5557722308892356, "grad_norm": 0.0014700735919177532, "learning_rate": 3.097101449275363e-05, "loss": 0.0003841959312558174, "step": 4275 }, { "epoch": 0.5590223608944358, "grad_norm": 0.01717543788254261, "learning_rate": 3.115217391304348e-05, "loss": 0.0003442119434475899, "step": 4300 }, { "epoch": 0.5622724908996359, "grad_norm": 0.0022744322195649147, "learning_rate": 3.1333333333333334e-05, "loss": 0.0004083585739135742, "step": 4325 }, { "epoch": 0.5655226209048362, "grad_norm": 0.0019075083546340466, "learning_rate": 3.151449275362319e-05, "loss": 0.00033581096678972247, "step": 4350 }, { "epoch": 0.5687727509100364, "grad_norm": 0.003801671089604497, "learning_rate": 3.1695652173913046e-05, "loss": 0.00036067895591259004, "step": 4375 }, { "epoch": 0.5720228809152366, "grad_norm": 0.0011975554516538978, "learning_rate": 3.18768115942029e-05, "loss": 0.0003966550901532173, "step": 4400 }, { "epoch": 0.5752730109204368, "grad_norm": 0.005756833590567112, "learning_rate": 3.205797101449275e-05, "loss": 0.0003798803687095642, "step": 4425 }, { "epoch": 0.5785231409256371, "grad_norm": 0.002057137433439493, "learning_rate": 3.223913043478261e-05, "loss": 0.00037363722920417784, "step": 4450 }, { "epoch": 0.5817732709308372, "grad_norm": 0.0018292538588866591, "learning_rate": 3.2420289855072464e-05, "loss": 0.0003827802836894989, "step": 4475 }, { "epoch": 0.5850234009360374, "grad_norm": 0.0031336594838649035, "learning_rate": 3.2601449275362324e-05, "loss": 0.00031954482197761537, "step": 4500 }, { "epoch": 0.5882735309412377, "grad_norm": 0.002637260127812624, "learning_rate": 3.278260869565217e-05, "loss": 0.0003741474822163582, "step": 4525 }, { "epoch": 0.5915236609464378, "grad_norm": 0.0017657590797170997, "learning_rate": 3.296376811594203e-05, "loss": 0.0003575438633561134, "step": 4550 }, { "epoch": 0.5947737909516381, "grad_norm": 0.00354047492146492, "learning_rate": 3.314492753623188e-05, "loss": 0.0003497960790991783, "step": 4575 }, { "epoch": 0.5980239209568383, "grad_norm": 0.0017961938865482807, "learning_rate": 3.332608695652174e-05, "loss": 0.00039899878203868865, "step": 4600 }, { "epoch": 0.6012740509620385, "grad_norm": 0.0013773336540907621, "learning_rate": 3.3507246376811594e-05, "loss": 0.0003468652069568634, "step": 4625 }, { "epoch": 0.6045241809672387, "grad_norm": 0.0015784098068252206, "learning_rate": 3.3688405797101454e-05, "loss": 0.00034876059740781786, "step": 4650 }, { "epoch": 0.607774310972439, "grad_norm": 0.003309419145807624, "learning_rate": 3.386956521739131e-05, "loss": 0.000346483550965786, "step": 4675 }, { "epoch": 0.6110244409776391, "grad_norm": 0.0019642598927021027, "learning_rate": 3.405072463768116e-05, "loss": 0.0003129390254616737, "step": 4700 }, { "epoch": 0.6142745709828393, "grad_norm": 0.0018581639742478728, "learning_rate": 3.423188405797101e-05, "loss": 0.00032798755913972857, "step": 4725 }, { "epoch": 0.6175247009880396, "grad_norm": 0.0029012670274823904, "learning_rate": 3.441304347826087e-05, "loss": 0.00033405110239982606, "step": 4750 }, { "epoch": 0.6207748309932397, "grad_norm": 0.002787525998428464, "learning_rate": 3.4594202898550725e-05, "loss": 0.0003223710134625435, "step": 4775 }, { "epoch": 0.62402496099844, "grad_norm": 0.0017276693833991885, "learning_rate": 3.4775362318840584e-05, "loss": 0.0003574707731604576, "step": 4800 }, { "epoch": 0.6272750910036401, "grad_norm": 0.0032260166481137276, "learning_rate": 3.495652173913044e-05, "loss": 0.00036472782492637636, "step": 4825 }, { "epoch": 0.6305252210088403, "grad_norm": 0.002348755020648241, "learning_rate": 3.51376811594203e-05, "loss": 0.0002934296987950802, "step": 4850 }, { "epoch": 0.6337753510140406, "grad_norm": 0.0017877062782645226, "learning_rate": 3.531884057971014e-05, "loss": 0.00033006574958562853, "step": 4875 }, { "epoch": 0.6370254810192407, "grad_norm": 0.0011508421739563346, "learning_rate": 3.55e-05, "loss": 0.00033879075199365615, "step": 4900 }, { "epoch": 0.640275611024441, "grad_norm": 0.0021689175628125668, "learning_rate": 3.5681159420289855e-05, "loss": 0.00034071825444698334, "step": 4925 }, { "epoch": 0.6435257410296412, "grad_norm": 0.001443523564375937, "learning_rate": 3.5862318840579715e-05, "loss": 0.0003129898384213448, "step": 4950 }, { "epoch": 0.6467758710348414, "grad_norm": 0.001089542405679822, "learning_rate": 3.604347826086957e-05, "loss": 0.00034003332257270813, "step": 4975 }, { "epoch": 0.6500260010400416, "grad_norm": 0.004490668885409832, "learning_rate": 3.622463768115942e-05, "loss": 0.00037308726459741595, "step": 5000 }, { "epoch": 0.6532761310452418, "grad_norm": 0.0019078904297202826, "learning_rate": 3.640579710144928e-05, "loss": 0.00040014833211898804, "step": 5025 }, { "epoch": 0.656526261050442, "grad_norm": 0.005327039398252964, "learning_rate": 3.658695652173913e-05, "loss": 0.00038816750049591064, "step": 5050 }, { "epoch": 0.6597763910556422, "grad_norm": 0.0015874936943873763, "learning_rate": 3.6768115942028985e-05, "loss": 0.0003395514935255051, "step": 5075 }, { "epoch": 0.6630265210608425, "grad_norm": 0.001610973384231329, "learning_rate": 3.694927536231884e-05, "loss": 0.0003646326065063477, "step": 5100 }, { "epoch": 0.6662766510660426, "grad_norm": 0.0019586284179240465, "learning_rate": 3.71304347826087e-05, "loss": 0.00032726649194955823, "step": 5125 }, { "epoch": 0.6695267810712429, "grad_norm": 0.0011525078443810344, "learning_rate": 3.731159420289855e-05, "loss": 0.0003709142655134201, "step": 5150 }, { "epoch": 0.6727769110764431, "grad_norm": 0.0020568196196109056, "learning_rate": 3.749275362318841e-05, "loss": 0.0004013935476541519, "step": 5175 }, { "epoch": 0.6760270410816432, "grad_norm": 0.0034161447547376156, "learning_rate": 3.767391304347826e-05, "loss": 0.00032214373350143434, "step": 5200 }, { "epoch": 0.6792771710868435, "grad_norm": 0.0010419136378914118, "learning_rate": 3.7855072463768116e-05, "loss": 0.000292956680059433, "step": 5225 }, { "epoch": 0.6825273010920437, "grad_norm": 0.0020100681576877832, "learning_rate": 3.803623188405797e-05, "loss": 0.00033670149743556975, "step": 5250 }, { "epoch": 0.6857774310972439, "grad_norm": 0.004615044221282005, "learning_rate": 3.821739130434783e-05, "loss": 0.00035760205239057543, "step": 5275 }, { "epoch": 0.6890275611024441, "grad_norm": 0.0007368104998022318, "learning_rate": 3.839855072463768e-05, "loss": 0.00034552190452814103, "step": 5300 }, { "epoch": 0.6922776911076443, "grad_norm": 0.001840224489569664, "learning_rate": 3.857971014492754e-05, "loss": 0.0003251539543271065, "step": 5325 }, { "epoch": 0.6955278211128445, "grad_norm": 0.0034191531594842672, "learning_rate": 3.876086956521739e-05, "loss": 0.0003743323311209679, "step": 5350 }, { "epoch": 0.6987779511180447, "grad_norm": 0.002969014458358288, "learning_rate": 3.894202898550725e-05, "loss": 0.0003549868240952492, "step": 5375 }, { "epoch": 0.7020280811232449, "grad_norm": 0.002682388760149479, "learning_rate": 3.91231884057971e-05, "loss": 0.0003697166219353676, "step": 5400 }, { "epoch": 0.7052782111284451, "grad_norm": 0.0019561341032385826, "learning_rate": 3.930434782608696e-05, "loss": 0.00029268305748701094, "step": 5425 }, { "epoch": 0.7085283411336454, "grad_norm": 0.0015227431431412697, "learning_rate": 3.948550724637681e-05, "loss": 0.00030088482424616813, "step": 5450 }, { "epoch": 0.7117784711388455, "grad_norm": 0.0008432468748651445, "learning_rate": 3.966666666666667e-05, "loss": 0.0003448799252510071, "step": 5475 }, { "epoch": 0.7150286011440458, "grad_norm": 0.0027734299656003714, "learning_rate": 3.9847826086956524e-05, "loss": 0.0003730638697743416, "step": 5500 }, { "epoch": 0.718278731149246, "grad_norm": 0.002775531494989991, "learning_rate": 4.002898550724638e-05, "loss": 0.0002861537970602512, "step": 5525 }, { "epoch": 0.7215288611544461, "grad_norm": 0.0013877362944185734, "learning_rate": 4.0210144927536236e-05, "loss": 0.0003062456473708153, "step": 5550 }, { "epoch": 0.7247789911596464, "grad_norm": 0.0016100159846246243, "learning_rate": 4.039130434782609e-05, "loss": 0.00034022834151983263, "step": 5575 }, { "epoch": 0.7280291211648466, "grad_norm": 0.0023292386904358864, "learning_rate": 4.057246376811594e-05, "loss": 0.00032042227685451506, "step": 5600 }, { "epoch": 0.7312792511700468, "grad_norm": 0.005723954644054174, "learning_rate": 4.07536231884058e-05, "loss": 0.00036787450313568114, "step": 5625 }, { "epoch": 0.734529381175247, "grad_norm": 0.007385662756860256, "learning_rate": 4.0934782608695654e-05, "loss": 0.00030214842408895495, "step": 5650 }, { "epoch": 0.7377795111804473, "grad_norm": 0.0016194393392652273, "learning_rate": 4.111594202898551e-05, "loss": 0.0003026936203241348, "step": 5675 }, { "epoch": 0.7410296411856474, "grad_norm": 0.0011678567389026284, "learning_rate": 4.1297101449275366e-05, "loss": 0.0003290276974439621, "step": 5700 }, { "epoch": 0.7442797711908476, "grad_norm": 0.0015876541147008538, "learning_rate": 4.147826086956522e-05, "loss": 0.0002660868316888809, "step": 5725 }, { "epoch": 0.7475299011960479, "grad_norm": 0.002573238452896476, "learning_rate": 4.165942028985507e-05, "loss": 0.0003120236098766327, "step": 5750 }, { "epoch": 0.750780031201248, "grad_norm": 0.001261972007341683, "learning_rate": 4.184057971014493e-05, "loss": 0.000330447293817997, "step": 5775 }, { "epoch": 0.7540301612064483, "grad_norm": 0.002024536021053791, "learning_rate": 4.2021739130434784e-05, "loss": 0.0003500768169760704, "step": 5800 }, { "epoch": 0.7572802912116484, "grad_norm": 0.0013312718365341425, "learning_rate": 4.220289855072464e-05, "loss": 0.00034043505787849425, "step": 5825 }, { "epoch": 0.7605304212168487, "grad_norm": 0.0014061352703720331, "learning_rate": 4.23840579710145e-05, "loss": 0.0003583569824695587, "step": 5850 }, { "epoch": 0.7637805512220489, "grad_norm": 0.0017677943687886, "learning_rate": 4.256521739130435e-05, "loss": 0.0003040175698697567, "step": 5875 }, { "epoch": 0.767030681227249, "grad_norm": 0.002769756829366088, "learning_rate": 4.274637681159421e-05, "loss": 0.00031752903014421464, "step": 5900 }, { "epoch": 0.7702808112324493, "grad_norm": 0.0013718277914449573, "learning_rate": 4.2927536231884055e-05, "loss": 0.0003393003344535828, "step": 5925 }, { "epoch": 0.7735309412376495, "grad_norm": 0.0019314177334308624, "learning_rate": 4.3108695652173915e-05, "loss": 0.00027401041239500046, "step": 5950 }, { "epoch": 0.7767810712428497, "grad_norm": 0.007918702438473701, "learning_rate": 4.328985507246377e-05, "loss": 0.0002910470962524414, "step": 5975 }, { "epoch": 0.7800312012480499, "grad_norm": 0.0017927872249856591, "learning_rate": 4.347101449275363e-05, "loss": 0.0003286924958229065, "step": 6000 }, { "epoch": 0.7832813312532502, "grad_norm": 0.001361369388177991, "learning_rate": 4.365217391304348e-05, "loss": 0.00030220640823245046, "step": 6025 }, { "epoch": 0.7865314612584503, "grad_norm": 0.0010171420872211456, "learning_rate": 4.383333333333334e-05, "loss": 0.0002842904068529606, "step": 6050 }, { "epoch": 0.7897815912636506, "grad_norm": 0.0032635347452014685, "learning_rate": 4.401449275362319e-05, "loss": 0.00035091206431388857, "step": 6075 }, { "epoch": 0.7930317212688508, "grad_norm": 0.0009199533378705382, "learning_rate": 4.4195652173913045e-05, "loss": 0.0002981584332883358, "step": 6100 }, { "epoch": 0.7962818512740509, "grad_norm": 0.0011878847144544125, "learning_rate": 4.43768115942029e-05, "loss": 0.0002847062610089779, "step": 6125 }, { "epoch": 0.7995319812792512, "grad_norm": 0.0005240865866653621, "learning_rate": 4.455797101449276e-05, "loss": 0.0002426844649016857, "step": 6150 }, { "epoch": 0.8027821112844514, "grad_norm": 0.004690847359597683, "learning_rate": 4.473913043478261e-05, "loss": 0.0003175145760178566, "step": 6175 }, { "epoch": 0.8060322412896516, "grad_norm": 0.002477250760421157, "learning_rate": 4.492028985507247e-05, "loss": 0.0002982656471431255, "step": 6200 }, { "epoch": 0.8092823712948518, "grad_norm": 0.0012452919036149979, "learning_rate": 4.510144927536232e-05, "loss": 0.00032246861606836317, "step": 6225 }, { "epoch": 0.8125325013000521, "grad_norm": 0.0023345041554421186, "learning_rate": 4.5282608695652175e-05, "loss": 0.0002904561534523964, "step": 6250 }, { "epoch": 0.8157826313052522, "grad_norm": 0.0006569608813151717, "learning_rate": 4.546376811594203e-05, "loss": 0.000323328822851181, "step": 6275 }, { "epoch": 0.8190327613104524, "grad_norm": 0.022973662242293358, "learning_rate": 4.564492753623189e-05, "loss": 0.00027932059019804, "step": 6300 }, { "epoch": 0.8222828913156526, "grad_norm": 0.0065062702633440495, "learning_rate": 4.582608695652174e-05, "loss": 0.00029802778735756876, "step": 6325 }, { "epoch": 0.8255330213208528, "grad_norm": 0.005543549545109272, "learning_rate": 4.60072463768116e-05, "loss": 0.00036395326256752017, "step": 6350 }, { "epoch": 0.8287831513260531, "grad_norm": 0.0020637274719774723, "learning_rate": 4.618840579710145e-05, "loss": 0.00036908872425556183, "step": 6375 }, { "epoch": 0.8320332813312532, "grad_norm": 0.003742776345461607, "learning_rate": 4.6369565217391306e-05, "loss": 0.0003229105472564697, "step": 6400 }, { "epoch": 0.8352834113364535, "grad_norm": 0.001703648827970028, "learning_rate": 4.655072463768116e-05, "loss": 0.00033204488456249235, "step": 6425 }, { "epoch": 0.8385335413416537, "grad_norm": 0.0012357374653220177, "learning_rate": 4.673188405797102e-05, "loss": 0.00032585758715867995, "step": 6450 }, { "epoch": 0.8417836713468538, "grad_norm": 0.006874839309602976, "learning_rate": 4.691304347826087e-05, "loss": 0.00027060166001319886, "step": 6475 }, { "epoch": 0.8450338013520541, "grad_norm": 0.0022275864612311125, "learning_rate": 4.7094202898550724e-05, "loss": 0.0003158362582325935, "step": 6500 }, { "epoch": 0.8482839313572543, "grad_norm": 0.0011992513900622725, "learning_rate": 4.727536231884058e-05, "loss": 0.0003127120807766914, "step": 6525 }, { "epoch": 0.8515340613624545, "grad_norm": 0.0010171785252168775, "learning_rate": 4.7456521739130436e-05, "loss": 0.0002979818731546402, "step": 6550 }, { "epoch": 0.8547841913676547, "grad_norm": 0.0028656974900513887, "learning_rate": 4.7637681159420296e-05, "loss": 0.00031414445489645, "step": 6575 }, { "epoch": 0.858034321372855, "grad_norm": 0.0008505930309183896, "learning_rate": 4.781884057971014e-05, "loss": 0.000277229230850935, "step": 6600 }, { "epoch": 0.8612844513780551, "grad_norm": 0.0007299727294594049, "learning_rate": 4.8e-05, "loss": 0.0002848735637962818, "step": 6625 }, { "epoch": 0.8645345813832553, "grad_norm": 0.001255713519640267, "learning_rate": 4.8181159420289854e-05, "loss": 0.00028432700783014296, "step": 6650 }, { "epoch": 0.8677847113884556, "grad_norm": 0.0008443425176665187, "learning_rate": 4.8362318840579714e-05, "loss": 0.000307377353310585, "step": 6675 }, { "epoch": 0.8710348413936557, "grad_norm": 0.0024411012418568134, "learning_rate": 4.8543478260869566e-05, "loss": 0.00029829660430550573, "step": 6700 }, { "epoch": 0.874284971398856, "grad_norm": 0.001056804321706295, "learning_rate": 4.8724637681159426e-05, "loss": 0.0003243882581591606, "step": 6725 }, { "epoch": 0.8775351014040562, "grad_norm": 0.0011033945484086871, "learning_rate": 4.890579710144928e-05, "loss": 0.0002712445519864559, "step": 6750 }, { "epoch": 0.8807852314092564, "grad_norm": 0.001996325794607401, "learning_rate": 4.908695652173913e-05, "loss": 0.0003028985857963562, "step": 6775 }, { "epoch": 0.8840353614144566, "grad_norm": 0.001191786490380764, "learning_rate": 4.9268115942028984e-05, "loss": 0.00029174651950597763, "step": 6800 }, { "epoch": 0.8872854914196567, "grad_norm": 0.0018096808344125748, "learning_rate": 4.9449275362318844e-05, "loss": 0.0002984482236206532, "step": 6825 }, { "epoch": 0.890535621424857, "grad_norm": 0.0015695627080276608, "learning_rate": 4.96304347826087e-05, "loss": 0.00027819450944662096, "step": 6850 }, { "epoch": 0.8937857514300572, "grad_norm": 0.0014000756200402975, "learning_rate": 4.9811594202898556e-05, "loss": 0.00033636294305324556, "step": 6875 }, { "epoch": 0.8970358814352574, "grad_norm": 0.0017718684393912554, "learning_rate": 4.999275362318841e-05, "loss": 0.0003006098046898842, "step": 6900 }, { "epoch": 0.8970358814352574, "eval_loss": 0.001117659150622785, "eval_runtime": 9.2541, "eval_samples_per_second": 540.302, "eval_steps_per_second": 4.322, "step": 6900 }, { "epoch": 0.8970358814352574, "eval_holdout_avg_strict_f1": 0.047399586588974675, "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": 0.1927814998919386, "eval_holdout_nemotron_pii_strict_f1": 0.062429558484833635, "eval_holdout_open_pii_masking_500k_strict_f1": 0.16210173281162663, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.10408266129032258, "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": 0.9002860114404576, "grad_norm": 0.0030266817193478346, "learning_rate": 4.999998157323963e-05, "loss": 0.00031684111803770065, "step": 6925 }, { "epoch": 0.9035361414456579, "grad_norm": 0.0023532931227236986, "learning_rate": 4.999992318987079e-05, "loss": 0.00027174990624189376, "step": 6950 }, { "epoch": 0.906786271450858, "grad_norm": 0.0015111297834664583, "learning_rate": 4.999982481799595e-05, "loss": 0.00034066613763570784, "step": 6975 }, { "epoch": 0.9100364014560582, "grad_norm": 0.002268970711156726, "learning_rate": 4.999968645777246e-05, "loss": 0.0002984613366425037, "step": 7000 }, { "epoch": 0.9132865314612585, "grad_norm": 0.00104411446955055, "learning_rate": 4.999950810942164e-05, "loss": 0.0003224646672606468, "step": 7025 }, { "epoch": 0.9165366614664586, "grad_norm": 0.001416088198311627, "learning_rate": 4.999928977322876e-05, "loss": 0.0002991696447134018, "step": 7050 }, { "epoch": 0.9197867914716589, "grad_norm": 0.002220858121290803, "learning_rate": 4.999903144954307e-05, "loss": 0.00030125860124826433, "step": 7075 }, { "epoch": 0.9230369214768591, "grad_norm": 0.001945727621205151, "learning_rate": 4.9998733138777766e-05, "loss": 0.00029435833916068076, "step": 7100 }, { "epoch": 0.9262870514820593, "grad_norm": 0.0019027380039915442, "learning_rate": 4.999839484140999e-05, "loss": 0.00026273664087057114, "step": 7125 }, { "epoch": 0.9295371814872595, "grad_norm": 0.0028017114382237196, "learning_rate": 4.9998016557980896e-05, "loss": 0.0002820346690714359, "step": 7150 }, { "epoch": 0.9327873114924597, "grad_norm": 0.0015707556158304214, "learning_rate": 4.999759828909555e-05, "loss": 0.00028507132083177567, "step": 7175 }, { "epoch": 0.9360374414976599, "grad_norm": 0.0019409273518249393, "learning_rate": 4.9997140035422984e-05, "loss": 0.00028136296197772025, "step": 7200 }, { "epoch": 0.9392875715028601, "grad_norm": 0.0018527988577261567, "learning_rate": 4.9996641797696206e-05, "loss": 0.00028836311772465704, "step": 7225 }, { "epoch": 0.9425377015080604, "grad_norm": 0.0027005046140402555, "learning_rate": 4.999610357671217e-05, "loss": 0.0002803043834865093, "step": 7250 }, { "epoch": 0.9457878315132605, "grad_norm": 0.0014811495784670115, "learning_rate": 4.999552537333178e-05, "loss": 0.00028542324900627137, "step": 7275 }, { "epoch": 0.9490379615184608, "grad_norm": 0.0015694370958954096, "learning_rate": 4.99949071884799e-05, "loss": 0.00029463691636919974, "step": 7300 }, { "epoch": 0.9522880915236609, "grad_norm": 0.0013177198125049472, "learning_rate": 4.999424902314534e-05, "loss": 0.00025012722238898277, "step": 7325 }, { "epoch": 0.9555382215288611, "grad_norm": 0.000802877766545862, "learning_rate": 4.9993550878380876e-05, "loss": 0.0002755519188940525, "step": 7350 }, { "epoch": 0.9587883515340614, "grad_norm": 0.0006859932327643037, "learning_rate": 4.999281275530321e-05, "loss": 0.00028787543997168543, "step": 7375 }, { "epoch": 0.9620384815392615, "grad_norm": 0.0023639509454369545, "learning_rate": 4.9992034655093016e-05, "loss": 0.00028885766863822937, "step": 7400 }, { "epoch": 0.9652886115444618, "grad_norm": 0.0009986214572563767, "learning_rate": 4.9991216578994894e-05, "loss": 0.00027358153834939003, "step": 7425 }, { "epoch": 0.968538741549662, "grad_norm": 0.0029798035975545645, "learning_rate": 4.999035852831739e-05, "loss": 0.00027591008692979814, "step": 7450 }, { "epoch": 0.9717888715548622, "grad_norm": 0.0023388254921883345, "learning_rate": 4.998946050443299e-05, "loss": 0.00026363175362348557, "step": 7475 }, { "epoch": 0.9750390015600624, "grad_norm": 0.000977223739027977, "learning_rate": 4.9988522508778144e-05, "loss": 0.00030499791726469995, "step": 7500 }, { "epoch": 0.9782891315652626, "grad_norm": 0.0017290436662733555, "learning_rate": 4.9987544542853207e-05, "loss": 0.00027209220454096797, "step": 7525 }, { "epoch": 0.9815392615704628, "grad_norm": 0.0011989338090643287, "learning_rate": 4.9986526608222475e-05, "loss": 0.0002605011686682701, "step": 7550 }, { "epoch": 0.984789391575663, "grad_norm": 0.0009172749705612659, "learning_rate": 4.998546870651418e-05, "loss": 0.0002654053457081318, "step": 7575 }, { "epoch": 0.9880395215808633, "grad_norm": 0.0017111243214458227, "learning_rate": 4.998437083942049e-05, "loss": 0.00027476752176880837, "step": 7600 }, { "epoch": 0.9912896515860634, "grad_norm": 0.0009734177147038281, "learning_rate": 4.998323300869749e-05, "loss": 0.0002582584507763386, "step": 7625 }, { "epoch": 0.9945397815912637, "grad_norm": 0.0007609701715409756, "learning_rate": 4.99820552161652e-05, "loss": 0.00026447221636772156, "step": 7650 }, { "epoch": 0.9977899115964639, "grad_norm": 0.002729939529672265, "learning_rate": 4.998083746370754e-05, "loss": 0.00029974594712257386, "step": 7675 }, { "epoch": 1.001040041601664, "grad_norm": 0.0016189470188692212, "learning_rate": 4.9979579753272364e-05, "loss": 0.00026583246886730194, "step": 7700 }, { "epoch": 1.0042901716068642, "grad_norm": 0.0018497901037335396, "learning_rate": 4.997828208687144e-05, "loss": 0.00030912613496184347, "step": 7725 }, { "epoch": 1.0075403016120645, "grad_norm": 0.002935883356258273, "learning_rate": 4.997694446658044e-05, "loss": 0.0002521901950240135, "step": 7750 }, { "epoch": 1.0107904316172647, "grad_norm": 0.0007819763850420713, "learning_rate": 4.997556689453895e-05, "loss": 0.00022437306120991706, "step": 7775 }, { "epoch": 1.0140405616224648, "grad_norm": 0.001313910586759448, "learning_rate": 4.997414937295046e-05, "loss": 0.00027127765119075773, "step": 7800 }, { "epoch": 1.0172906916276652, "grad_norm": 0.0016395088750869036, "learning_rate": 4.997269190408235e-05, "loss": 0.00027738766744732856, "step": 7825 }, { "epoch": 1.0205408216328653, "grad_norm": 0.0016652283957228065, "learning_rate": 4.997119449026592e-05, "loss": 0.0002703977935016155, "step": 7850 }, { "epoch": 1.0237909516380654, "grad_norm": 0.0010423657950013876, "learning_rate": 4.996965713389635e-05, "loss": 0.00022714242339134217, "step": 7875 }, { "epoch": 1.0270410816432658, "grad_norm": 0.000837469648104161, "learning_rate": 4.99680798374327e-05, "loss": 0.00026420921087265013, "step": 7900 }, { "epoch": 1.030291211648466, "grad_norm": 0.001708422671072185, "learning_rate": 4.9966462603397946e-05, "loss": 0.0002601585164666176, "step": 7925 }, { "epoch": 1.033541341653666, "grad_norm": 0.0008940563420765102, "learning_rate": 4.9964805434378906e-05, "loss": 0.000257425457239151, "step": 7950 }, { "epoch": 1.0367914716588664, "grad_norm": 0.0009178609470836818, "learning_rate": 4.996310833302631e-05, "loss": 0.00029499370604753496, "step": 7975 }, { "epoch": 1.0400416016640666, "grad_norm": 0.0012339595705270767, "learning_rate": 4.996137130205474e-05, "loss": 0.00030053269118070604, "step": 8000 }, { "epoch": 1.0432917316692667, "grad_norm": 0.0012492527021095157, "learning_rate": 4.995959434424265e-05, "loss": 0.00028023691847920416, "step": 8025 }, { "epoch": 1.046541861674467, "grad_norm": 0.0011979590635746717, "learning_rate": 4.9957777462432394e-05, "loss": 0.00030107472091913225, "step": 8050 }, { "epoch": 1.0497919916796672, "grad_norm": 0.0021881945431232452, "learning_rate": 4.9955920659530124e-05, "loss": 0.00025908147916197776, "step": 8075 }, { "epoch": 1.0530421216848673, "grad_norm": 0.001974343555048108, "learning_rate": 4.99540239385059e-05, "loss": 0.0002683600224554539, "step": 8100 }, { "epoch": 1.0562922516900677, "grad_norm": 0.00107442622538656, "learning_rate": 4.99520873023936e-05, "loss": 0.0002770363166928291, "step": 8125 }, { "epoch": 1.0595423816952678, "grad_norm": 0.0019235480576753616, "learning_rate": 4.9950110754290966e-05, "loss": 0.00027815064415335653, "step": 8150 }, { "epoch": 1.062792511700468, "grad_norm": 0.001666422002017498, "learning_rate": 4.994809429735957e-05, "loss": 0.0002477550320327282, "step": 8175 }, { "epoch": 1.0660426417056683, "grad_norm": 0.0009593910654075444, "learning_rate": 4.994603793482484e-05, "loss": 0.0002452738955616951, "step": 8200 }, { "epoch": 1.0692927717108685, "grad_norm": 0.0018539578886702657, "learning_rate": 4.994394166997601e-05, "loss": 0.0002694200538098812, "step": 8225 }, { "epoch": 1.0725429017160686, "grad_norm": 0.001612568274140358, "learning_rate": 4.994180550616615e-05, "loss": 0.00026693956926465034, "step": 8250 }, { "epoch": 1.075793031721269, "grad_norm": 0.0010748225031420588, "learning_rate": 4.993962944681216e-05, "loss": 0.00025574009865522387, "step": 8275 }, { "epoch": 1.079043161726469, "grad_norm": 0.0026713060215115547, "learning_rate": 4.993741349539474e-05, "loss": 0.00027934052050113676, "step": 8300 }, { "epoch": 1.0822932917316692, "grad_norm": 0.0028977917972952127, "learning_rate": 4.99351576554584e-05, "loss": 0.0002870534546673298, "step": 8325 }, { "epoch": 1.0855434217368696, "grad_norm": 0.0017800545319914818, "learning_rate": 4.9932861930611454e-05, "loss": 0.0002597590535879135, "step": 8350 }, { "epoch": 1.0887935517420697, "grad_norm": 0.0010963486274704337, "learning_rate": 4.993052632452603e-05, "loss": 0.00021376239135861396, "step": 8375 }, { "epoch": 1.0920436817472698, "grad_norm": 0.004095334559679031, "learning_rate": 4.9928150840938034e-05, "loss": 0.00024395940825343133, "step": 8400 }, { "epoch": 1.09529381175247, "grad_norm": 0.0016407609218731523, "learning_rate": 4.9925735483647144e-05, "loss": 0.00022858794778585434, "step": 8425 }, { "epoch": 1.0985439417576703, "grad_norm": 0.0011426799464970827, "learning_rate": 4.9923280256516856e-05, "loss": 0.00025209063664078713, "step": 8450 }, { "epoch": 1.1017940717628705, "grad_norm": 0.0008142830338329077, "learning_rate": 4.99207851634744e-05, "loss": 0.00023667672649025918, "step": 8475 }, { "epoch": 1.1050442017680706, "grad_norm": 0.0013887656386941671, "learning_rate": 4.991825020851079e-05, "loss": 0.00023785781115293503, "step": 8500 }, { "epoch": 1.108294331773271, "grad_norm": 0.0016793243121355772, "learning_rate": 4.991567539568081e-05, "loss": 0.00025064632296562195, "step": 8525 }, { "epoch": 1.111544461778471, "grad_norm": 0.0015402145218104124, "learning_rate": 4.991306072910299e-05, "loss": 0.0002445879392325878, "step": 8550 }, { "epoch": 1.1147945917836712, "grad_norm": 0.0006315167411230505, "learning_rate": 4.991040621295959e-05, "loss": 0.0002341064065694809, "step": 8575 }, { "epoch": 1.1180447217888716, "grad_norm": 0.0017532727215439081, "learning_rate": 4.9907711851496655e-05, "loss": 0.0002281763032078743, "step": 8600 }, { "epoch": 1.1212948517940717, "grad_norm": 0.0017055863281711936, "learning_rate": 4.9904977649023906e-05, "loss": 0.00024771852418780326, "step": 8625 }, { "epoch": 1.1245449817992719, "grad_norm": 0.003801319282501936, "learning_rate": 4.9902203609914855e-05, "loss": 0.00024433283135294915, "step": 8650 }, { "epoch": 1.1277951118044722, "grad_norm": 0.0022220660466700792, "learning_rate": 4.989938973860668e-05, "loss": 0.0002709745801985264, "step": 8675 }, { "epoch": 1.1310452418096724, "grad_norm": 0.0017162845470011234, "learning_rate": 4.989653603960032e-05, "loss": 0.00023029427975416184, "step": 8700 }, { "epoch": 1.1342953718148725, "grad_norm": 0.0037925834767520428, "learning_rate": 4.989364251746036e-05, "loss": 0.00024551210924983024, "step": 8725 }, { "epoch": 1.1375455018200729, "grad_norm": 0.0031808854546397924, "learning_rate": 4.989070917681515e-05, "loss": 0.00026286788284778594, "step": 8750 }, { "epoch": 1.140795631825273, "grad_norm": 0.0016192150069400668, "learning_rate": 4.988773602235669e-05, "loss": 0.00026194704696536064, "step": 8775 }, { "epoch": 1.1440457618304731, "grad_norm": 0.0011428098659962416, "learning_rate": 4.9884723058840665e-05, "loss": 0.00022088117897510527, "step": 8800 }, { "epoch": 1.1472958918356735, "grad_norm": 0.0011217723367735744, "learning_rate": 4.988167029108646e-05, "loss": 0.00024152018129825593, "step": 8825 }, { "epoch": 1.1505460218408736, "grad_norm": 0.0013131353771314025, "learning_rate": 4.9878577723977116e-05, "loss": 0.00024948714300990107, "step": 8850 }, { "epoch": 1.1537961518460738, "grad_norm": 0.001230393536388874, "learning_rate": 4.987544536245931e-05, "loss": 0.00024934813380241396, "step": 8875 }, { "epoch": 1.1570462818512741, "grad_norm": 0.001053430256433785, "learning_rate": 4.987227321154344e-05, "loss": 0.00024760672822594644, "step": 8900 }, { "epoch": 1.1602964118564743, "grad_norm": 0.0014641049783676863, "learning_rate": 4.986906127630346e-05, "loss": 0.00021234707906842232, "step": 8925 }, { "epoch": 1.1635465418616744, "grad_norm": 0.0020078544039279222, "learning_rate": 4.986580956187703e-05, "loss": 0.00022885441780090332, "step": 8950 }, { "epoch": 1.1667966718668747, "grad_norm": 0.0016951245488598943, "learning_rate": 4.9862518073465405e-05, "loss": 0.00024043211713433265, "step": 8975 }, { "epoch": 1.1700468018720749, "grad_norm": 0.0011139962589368224, "learning_rate": 4.985918681633348e-05, "loss": 0.0002487810701131821, "step": 9000 }, { "epoch": 1.173296931877275, "grad_norm": 0.0008373457822017372, "learning_rate": 4.985581579580973e-05, "loss": 0.00023622142150998116, "step": 9025 }, { "epoch": 1.1765470618824754, "grad_norm": 0.0013526729308068752, "learning_rate": 4.985240501728628e-05, "loss": 0.0002516124211251736, "step": 9050 }, { "epoch": 1.1797971918876755, "grad_norm": 0.0012392222415655851, "learning_rate": 4.984895448621881e-05, "loss": 0.00022982005029916763, "step": 9075 }, { "epoch": 1.1830473218928756, "grad_norm": 0.0012214110465720296, "learning_rate": 4.98454642081266e-05, "loss": 0.00023133255541324616, "step": 9100 }, { "epoch": 1.186297451898076, "grad_norm": 0.0007031799177639186, "learning_rate": 4.984193418859251e-05, "loss": 0.00024310629814863204, "step": 9125 }, { "epoch": 1.1895475819032761, "grad_norm": 0.0014168958878144622, "learning_rate": 4.9838364433262965e-05, "loss": 0.000265915896743536, "step": 9150 }, { "epoch": 1.1927977119084763, "grad_norm": 0.0010334665421396494, "learning_rate": 4.983475494784795e-05, "loss": 0.000241184551268816, "step": 9175 }, { "epoch": 1.1960478419136766, "grad_norm": 0.0019802378956228495, "learning_rate": 4.9831105738120995e-05, "loss": 0.0002582270838320255, "step": 9200 }, { "epoch": 1.1992979719188768, "grad_norm": 0.0015125485369935632, "learning_rate": 4.982741680991919e-05, "loss": 0.00022809958085417747, "step": 9225 }, { "epoch": 1.202548101924077, "grad_norm": 0.0014787097461521626, "learning_rate": 4.982368816914314e-05, "loss": 0.00020900048315525055, "step": 9250 }, { "epoch": 1.2057982319292773, "grad_norm": 0.0005954820080660284, "learning_rate": 4.981991982175695e-05, "loss": 0.00021818505600094796, "step": 9275 }, { "epoch": 1.2090483619344774, "grad_norm": 0.0026676205452531576, "learning_rate": 4.981611177378829e-05, "loss": 0.00022581884637475015, "step": 9300 }, { "epoch": 1.2122984919396775, "grad_norm": 0.0024808698799461126, "learning_rate": 4.9812264031328285e-05, "loss": 0.00027215268462896344, "step": 9325 }, { "epoch": 1.215548621944878, "grad_norm": 0.0031435610726475716, "learning_rate": 4.980837660053159e-05, "loss": 0.00024729188531637193, "step": 9350 }, { "epoch": 1.218798751950078, "grad_norm": 0.002376891439780593, "learning_rate": 4.980444948761631e-05, "loss": 0.000256987065076828, "step": 9375 }, { "epoch": 1.2220488819552782, "grad_norm": 0.0008802884840406477, "learning_rate": 4.980048269886406e-05, "loss": 0.0002453344129025936, "step": 9400 }, { "epoch": 1.2252990119604785, "grad_norm": 0.0007192345801740885, "learning_rate": 4.979647624061987e-05, "loss": 0.0002300410531461239, "step": 9425 }, { "epoch": 1.2285491419656787, "grad_norm": 0.0010762346209958196, "learning_rate": 4.9792430119292275e-05, "loss": 0.00026356540620326997, "step": 9450 }, { "epoch": 1.2317992719708788, "grad_norm": 0.0016680917469784617, "learning_rate": 4.978834434135322e-05, "loss": 0.0002518729493021965, "step": 9475 }, { "epoch": 1.2350494019760792, "grad_norm": 0.0014808833366259933, "learning_rate": 4.9784218913338096e-05, "loss": 0.0002638903260231018, "step": 9500 }, { "epoch": 1.2382995319812793, "grad_norm": 0.0018340969691053033, "learning_rate": 4.9780053841845697e-05, "loss": 0.00024728938937187197, "step": 9525 }, { "epoch": 1.2415496619864794, "grad_norm": 0.000639909238088876, "learning_rate": 4.9775849133538254e-05, "loss": 0.0002366364374756813, "step": 9550 }, { "epoch": 1.2447997919916798, "grad_norm": 0.0005515090888366103, "learning_rate": 4.9771604795141385e-05, "loss": 0.0002480141818523407, "step": 9575 }, { "epoch": 1.24804992199688, "grad_norm": 0.001218414050526917, "learning_rate": 4.976732083344411e-05, "loss": 0.0002754170633852482, "step": 9600 }, { "epoch": 1.25130005200208, "grad_norm": 0.0019095524912700057, "learning_rate": 4.97629972552988e-05, "loss": 0.00025110188871622083, "step": 9625 }, { "epoch": 1.2545501820072804, "grad_norm": 0.0022047131787985563, "learning_rate": 4.975863406762124e-05, "loss": 0.00023579886183142663, "step": 9650 }, { "epoch": 1.2578003120124805, "grad_norm": 0.0010715682292357087, "learning_rate": 4.9754231277390514e-05, "loss": 0.00025938162580132487, "step": 9675 }, { "epoch": 1.2610504420176807, "grad_norm": 0.0014722577761858702, "learning_rate": 4.974978889164911e-05, "loss": 0.00023980937898159026, "step": 9700 }, { "epoch": 1.264300572022881, "grad_norm": 0.0010208309395238757, "learning_rate": 4.9745306917502805e-05, "loss": 0.00021998122334480286, "step": 9725 }, { "epoch": 1.2675507020280812, "grad_norm": 0.0005931083578616381, "learning_rate": 4.9740785362120736e-05, "loss": 0.0002296293154358864, "step": 9750 }, { "epoch": 1.2708008320332813, "grad_norm": 0.009204435162246227, "learning_rate": 4.973622423273533e-05, "loss": 0.00026070356369018555, "step": 9775 }, { "epoch": 1.2740509620384817, "grad_norm": 0.0020595588721334934, "learning_rate": 4.973162353664231e-05, "loss": 0.00023075552657246588, "step": 9800 }, { "epoch": 1.2773010920436818, "grad_norm": 0.0013328915229067206, "learning_rate": 4.972698328120071e-05, "loss": 0.00023088693618774413, "step": 9825 }, { "epoch": 1.280551222048882, "grad_norm": 0.004525795113295317, "learning_rate": 4.9722303473832824e-05, "loss": 0.00023551590740680694, "step": 9850 }, { "epoch": 1.2838013520540823, "grad_norm": 0.0028794463723897934, "learning_rate": 4.97175841220242e-05, "loss": 0.00022693824023008345, "step": 9875 }, { "epoch": 1.2870514820592824, "grad_norm": 0.0015256752958521247, "learning_rate": 4.971282523332368e-05, "loss": 0.00022677043452858924, "step": 9900 }, { "epoch": 1.2903016120644826, "grad_norm": 0.0033297943882644176, "learning_rate": 4.9708026815343314e-05, "loss": 0.0002465812861919403, "step": 9925 }, { "epoch": 1.2935517420696827, "grad_norm": 0.000917601864784956, "learning_rate": 4.970318887575837e-05, "loss": 0.0002653016895055771, "step": 9950 }, { "epoch": 1.296801872074883, "grad_norm": 0.002418952528387308, "learning_rate": 4.969831142230737e-05, "loss": 0.00022590529173612594, "step": 9975 }, { "epoch": 1.3000520020800832, "grad_norm": 0.001454479293897748, "learning_rate": 4.969339446279202e-05, "loss": 0.00027158020064234735, "step": 10000 }, { "epoch": 1.3033021320852833, "grad_norm": 0.0012225952232256532, "learning_rate": 4.968843800507721e-05, "loss": 0.0002480693906545639, "step": 10025 }, { "epoch": 1.3065522620904837, "grad_norm": 0.001239932724274695, "learning_rate": 4.9683442057091024e-05, "loss": 0.0002388366684317589, "step": 10050 }, { "epoch": 1.3098023920956838, "grad_norm": 0.0016925641102716327, "learning_rate": 4.96784066268247e-05, "loss": 0.00022450752556324005, "step": 10075 }, { "epoch": 1.313052522100884, "grad_norm": 0.000952462840359658, "learning_rate": 4.9673331722332644e-05, "loss": 0.00020575648173689842, "step": 10100 }, { "epoch": 1.3163026521060843, "grad_norm": 0.0010533633176237345, "learning_rate": 4.9668217351732396e-05, "loss": 0.0002651925757527351, "step": 10125 }, { "epoch": 1.3195527821112845, "grad_norm": 0.00173302018083632, "learning_rate": 4.966306352320461e-05, "loss": 0.00021947069093585013, "step": 10150 }, { "epoch": 1.3228029121164846, "grad_norm": 0.002059893449768424, "learning_rate": 4.9657870244993074e-05, "loss": 0.00022877845913171768, "step": 10175 }, { "epoch": 1.3260530421216847, "grad_norm": 0.0013976760674268007, "learning_rate": 4.965263752540468e-05, "loss": 0.00020990870893001557, "step": 10200 }, { "epoch": 1.329303172126885, "grad_norm": 0.0012817075476050377, "learning_rate": 4.964736537280939e-05, "loss": 0.00023846810683608054, "step": 10225 }, { "epoch": 1.3325533021320852, "grad_norm": 0.001444034744054079, "learning_rate": 4.9642053795640255e-05, "loss": 0.00024047080427408218, "step": 10250 }, { "epoch": 1.3358034321372854, "grad_norm": 0.0013552135787904263, "learning_rate": 4.963670280239337e-05, "loss": 0.00022178145125508307, "step": 10275 }, { "epoch": 1.3390535621424857, "grad_norm": 0.0014398591592907906, "learning_rate": 4.96313124016279e-05, "loss": 0.0002458404749631882, "step": 10300 }, { "epoch": 1.3423036921476859, "grad_norm": 0.0016251268098130822, "learning_rate": 4.962588260196605e-05, "loss": 0.00020361352711915969, "step": 10325 }, { "epoch": 1.345553822152886, "grad_norm": 0.00420821039006114, "learning_rate": 4.9620413412093e-05, "loss": 0.00022385528311133385, "step": 10350 }, { "epoch": 1.345553822152886, "eval_loss": 0.00095493218395859, "eval_runtime": 9.3187, "eval_samples_per_second": 536.555, "eval_steps_per_second": 4.292, "step": 10350 }, { "epoch": 1.345553822152886, "eval_holdout_avg_strict_f1": 0.06836038252415962, "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": 0.27740641711229946, "eval_holdout_nemotron_pii_strict_f1": 0.17409166773655155, "eval_holdout_open_pii_masking_500k_strict_f1": 0.16683151994724696, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.13363460296965785, "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": 1.3488039521580864, "grad_norm": 0.0007410464459098876, "learning_rate": 4.9614904840756985e-05, "loss": 0.00022841570898890495, "step": 10375 }, { "epoch": 1.3520540821632865, "grad_norm": 0.0010557317873463035, "learning_rate": 4.96093568967692e-05, "loss": 0.0002412230148911476, "step": 10400 }, { "epoch": 1.3553042121684866, "grad_norm": 0.0012896433472633362, "learning_rate": 4.960376958900385e-05, "loss": 0.00022234860807657242, "step": 10425 }, { "epoch": 1.358554342173687, "grad_norm": 0.0014095305232331157, "learning_rate": 4.9598142926398075e-05, "loss": 0.0002344328723847866, "step": 10450 }, { "epoch": 1.3618044721788871, "grad_norm": 0.0018959847511723638, "learning_rate": 4.959247691795198e-05, "loss": 0.0002503533661365509, "step": 10475 }, { "epoch": 1.3650546021840873, "grad_norm": 0.0008397601777687669, "learning_rate": 4.9586771572728597e-05, "loss": 0.0002315433695912361, "step": 10500 }, { "epoch": 1.3683047321892876, "grad_norm": 0.0008668754016980529, "learning_rate": 4.958102689985388e-05, "loss": 0.00021066755056381225, "step": 10525 }, { "epoch": 1.3715548621944877, "grad_norm": 0.0016179216327145696, "learning_rate": 4.9575242908516705e-05, "loss": 0.00023502033203840256, "step": 10550 }, { "epoch": 1.3748049921996879, "grad_norm": 0.0014446236891672015, "learning_rate": 4.956941960796881e-05, "loss": 0.00023628858849406243, "step": 10575 }, { "epoch": 1.3780551222048882, "grad_norm": 0.0007303371676243842, "learning_rate": 4.9563557007524854e-05, "loss": 0.00022226251661777496, "step": 10600 }, { "epoch": 1.3813052522100884, "grad_norm": 0.0008387739071622491, "learning_rate": 4.95576551165623e-05, "loss": 0.00022688502445816994, "step": 10625 }, { "epoch": 1.3845553822152885, "grad_norm": 0.0012891859514638782, "learning_rate": 4.955171394452151e-05, "loss": 0.0002495447546243668, "step": 10650 }, { "epoch": 1.3878055122204889, "grad_norm": 0.0006860825233161449, "learning_rate": 4.954573350090565e-05, "loss": 0.0002485157176852226, "step": 10675 }, { "epoch": 1.391055642225689, "grad_norm": 0.0013238989049568772, "learning_rate": 4.953971379528071e-05, "loss": 0.00021471558138728142, "step": 10700 }, { "epoch": 1.3943057722308891, "grad_norm": 0.0013835977297276258, "learning_rate": 4.953365483727548e-05, "loss": 0.00021957125514745712, "step": 10725 }, { "epoch": 1.3975559022360895, "grad_norm": 0.0016742295119911432, "learning_rate": 4.952755663658154e-05, "loss": 0.0002339155413210392, "step": 10750 }, { "epoch": 1.4008060322412896, "grad_norm": 0.0007948394049890339, "learning_rate": 4.9521419202953236e-05, "loss": 0.00022374913096427916, "step": 10775 }, { "epoch": 1.4040561622464898, "grad_norm": 0.001215911004692316, "learning_rate": 4.951524254620766e-05, "loss": 0.0002276202104985714, "step": 10800 }, { "epoch": 1.4073062922516901, "grad_norm": 0.001693572150543332, "learning_rate": 4.950902667622468e-05, "loss": 0.00024126509204506875, "step": 10825 }, { "epoch": 1.4105564222568903, "grad_norm": 0.0011415114859119058, "learning_rate": 4.950277160294683e-05, "loss": 0.00021039823070168496, "step": 10850 }, { "epoch": 1.4138065522620904, "grad_norm": 0.0012624706141650677, "learning_rate": 4.94964773363794e-05, "loss": 0.0002335314080119133, "step": 10875 }, { "epoch": 1.4170566822672908, "grad_norm": 0.0023544938303530216, "learning_rate": 4.9490143886590355e-05, "loss": 0.00023012714460492135, "step": 10900 }, { "epoch": 1.420306812272491, "grad_norm": 0.001988065429031849, "learning_rate": 4.948377126371032e-05, "loss": 0.00023836212232708931, "step": 10925 }, { "epoch": 1.423556942277691, "grad_norm": 0.00044153345515951514, "learning_rate": 4.9477359477932604e-05, "loss": 0.00022806664928793908, "step": 10950 }, { "epoch": 1.4268070722828914, "grad_norm": 0.0008878413937054574, "learning_rate": 4.947090853951315e-05, "loss": 0.00020782511681318282, "step": 10975 }, { "epoch": 1.4300572022880915, "grad_norm": 0.0016059972112998366, "learning_rate": 4.9464418458770516e-05, "loss": 0.00020815758034586906, "step": 11000 }, { "epoch": 1.4333073322932917, "grad_norm": 0.0006840807036496699, "learning_rate": 4.945788924608589e-05, "loss": 0.00022403839975595474, "step": 11025 }, { "epoch": 1.436557462298492, "grad_norm": 0.0018522337777540088, "learning_rate": 4.9451320911903027e-05, "loss": 0.0002529165893793106, "step": 11050 }, { "epoch": 1.4398075923036922, "grad_norm": 0.0011392493033781648, "learning_rate": 4.9444713466728286e-05, "loss": 0.00023853225633502006, "step": 11075 }, { "epoch": 1.4430577223088923, "grad_norm": 0.0024292694870382547, "learning_rate": 4.943806692113058e-05, "loss": 0.00024014655500650405, "step": 11100 }, { "epoch": 1.4463078523140926, "grad_norm": 0.0007658280665054917, "learning_rate": 4.943138128574134e-05, "loss": 0.00023862946778535843, "step": 11125 }, { "epoch": 1.4495579823192928, "grad_norm": 0.0004227055178489536, "learning_rate": 4.942465657125455e-05, "loss": 0.0002230224758386612, "step": 11150 }, { "epoch": 1.452808112324493, "grad_norm": 0.003415195969864726, "learning_rate": 4.94178927884267e-05, "loss": 0.00022361867129802704, "step": 11175 }, { "epoch": 1.4560582423296933, "grad_norm": 0.0030447698663920164, "learning_rate": 4.941108994807676e-05, "loss": 0.00023454848676919936, "step": 11200 }, { "epoch": 1.4593083723348934, "grad_norm": 0.0012138801394030452, "learning_rate": 4.940424806108619e-05, "loss": 0.0002123577147722244, "step": 11225 }, { "epoch": 1.4625585023400935, "grad_norm": 0.0014790329150855541, "learning_rate": 4.939736713839889e-05, "loss": 0.0002538035623729229, "step": 11250 }, { "epoch": 1.465808632345294, "grad_norm": 0.0024601540062576532, "learning_rate": 4.93904471910212e-05, "loss": 0.00022838005796074867, "step": 11275 }, { "epoch": 1.469058762350494, "grad_norm": 0.001427294802851975, "learning_rate": 4.938348823002189e-05, "loss": 0.00022333266213536262, "step": 11300 }, { "epoch": 1.4723088923556942, "grad_norm": 0.0018155802972614765, "learning_rate": 4.937649026653215e-05, "loss": 0.0002779684402048588, "step": 11325 }, { "epoch": 1.4755590223608945, "grad_norm": 0.0015379923861473799, "learning_rate": 4.9369453311745516e-05, "loss": 0.00022361904382705688, "step": 11350 }, { "epoch": 1.4788091523660947, "grad_norm": 0.0015094184782356024, "learning_rate": 4.9362377376917936e-05, "loss": 0.0002118166908621788, "step": 11375 }, { "epoch": 1.4820592823712948, "grad_norm": 0.0019516360480338335, "learning_rate": 4.935526247336767e-05, "loss": 0.00021778607740998267, "step": 11400 }, { "epoch": 1.4853094123764952, "grad_norm": 0.000928438501432538, "learning_rate": 4.934810861247533e-05, "loss": 0.00020529730245471, "step": 11425 }, { "epoch": 1.4885595423816953, "grad_norm": 0.001177873113192618, "learning_rate": 4.934091580568384e-05, "loss": 0.00020764494314789772, "step": 11450 }, { "epoch": 1.4918096723868954, "grad_norm": 0.0008443294209428132, "learning_rate": 4.933368406449843e-05, "loss": 0.0002065547928214073, "step": 11475 }, { "epoch": 1.4950598023920958, "grad_norm": 0.0018499024445191026, "learning_rate": 4.932641340048658e-05, "loss": 0.0002670598588883877, "step": 11500 }, { "epoch": 1.498309932397296, "grad_norm": 0.001366683398373425, "learning_rate": 4.931910382527806e-05, "loss": 0.0002089797891676426, "step": 11525 }, { "epoch": 1.501560062402496, "grad_norm": 0.0014287630328908563, "learning_rate": 4.931175535056486e-05, "loss": 0.00023185288533568384, "step": 11550 }, { "epoch": 1.5048101924076964, "grad_norm": 0.0011994066881015897, "learning_rate": 4.9304367988101194e-05, "loss": 0.00022137219086289405, "step": 11575 }, { "epoch": 1.5080603224128966, "grad_norm": 0.001302711432799697, "learning_rate": 4.9296941749703486e-05, "loss": 0.00021828755736351014, "step": 11600 }, { "epoch": 1.5113104524180967, "grad_norm": 0.0009471996454522014, "learning_rate": 4.9289476647250344e-05, "loss": 0.0002089974656701088, "step": 11625 }, { "epoch": 1.514560582423297, "grad_norm": 0.0025708491448312998, "learning_rate": 4.928197269268252e-05, "loss": 0.00020671421661973, "step": 11650 }, { "epoch": 1.5178107124284972, "grad_norm": 0.0008076655794866383, "learning_rate": 4.927442989800294e-05, "loss": 0.0002104758471250534, "step": 11675 }, { "epoch": 1.5210608424336973, "grad_norm": 0.0009024995379149914, "learning_rate": 4.926684827527665e-05, "loss": 0.00019747575744986535, "step": 11700 }, { "epoch": 1.5243109724388977, "grad_norm": 0.001300012576393783, "learning_rate": 4.925922783663079e-05, "loss": 0.0002422116696834564, "step": 11725 }, { "epoch": 1.5275611024440978, "grad_norm": 0.0009546473156660795, "learning_rate": 4.925156859425459e-05, "loss": 0.00019759729504585267, "step": 11750 }, { "epoch": 1.530811232449298, "grad_norm": 0.001021179836243391, "learning_rate": 4.924387056039937e-05, "loss": 0.0002173416130244732, "step": 11775 }, { "epoch": 1.5340613624544983, "grad_norm": 0.0015582593623548746, "learning_rate": 4.9236133747378475e-05, "loss": 0.000237205158919096, "step": 11800 }, { "epoch": 1.5373114924596982, "grad_norm": 0.002049966948106885, "learning_rate": 4.922835816756728e-05, "loss": 0.00021319374442100526, "step": 11825 }, { "epoch": 1.5405616224648986, "grad_norm": 0.0014623207971453667, "learning_rate": 4.922054383340319e-05, "loss": 0.00022468648850917816, "step": 11850 }, { "epoch": 1.543811752470099, "grad_norm": 0.0010616122744977474, "learning_rate": 4.9212690757385565e-05, "loss": 0.0002278902754187584, "step": 11875 }, { "epoch": 1.5470618824752989, "grad_norm": 0.0014538065297529101, "learning_rate": 4.920479895207577e-05, "loss": 0.00022692535072565078, "step": 11900 }, { "epoch": 1.5503120124804992, "grad_norm": 0.0010035118320956826, "learning_rate": 4.919686843009711e-05, "loss": 0.0002275378815829754, "step": 11925 }, { "epoch": 1.5535621424856996, "grad_norm": 0.0028484691865742207, "learning_rate": 4.9188899204134794e-05, "loss": 0.00024725059047341346, "step": 11950 }, { "epoch": 1.5568122724908995, "grad_norm": 0.0010700999991968274, "learning_rate": 4.918089128693597e-05, "loss": 0.00023311510682106018, "step": 11975 }, { "epoch": 1.5600624024960998, "grad_norm": 0.0013243206776678562, "learning_rate": 4.917284469130966e-05, "loss": 0.00020961858332157134, "step": 12000 }, { "epoch": 1.5633125325013002, "grad_norm": 0.0012829856714233756, "learning_rate": 4.916475943012676e-05, "loss": 0.0002158079296350479, "step": 12025 }, { "epoch": 1.5665626625065001, "grad_norm": 0.00196343963034451, "learning_rate": 4.915663551632002e-05, "loss": 0.0002173725888133049, "step": 12050 }, { "epoch": 1.5698127925117005, "grad_norm": 0.0017143343575298786, "learning_rate": 4.914847296288398e-05, "loss": 0.0002406243234872818, "step": 12075 }, { "epoch": 1.5730629225169008, "grad_norm": 0.0016624074196442962, "learning_rate": 4.9140271782875035e-05, "loss": 0.0002361990697681904, "step": 12100 }, { "epoch": 1.5763130525221007, "grad_norm": 0.0007804373744875193, "learning_rate": 4.913203198941134e-05, "loss": 0.0002275773510336876, "step": 12125 }, { "epoch": 1.579563182527301, "grad_norm": 0.0023541946429759264, "learning_rate": 4.912375359567281e-05, "loss": 0.0001959991455078125, "step": 12150 }, { "epoch": 1.5828133125325015, "grad_norm": 0.0010233235079795122, "learning_rate": 4.9115436614901114e-05, "loss": 0.00018739113584160806, "step": 12175 }, { "epoch": 1.5860634425377014, "grad_norm": 0.0016051802085712552, "learning_rate": 4.9107081060399627e-05, "loss": 0.0002133057452738285, "step": 12200 }, { "epoch": 1.5893135725429017, "grad_norm": 0.0013718517730012536, "learning_rate": 4.909868694553346e-05, "loss": 0.00021465757861733437, "step": 12225 }, { "epoch": 1.592563702548102, "grad_norm": 0.0007805069908499718, "learning_rate": 4.909025428372936e-05, "loss": 0.00022665571421384812, "step": 12250 }, { "epoch": 1.595813832553302, "grad_norm": 0.0018547538202255964, "learning_rate": 4.908178308847575e-05, "loss": 0.00022225631400942802, "step": 12275 }, { "epoch": 1.5990639625585024, "grad_norm": 0.001349901081994176, "learning_rate": 4.907327337332271e-05, "loss": 0.00018927998840808868, "step": 12300 }, { "epoch": 1.6023140925637025, "grad_norm": 0.000917712808586657, "learning_rate": 4.906472515188188e-05, "loss": 0.00020415421575307847, "step": 12325 }, { "epoch": 1.6055642225689026, "grad_norm": 0.001299075549468398, "learning_rate": 4.905613843782655e-05, "loss": 0.0002180762030184269, "step": 12350 }, { "epoch": 1.608814352574103, "grad_norm": 0.0011308664688840508, "learning_rate": 4.904751324489155e-05, "loss": 0.00020294418558478356, "step": 12375 }, { "epoch": 1.6120644825793031, "grad_norm": 0.0010383251355960965, "learning_rate": 4.903884958687327e-05, "loss": 0.00020127050578594208, "step": 12400 }, { "epoch": 1.6153146125845033, "grad_norm": 0.0007700969581492245, "learning_rate": 4.903014747762961e-05, "loss": 0.00022019905969500542, "step": 12425 }, { "epoch": 1.6185647425897036, "grad_norm": 0.0015845868038013577, "learning_rate": 4.902140693108e-05, "loss": 0.00023882202804088594, "step": 12450 }, { "epoch": 1.6218148725949038, "grad_norm": 0.002057379810139537, "learning_rate": 4.901262796120534e-05, "loss": 0.00021504990756511687, "step": 12475 }, { "epoch": 1.625065002600104, "grad_norm": 0.0011629246873781085, "learning_rate": 4.900381058204798e-05, "loss": 0.0002195056900382042, "step": 12500 }, { "epoch": 1.6283151326053042, "grad_norm": 0.0008853785693645477, "learning_rate": 4.8994954807711715e-05, "loss": 0.0002198290452361107, "step": 12525 }, { "epoch": 1.6315652626105044, "grad_norm": 0.0023640524595975876, "learning_rate": 4.898606065236176e-05, "loss": 0.00022358374670147896, "step": 12550 }, { "epoch": 1.6348153926157045, "grad_norm": 0.0012634290615096688, "learning_rate": 4.897712813022473e-05, "loss": 0.0002201900817453861, "step": 12575 }, { "epoch": 1.6380655226209049, "grad_norm": 0.001097681699320674, "learning_rate": 4.896815725558857e-05, "loss": 0.00021714471280574797, "step": 12600 }, { "epoch": 1.641315652626105, "grad_norm": 0.0007831507246010005, "learning_rate": 4.895914804280262e-05, "loss": 0.0002441369742155075, "step": 12625 }, { "epoch": 1.6445657826313052, "grad_norm": 0.0014596626861020923, "learning_rate": 4.895010050627752e-05, "loss": 0.00022420192137360574, "step": 12650 }, { "epoch": 1.6478159126365055, "grad_norm": 0.0009162931237369776, "learning_rate": 4.8941014660485206e-05, "loss": 0.0002115178294479847, "step": 12675 }, { "epoch": 1.6510660426417056, "grad_norm": 0.001233368762768805, "learning_rate": 4.893189051995891e-05, "loss": 0.00020989146083593368, "step": 12700 }, { "epoch": 1.6543161726469058, "grad_norm": 0.0005623113829642534, "learning_rate": 4.892272809929309e-05, "loss": 0.00022066382691264154, "step": 12725 }, { "epoch": 1.6575663026521061, "grad_norm": 0.0008610347867943347, "learning_rate": 4.891352741314347e-05, "loss": 0.00021332105621695518, "step": 12750 }, { "epoch": 1.6608164326573063, "grad_norm": 0.0006132300477474928, "learning_rate": 4.8904288476226954e-05, "loss": 0.0002009551413357258, "step": 12775 }, { "epoch": 1.6640665626625064, "grad_norm": 0.0022478275932371616, "learning_rate": 4.889501130332163e-05, "loss": 0.00020834658294916153, "step": 12800 }, { "epoch": 1.6673166926677068, "grad_norm": 0.0013704983284696937, "learning_rate": 4.8885695909266774e-05, "loss": 0.0002107241377234459, "step": 12825 }, { "epoch": 1.670566822672907, "grad_norm": 0.0012594923609867692, "learning_rate": 4.887634230896276e-05, "loss": 0.00020520130172371864, "step": 12850 }, { "epoch": 1.673816952678107, "grad_norm": 0.0009163892827928066, "learning_rate": 4.886695051737112e-05, "loss": 0.00018248358741402627, "step": 12875 }, { "epoch": 1.6770670826833074, "grad_norm": 0.0013087759725749493, "learning_rate": 4.885752054951442e-05, "loss": 0.0001804506406188011, "step": 12900 }, { "epoch": 1.6803172126885075, "grad_norm": 0.0009314049384556711, "learning_rate": 4.884805242047633e-05, "loss": 0.00020271694287657738, "step": 12925 }, { "epoch": 1.6835673426937077, "grad_norm": 0.001452924800105393, "learning_rate": 4.8838546145401556e-05, "loss": 0.0001986694522202015, "step": 12950 }, { "epoch": 1.686817472698908, "grad_norm": 0.0009039230062626302, "learning_rate": 4.882900173949581e-05, "loss": 0.0001967090740799904, "step": 12975 }, { "epoch": 1.6900676027041082, "grad_norm": 0.0022098368499428034, "learning_rate": 4.88194192180258e-05, "loss": 0.0002104349248111248, "step": 13000 }, { "epoch": 1.6933177327093083, "grad_norm": 0.0017814264865592122, "learning_rate": 4.88097985963192e-05, "loss": 0.00020009895786643028, "step": 13025 }, { "epoch": 1.6965678627145087, "grad_norm": 0.0009897558484226465, "learning_rate": 4.8800139889764635e-05, "loss": 0.00019421691074967385, "step": 13050 }, { "epoch": 1.6998179927197088, "grad_norm": 0.0008877114742062986, "learning_rate": 4.879044311381163e-05, "loss": 0.00021792301908135414, "step": 13075 }, { "epoch": 1.703068122724909, "grad_norm": 0.000991069246083498, "learning_rate": 4.8780708283970635e-05, "loss": 0.00021280685439705848, "step": 13100 }, { "epoch": 1.7063182527301093, "grad_norm": 0.0018834732472896576, "learning_rate": 4.877093541581293e-05, "loss": 0.00020899130031466485, "step": 13125 }, { "epoch": 1.7095683827353094, "grad_norm": 0.0024460970889776945, "learning_rate": 4.876112452497067e-05, "loss": 0.00021215084940195083, "step": 13150 }, { "epoch": 1.7128185127405096, "grad_norm": 0.0025619217194616795, "learning_rate": 4.875127562713682e-05, "loss": 0.00022624718025326729, "step": 13175 }, { "epoch": 1.71606864274571, "grad_norm": 0.00162825349252671, "learning_rate": 4.874138873806513e-05, "loss": 0.00021882947534322737, "step": 13200 }, { "epoch": 1.71931877275091, "grad_norm": 0.0006245311815291643, "learning_rate": 4.873146387357012e-05, "loss": 0.00019531719386577605, "step": 13225 }, { "epoch": 1.7225689027561102, "grad_norm": 0.0006454737158492208, "learning_rate": 4.8721501049527074e-05, "loss": 0.00019291777163743973, "step": 13250 }, { "epoch": 1.7258190327613105, "grad_norm": 0.0010474052978679538, "learning_rate": 4.871150028187197e-05, "loss": 0.00019108649343252182, "step": 13275 }, { "epoch": 1.7290691627665107, "grad_norm": 0.0005790158757008612, "learning_rate": 4.8701461586601495e-05, "loss": 0.00019627740606665612, "step": 13300 }, { "epoch": 1.7323192927717108, "grad_norm": 0.0019599865190684795, "learning_rate": 4.869138497977298e-05, "loss": 0.0002209186926484108, "step": 13325 }, { "epoch": 1.7355694227769112, "grad_norm": 0.0012518159346655011, "learning_rate": 4.8681270477504425e-05, "loss": 0.00022938210517168045, "step": 13350 }, { "epoch": 1.7388195527821113, "grad_norm": 0.0008453086484223604, "learning_rate": 4.8671118095974435e-05, "loss": 0.00020086592063307763, "step": 13375 }, { "epoch": 1.7420696827873114, "grad_norm": 0.0015744048869237304, "learning_rate": 4.86609278514222e-05, "loss": 0.00023271137848496437, "step": 13400 }, { "epoch": 1.7453198127925118, "grad_norm": 0.0009528041118755937, "learning_rate": 4.865069976014747e-05, "loss": 0.0002470199763774872, "step": 13425 }, { "epoch": 1.748569942797712, "grad_norm": 0.00111283827573061, "learning_rate": 4.864043383851054e-05, "loss": 0.00022434709593653678, "step": 13450 }, { "epoch": 1.751820072802912, "grad_norm": 0.0014392537996172905, "learning_rate": 4.8630130102932226e-05, "loss": 0.00019503209739923477, "step": 13475 }, { "epoch": 1.7550702028081124, "grad_norm": 0.0024195711594074965, "learning_rate": 4.86197885698938e-05, "loss": 0.00020250892266631125, "step": 13500 }, { "epoch": 1.7583203328133126, "grad_norm": 0.0018107002833858132, "learning_rate": 4.860940925593703e-05, "loss": 0.00018528325483202935, "step": 13525 }, { "epoch": 1.7615704628185127, "grad_norm": 0.00047586948494426906, "learning_rate": 4.859899217766408e-05, "loss": 0.0002012966200709343, "step": 13550 }, { "epoch": 1.764820592823713, "grad_norm": 0.0008106463355943561, "learning_rate": 4.858853735173756e-05, "loss": 0.00022149544209241868, "step": 13575 }, { "epoch": 1.7680707228289132, "grad_norm": 0.0015900592552497983, "learning_rate": 4.857804479488042e-05, "loss": 0.0002231018617749214, "step": 13600 }, { "epoch": 1.7713208528341133, "grad_norm": 0.0013972468441352248, "learning_rate": 4.856751452387597e-05, "loss": 0.0001727997325360775, "step": 13625 }, { "epoch": 1.7745709828393137, "grad_norm": 0.003206509631127119, "learning_rate": 4.8556946555567875e-05, "loss": 0.00020560242235660554, "step": 13650 }, { "epoch": 1.7778211128445138, "grad_norm": 0.0008185068727470934, "learning_rate": 4.854634090686005e-05, "loss": 0.00019721709191799163, "step": 13675 }, { "epoch": 1.781071242849714, "grad_norm": 0.001312661450356245, "learning_rate": 4.853569759471674e-05, "loss": 0.00018779512494802476, "step": 13700 }, { "epoch": 1.7843213728549143, "grad_norm": 0.0006430719513446093, "learning_rate": 4.85250166361624e-05, "loss": 0.00020717784762382506, "step": 13725 }, { "epoch": 1.7875715028601145, "grad_norm": 0.002790760016068816, "learning_rate": 4.851429804828168e-05, "loss": 0.00019336583092808724, "step": 13750 }, { "epoch": 1.7908216328653146, "grad_norm": 0.0013842202024534345, "learning_rate": 4.8503541848219464e-05, "loss": 0.00017480608075857163, "step": 13775 }, { "epoch": 1.794071762870515, "grad_norm": 0.0015860736602917314, "learning_rate": 4.8492748053180776e-05, "loss": 0.0001934964582324028, "step": 13800 }, { "epoch": 1.794071762870515, "eval_loss": 0.0007873945869505405, "eval_runtime": 9.5205, "eval_samples_per_second": 525.18, "eval_steps_per_second": 4.201, "step": 13800 }, { "epoch": 1.794071762870515, "eval_holdout_avg_strict_f1": 0.07671023568489087, "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": 0.3106818443141313, "eval_holdout_nemotron_pii_strict_f1": 0.2033773260103287, "eval_holdout_open_pii_masking_500k_strict_f1": 0.17042764715164904, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.15932577505769038, "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": 1.7973218928757149, "grad_norm": 0.0019391707610338926, "learning_rate": 4.848191668043078e-05, "loss": 0.0001878507435321808, "step": 13825 }, { "epoch": 1.8005720228809152, "grad_norm": 0.0014676563441753387, "learning_rate": 4.847104774729474e-05, "loss": 0.00021142667159438134, "step": 13850 }, { "epoch": 1.8038221528861156, "grad_norm": 0.0032201732974499464, "learning_rate": 4.8460141271158014e-05, "loss": 0.0001980452425777912, "step": 13875 }, { "epoch": 1.8070722828913155, "grad_norm": 0.0010093223536387086, "learning_rate": 4.8449197269466e-05, "loss": 0.00018527789041399955, "step": 13900 }, { "epoch": 1.8103224128965159, "grad_norm": 0.002089881105348468, "learning_rate": 4.843821575972411e-05, "loss": 0.00018696235492825507, "step": 13925 }, { "epoch": 1.8135725429017162, "grad_norm": 0.0012031790101900697, "learning_rate": 4.8427196759497796e-05, "loss": 0.00019349925220012664, "step": 13950 }, { "epoch": 1.8168226729069161, "grad_norm": 0.0032598827965557575, "learning_rate": 4.8416140286412416e-05, "loss": 0.0001790124922990799, "step": 13975 }, { "epoch": 1.8200728029121165, "grad_norm": 0.0011320498306304216, "learning_rate": 4.840504635815331e-05, "loss": 0.00020609425380825995, "step": 14000 }, { "epoch": 1.8233229329173168, "grad_norm": 0.0021722533274441957, "learning_rate": 4.8393914992465715e-05, "loss": 0.00017540406435728072, "step": 14025 }, { "epoch": 1.8265730629225168, "grad_norm": 0.0009918785654008389, "learning_rate": 4.838274620715475e-05, "loss": 0.00018825355917215347, "step": 14050 }, { "epoch": 1.8298231929277171, "grad_norm": 0.0021330395247787237, "learning_rate": 4.8371540020085406e-05, "loss": 0.0001849439740180969, "step": 14075 }, { "epoch": 1.8330733229329175, "grad_norm": 0.001202671555802226, "learning_rate": 4.836029644918246e-05, "loss": 0.00018819918856024742, "step": 14100 }, { "epoch": 1.8363234529381174, "grad_norm": 0.0035825998056679964, "learning_rate": 4.834901551243054e-05, "loss": 0.00020158516243100168, "step": 14125 }, { "epoch": 1.8395735829433177, "grad_norm": 0.005913496483117342, "learning_rate": 4.833769722787399e-05, "loss": 0.00019377293065190316, "step": 14150 }, { "epoch": 1.842823712948518, "grad_norm": 0.0009982505580410361, "learning_rate": 4.832634161361693e-05, "loss": 0.0001952342875301838, "step": 14175 }, { "epoch": 1.846073842953718, "grad_norm": 0.0014910399913787842, "learning_rate": 4.831494868782318e-05, "loss": 0.0002068406343460083, "step": 14200 }, { "epoch": 1.8493239729589184, "grad_norm": 0.0053688944317400455, "learning_rate": 4.830351846871623e-05, "loss": 0.00020632198080420495, "step": 14225 }, { "epoch": 1.8525741029641187, "grad_norm": 0.003236903343349695, "learning_rate": 4.829205097457923e-05, "loss": 0.00021189013496041297, "step": 14250 }, { "epoch": 1.8558242329693186, "grad_norm": 0.0021175884176045656, "learning_rate": 4.8280546223754967e-05, "loss": 0.00021266382187604905, "step": 14275 }, { "epoch": 1.859074362974519, "grad_norm": 0.0016959202475845814, "learning_rate": 4.8269004234645805e-05, "loss": 0.00016569169238209725, "step": 14300 }, { "epoch": 1.8623244929797191, "grad_norm": 0.0011466607684269547, "learning_rate": 4.825742502571366e-05, "loss": 0.00017714653164148332, "step": 14325 }, { "epoch": 1.8655746229849193, "grad_norm": 0.002087001921609044, "learning_rate": 4.824580861548004e-05, "loss": 0.0001798272505402565, "step": 14350 }, { "epoch": 1.8688247529901196, "grad_norm": 0.0013011404080316424, "learning_rate": 4.823415502252587e-05, "loss": 0.00019987838342785835, "step": 14375 }, { "epoch": 1.8720748829953198, "grad_norm": 0.003103255992755294, "learning_rate": 4.8222464265491624e-05, "loss": 0.00018162962049245835, "step": 14400 }, { "epoch": 1.87532501300052, "grad_norm": 0.0026980354450643063, "learning_rate": 4.821073636307719e-05, "loss": 0.0001928180642426014, "step": 14425 }, { "epoch": 1.8785751430057203, "grad_norm": 0.0022120249923318624, "learning_rate": 4.819897133404189e-05, "loss": 0.00022065060213208198, "step": 14450 }, { "epoch": 1.8818252730109204, "grad_norm": 0.0012642544461414218, "learning_rate": 4.8187169197204395e-05, "loss": 0.0001877201721072197, "step": 14475 }, { "epoch": 1.8850754030161205, "grad_norm": 0.0012029558420181274, "learning_rate": 4.8175329971442774e-05, "loss": 0.0001797371543943882, "step": 14500 }, { "epoch": 1.888325533021321, "grad_norm": 0.006576585583388805, "learning_rate": 4.8163453675694396e-05, "loss": 0.00020043499767780304, "step": 14525 }, { "epoch": 1.891575663026521, "grad_norm": 0.001970443408936262, "learning_rate": 4.8151540328955935e-05, "loss": 0.0001659386046230793, "step": 14550 }, { "epoch": 1.8948257930317212, "grad_norm": 0.0025421991012990475, "learning_rate": 4.813958995028333e-05, "loss": 0.00019923953339457513, "step": 14575 }, { "epoch": 1.8980759230369215, "grad_norm": 0.001944137504324317, "learning_rate": 4.812760255879175e-05, "loss": 0.00019897514954209328, "step": 14600 }, { "epoch": 1.9013260530421217, "grad_norm": 0.0016694455407559872, "learning_rate": 4.811557817365556e-05, "loss": 0.0002129945158958435, "step": 14625 }, { "epoch": 1.9045761830473218, "grad_norm": 0.0018652010476216674, "learning_rate": 4.810351681410832e-05, "loss": 0.00018253499642014503, "step": 14650 }, { "epoch": 1.9078263130525221, "grad_norm": 0.002443675883114338, "learning_rate": 4.8091418499442705e-05, "loss": 0.00018208036199212073, "step": 14675 }, { "epoch": 1.9110764430577223, "grad_norm": 0.001355400076135993, "learning_rate": 4.8079283249010535e-05, "loss": 0.00018838070333003997, "step": 14700 }, { "epoch": 1.9143265730629224, "grad_norm": 0.0015903201419860125, "learning_rate": 4.806711108222267e-05, "loss": 0.0001955299824476242, "step": 14725 }, { "epoch": 1.9175767030681228, "grad_norm": 0.0031122886575758457, "learning_rate": 4.805490201854905e-05, "loss": 0.00020101873204112053, "step": 14750 }, { "epoch": 1.920826833073323, "grad_norm": 0.001963747898116708, "learning_rate": 4.8042656077518625e-05, "loss": 0.00018206274136900902, "step": 14775 }, { "epoch": 1.924076963078523, "grad_norm": 0.0031640648376196623, "learning_rate": 4.8030373278719335e-05, "loss": 0.0001737309992313385, "step": 14800 }, { "epoch": 1.9273270930837234, "grad_norm": 0.0023399752099066973, "learning_rate": 4.801805364179806e-05, "loss": 0.00018427133560180664, "step": 14825 }, { "epoch": 1.9305772230889235, "grad_norm": 0.001325368182733655, "learning_rate": 4.800569718646062e-05, "loss": 0.00016195224598050117, "step": 14850 }, { "epoch": 1.9338273530941237, "grad_norm": 0.0016849812818691134, "learning_rate": 4.7993303932471726e-05, "loss": 0.0001758340932428837, "step": 14875 }, { "epoch": 1.937077483099324, "grad_norm": 0.0011520645348355174, "learning_rate": 4.798087389965495e-05, "loss": 0.00018262149766087532, "step": 14900 }, { "epoch": 1.9403276131045242, "grad_norm": 0.0009939279407262802, "learning_rate": 4.7968407107892684e-05, "loss": 0.00017483439296483994, "step": 14925 }, { "epoch": 1.9435777431097243, "grad_norm": 0.0011320949997752905, "learning_rate": 4.795590357712613e-05, "loss": 0.00017233431339263916, "step": 14950 }, { "epoch": 1.9468278731149247, "grad_norm": 0.0012969585368409753, "learning_rate": 4.794336332735524e-05, "loss": 0.0001781269535422325, "step": 14975 }, { "epoch": 1.9500780031201248, "grad_norm": 0.00279130763374269, "learning_rate": 4.793078637863872e-05, "loss": 0.00018540842458605766, "step": 15000 }, { "epoch": 1.953328133125325, "grad_norm": 0.001861119526438415, "learning_rate": 4.791817275109396e-05, "loss": 0.00019540552049875258, "step": 15025 }, { "epoch": 1.9565782631305253, "grad_norm": 0.0033701809588819742, "learning_rate": 4.790552246489703e-05, "loss": 0.00016461025923490525, "step": 15050 }, { "epoch": 1.9598283931357254, "grad_norm": 0.0006286469288170338, "learning_rate": 4.789283554028264e-05, "loss": 0.00017568401992321014, "step": 15075 }, { "epoch": 1.9630785231409256, "grad_norm": 0.0012872155057266355, "learning_rate": 4.7880111997544094e-05, "loss": 0.00015418815426528453, "step": 15100 }, { "epoch": 1.966328653146126, "grad_norm": 0.001639127847738564, "learning_rate": 4.786735185703327e-05, "loss": 0.0001733824983239174, "step": 15125 }, { "epoch": 1.969578783151326, "grad_norm": 0.00825419183820486, "learning_rate": 4.785455513916059e-05, "loss": 0.00018014784902334213, "step": 15150 }, { "epoch": 1.9728289131565262, "grad_norm": 0.0016525533283129334, "learning_rate": 4.784172186439499e-05, "loss": 0.00016880841925740242, "step": 15175 }, { "epoch": 1.9760790431617266, "grad_norm": 0.0008869419689290226, "learning_rate": 4.7828852053263865e-05, "loss": 0.00016358742490410805, "step": 15200 }, { "epoch": 1.9793291731669267, "grad_norm": 0.0021625568624585867, "learning_rate": 4.781594572635306e-05, "loss": 0.00015240022912621498, "step": 15225 }, { "epoch": 1.9825793031721268, "grad_norm": 0.0030781549867242575, "learning_rate": 4.780300290430682e-05, "loss": 0.00015993243083357812, "step": 15250 }, { "epoch": 1.9858294331773272, "grad_norm": 0.0019852917175740004, "learning_rate": 4.779002360782779e-05, "loss": 0.0001564650423824787, "step": 15275 }, { "epoch": 1.9890795631825273, "grad_norm": 0.000985127524472773, "learning_rate": 4.777700785767694e-05, "loss": 0.00017142394557595253, "step": 15300 }, { "epoch": 1.9923296931877275, "grad_norm": 0.0015094815753400326, "learning_rate": 4.776395567467353e-05, "loss": 0.000170376468449831, "step": 15325 }, { "epoch": 1.9955798231929278, "grad_norm": 0.002530918922275305, "learning_rate": 4.775086707969513e-05, "loss": 0.00015980442985892297, "step": 15350 }, { "epoch": 1.998829953198128, "grad_norm": 0.001743559492751956, "learning_rate": 4.773774209367753e-05, "loss": 0.0001495914813131094, "step": 15375 }, { "epoch": 2.002080083203328, "grad_norm": 0.005321058444678783, "learning_rate": 4.7724580737614755e-05, "loss": 0.00016431858763098716, "step": 15400 }, { "epoch": 2.0053302132085284, "grad_norm": 0.0011911957990378141, "learning_rate": 4.7711383032558976e-05, "loss": 0.00016631942242383956, "step": 15425 }, { "epoch": 2.0085803432137284, "grad_norm": 0.0012982947519049048, "learning_rate": 4.769814899962052e-05, "loss": 0.00015491821803152562, "step": 15450 }, { "epoch": 2.0118304732189287, "grad_norm": 0.0007231764029711485, "learning_rate": 4.7684878659967816e-05, "loss": 0.00017552003264427186, "step": 15475 }, { "epoch": 2.015080603224129, "grad_norm": 0.002448186744004488, "learning_rate": 4.7671572034827375e-05, "loss": 0.00017927879467606546, "step": 15500 }, { "epoch": 2.018330733229329, "grad_norm": 0.002163167344406247, "learning_rate": 4.765822914548375e-05, "loss": 0.0001637950725853443, "step": 15525 }, { "epoch": 2.0215808632345293, "grad_norm": 0.0025511952117085457, "learning_rate": 4.764485001327949e-05, "loss": 0.0001653164066374302, "step": 15550 }, { "epoch": 2.0248309932397297, "grad_norm": 0.0014500441029667854, "learning_rate": 4.763143465961512e-05, "loss": 0.00016453903168439865, "step": 15575 }, { "epoch": 2.0280811232449296, "grad_norm": 0.0033016984816640615, "learning_rate": 4.761798310594911e-05, "loss": 0.0001722812093794346, "step": 15600 }, { "epoch": 2.03133125325013, "grad_norm": 0.0014526959275826812, "learning_rate": 4.760449537379782e-05, "loss": 0.00017294855788350106, "step": 15625 }, { "epoch": 2.0345813832553303, "grad_norm": 0.0018753077602013946, "learning_rate": 4.7590971484735495e-05, "loss": 0.0001641126349568367, "step": 15650 }, { "epoch": 2.0378315132605302, "grad_norm": 0.004806871060281992, "learning_rate": 4.757741146039419e-05, "loss": 0.00015752952545881272, "step": 15675 }, { "epoch": 2.0410816432657306, "grad_norm": 0.001489722984842956, "learning_rate": 4.756381532246379e-05, "loss": 0.0001614074781537056, "step": 15700 }, { "epoch": 2.044331773270931, "grad_norm": 0.001606178586371243, "learning_rate": 4.755018309269194e-05, "loss": 0.00015808012336492538, "step": 15725 }, { "epoch": 2.047581903276131, "grad_norm": 0.003261657664552331, "learning_rate": 4.753651479288398e-05, "loss": 0.0001637156493961811, "step": 15750 }, { "epoch": 2.0508320332813312, "grad_norm": 0.00272456300444901, "learning_rate": 4.7522810444903e-05, "loss": 0.00016159968450665474, "step": 15775 }, { "epoch": 2.0540821632865316, "grad_norm": 0.00374131603166461, "learning_rate": 4.75090700706697e-05, "loss": 0.00017268521711230278, "step": 15800 }, { "epoch": 2.0573322932917315, "grad_norm": 0.001509288907982409, "learning_rate": 4.749529369216246e-05, "loss": 0.0001449667662382126, "step": 15825 }, { "epoch": 2.060582423296932, "grad_norm": 0.001631575170904398, "learning_rate": 4.748148133141718e-05, "loss": 0.0001835348829627037, "step": 15850 }, { "epoch": 2.0638325533021322, "grad_norm": 0.0013842219486832619, "learning_rate": 4.746763301052739e-05, "loss": 0.00016309289261698723, "step": 15875 }, { "epoch": 2.067082683307332, "grad_norm": 0.0010653831996023655, "learning_rate": 4.7453748751644075e-05, "loss": 0.00016087114810943602, "step": 15900 }, { "epoch": 2.0703328133125325, "grad_norm": 0.0026510499883443117, "learning_rate": 4.7439828576975766e-05, "loss": 0.00014180582948029042, "step": 15925 }, { "epoch": 2.073582943317733, "grad_norm": 0.0007459137123078108, "learning_rate": 4.7425872508788384e-05, "loss": 0.0001659255288541317, "step": 15950 }, { "epoch": 2.0768330733229328, "grad_norm": 0.0011213262332603335, "learning_rate": 4.74118805694053e-05, "loss": 0.00015620710328221322, "step": 15975 }, { "epoch": 2.080083203328133, "grad_norm": 0.0010032757418230176, "learning_rate": 4.739785278120725e-05, "loss": 0.00014287895523011683, "step": 16000 }, { "epoch": 2.0833333333333335, "grad_norm": 0.001386907184496522, "learning_rate": 4.738378916663233e-05, "loss": 0.0001561414636671543, "step": 16025 }, { "epoch": 2.0865834633385334, "grad_norm": 0.003277514362707734, "learning_rate": 4.73696897481759e-05, "loss": 0.00016391506418585777, "step": 16050 }, { "epoch": 2.0898335933437338, "grad_norm": 0.0013601903337985277, "learning_rate": 4.7355554548390636e-05, "loss": 0.00015725653618574144, "step": 16075 }, { "epoch": 2.093083723348934, "grad_norm": 0.005771314259618521, "learning_rate": 4.7341383589886423e-05, "loss": 0.00016310496255755424, "step": 16100 }, { "epoch": 2.096333853354134, "grad_norm": 0.0051210480742156506, "learning_rate": 4.732717689533035e-05, "loss": 0.00015210462734103203, "step": 16125 }, { "epoch": 2.0995839833593344, "grad_norm": 0.003579964628443122, "learning_rate": 4.731293448744666e-05, "loss": 0.0001609601080417633, "step": 16150 }, { "epoch": 2.1028341133645347, "grad_norm": 0.0032983669079840183, "learning_rate": 4.7298656389016735e-05, "loss": 0.0001764364168047905, "step": 16175 }, { "epoch": 2.1060842433697347, "grad_norm": 0.0009351523476652801, "learning_rate": 4.728434262287904e-05, "loss": 0.00015692852437496185, "step": 16200 }, { "epoch": 2.109334373374935, "grad_norm": 0.001914246822707355, "learning_rate": 4.726999321192908e-05, "loss": 0.00014737078920006751, "step": 16225 }, { "epoch": 2.1125845033801354, "grad_norm": 0.01522519625723362, "learning_rate": 4.725560817911939e-05, "loss": 0.00014986968599259854, "step": 16250 }, { "epoch": 2.1158346333853353, "grad_norm": 0.004886586219072342, "learning_rate": 4.724118754745949e-05, "loss": 0.00015928454697132112, "step": 16275 }, { "epoch": 2.1190847633905356, "grad_norm": 0.001382531481795013, "learning_rate": 4.7226731340015814e-05, "loss": 0.00016962438821792601, "step": 16300 }, { "epoch": 2.122334893395736, "grad_norm": 0.003711164928972721, "learning_rate": 4.721223957991174e-05, "loss": 0.00018285322934389115, "step": 16325 }, { "epoch": 2.125585023400936, "grad_norm": 0.001002818695269525, "learning_rate": 4.7197712290327465e-05, "loss": 0.00019346415996551513, "step": 16350 }, { "epoch": 2.1288351534061363, "grad_norm": 0.0012133610434830189, "learning_rate": 4.718314949450007e-05, "loss": 0.00015758270397782327, "step": 16375 }, { "epoch": 2.1320852834113366, "grad_norm": 0.006691213231533766, "learning_rate": 4.7168551215723395e-05, "loss": 0.0001590108871459961, "step": 16400 }, { "epoch": 2.1353354134165365, "grad_norm": 0.0008093746728263795, "learning_rate": 4.715391747734804e-05, "loss": 0.00014729909598827363, "step": 16425 }, { "epoch": 2.138585543421737, "grad_norm": 0.0008228124352172017, "learning_rate": 4.7139248302781335e-05, "loss": 0.00014613672159612178, "step": 16450 }, { "epoch": 2.1418356734269373, "grad_norm": 0.0027114360127598047, "learning_rate": 4.712454371548729e-05, "loss": 0.0001646210253238678, "step": 16475 }, { "epoch": 2.145085803432137, "grad_norm": 0.001401035813614726, "learning_rate": 4.710980373898656e-05, "loss": 0.00016259271651506424, "step": 16500 }, { "epoch": 2.1483359334373375, "grad_norm": 0.0011040671961382031, "learning_rate": 4.709502839685639e-05, "loss": 0.0001643284223973751, "step": 16525 }, { "epoch": 2.151586063442538, "grad_norm": 0.0015414290828630328, "learning_rate": 4.708021771273061e-05, "loss": 0.00015894066542387008, "step": 16550 }, { "epoch": 2.154836193447738, "grad_norm": 0.0017135144444182515, "learning_rate": 4.706537171029959e-05, "loss": 0.00013949666172266006, "step": 16575 }, { "epoch": 2.158086323452938, "grad_norm": 0.0010736393742263317, "learning_rate": 4.7050490413310166e-05, "loss": 0.00014713740907609462, "step": 16600 }, { "epoch": 2.1613364534581385, "grad_norm": 0.0010634919162839651, "learning_rate": 4.703557384556566e-05, "loss": 0.00015331355854868888, "step": 16625 }, { "epoch": 2.1645865834633384, "grad_norm": 0.0017489851452410221, "learning_rate": 4.7020622030925785e-05, "loss": 0.00014966667629778385, "step": 16650 }, { "epoch": 2.167836713468539, "grad_norm": 0.003463171888142824, "learning_rate": 4.700563499330664e-05, "loss": 0.0001615521125495434, "step": 16675 }, { "epoch": 2.171086843473739, "grad_norm": 0.002824497176334262, "learning_rate": 4.699061275668068e-05, "loss": 0.00014396561309695243, "step": 16700 }, { "epoch": 2.174336973478939, "grad_norm": 0.003909654449671507, "learning_rate": 4.6975555345076644e-05, "loss": 0.00016086556017398833, "step": 16725 }, { "epoch": 2.1775871034841394, "grad_norm": 0.007627058308571577, "learning_rate": 4.696046278257954e-05, "loss": 0.00014832202345132828, "step": 16750 }, { "epoch": 2.1808372334893398, "grad_norm": 0.003833773545920849, "learning_rate": 4.694533509333061e-05, "loss": 0.0001377189438790083, "step": 16775 }, { "epoch": 2.1840873634945397, "grad_norm": 0.002015323843806982, "learning_rate": 4.693017230152727e-05, "loss": 0.00014453311450779438, "step": 16800 }, { "epoch": 2.18733749349974, "grad_norm": 0.0015338279772549868, "learning_rate": 4.6914974431423095e-05, "loss": 0.0001446526125073433, "step": 16825 }, { "epoch": 2.19058762350494, "grad_norm": 0.007382693234831095, "learning_rate": 4.689974150732776e-05, "loss": 0.0001543944887816906, "step": 16850 }, { "epoch": 2.1938377535101403, "grad_norm": 0.007402203045785427, "learning_rate": 4.688447355360702e-05, "loss": 0.00014317329972982407, "step": 16875 }, { "epoch": 2.1970878835153407, "grad_norm": 0.0030225885566323996, "learning_rate": 4.686917059468265e-05, "loss": 0.00014895868487656118, "step": 16900 }, { "epoch": 2.2003380135205406, "grad_norm": 0.0025700044352561235, "learning_rate": 4.685383265503243e-05, "loss": 0.00014215481467545033, "step": 16925 }, { "epoch": 2.203588143525741, "grad_norm": 0.0025312029756605625, "learning_rate": 4.683845975919008e-05, "loss": 0.0001388161163777113, "step": 16950 }, { "epoch": 2.2068382735309413, "grad_norm": 0.0013139694929122925, "learning_rate": 4.682305193174524e-05, "loss": 0.00015126691199839114, "step": 16975 }, { "epoch": 2.210088403536141, "grad_norm": 0.002048899419605732, "learning_rate": 4.6807609197343444e-05, "loss": 0.00014540230855345727, "step": 17000 }, { "epoch": 2.2133385335413416, "grad_norm": 0.0032946141436696053, "learning_rate": 4.679213158068602e-05, "loss": 0.0001423128880560398, "step": 17025 }, { "epoch": 2.216588663546542, "grad_norm": 0.002506490331143141, "learning_rate": 4.677661910653013e-05, "loss": 0.00015011140145361425, "step": 17050 }, { "epoch": 2.219838793551742, "grad_norm": 0.0008630409138277173, "learning_rate": 4.676107179968867e-05, "loss": 0.0001389457006007433, "step": 17075 }, { "epoch": 2.223088923556942, "grad_norm": 0.0019061139319092035, "learning_rate": 4.674548968503026e-05, "loss": 0.00012431109324097632, "step": 17100 }, { "epoch": 2.2263390535621426, "grad_norm": 0.001061435672454536, "learning_rate": 4.672987278747919e-05, "loss": 0.00013729206286370755, "step": 17125 }, { "epoch": 2.2295891835673425, "grad_norm": 0.0025890942197293043, "learning_rate": 4.671422113201541e-05, "loss": 0.000145235862582922, "step": 17150 }, { "epoch": 2.232839313572543, "grad_norm": 0.0016887147212401032, "learning_rate": 4.6698534743674436e-05, "loss": 0.00013569452799856664, "step": 17175 }, { "epoch": 2.236089443577743, "grad_norm": 0.007036378141492605, "learning_rate": 4.668281364754735e-05, "loss": 0.00013721744529902934, "step": 17200 }, { "epoch": 2.239339573582943, "grad_norm": 0.0023496176581829786, "learning_rate": 4.666705786878077e-05, "loss": 0.0001310267113149166, "step": 17225 }, { "epoch": 2.2425897035881435, "grad_norm": 0.0036521628499031067, "learning_rate": 4.665126743257677e-05, "loss": 0.00013894345611333847, "step": 17250 }, { "epoch": 2.2425897035881435, "eval_loss": 0.0005545838503167033, "eval_runtime": 9.044, "eval_samples_per_second": 552.854, "eval_steps_per_second": 4.423, "step": 17250 }, { "epoch": 2.2425897035881435, "eval_holdout_avg_strict_f1": 0.09842238514349709, "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": 0.41258366800535473, "eval_holdout_nemotron_pii_strict_f1": 0.2584221748400853, "eval_holdout_open_pii_masking_500k_strict_f1": 0.2046483549652883, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.2069920387677397, "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": 2.245839833593344, "grad_norm": 0.002494937041774392, "learning_rate": 4.663544236419286e-05, "loss": 0.00014013076201081277, "step": 17275 }, { "epoch": 2.2490899635985437, "grad_norm": 0.0010333035606890917, "learning_rate": 4.6619582688941967e-05, "loss": 0.00013317276723682882, "step": 17300 }, { "epoch": 2.252340093603744, "grad_norm": 0.0018065182957798243, "learning_rate": 4.660368843219233e-05, "loss": 0.00012043621391057968, "step": 17325 }, { "epoch": 2.2555902236089445, "grad_norm": 0.0019112216541543603, "learning_rate": 4.6587759619367556e-05, "loss": 0.00011801742017269135, "step": 17350 }, { "epoch": 2.2588403536141444, "grad_norm": 0.004013299476355314, "learning_rate": 4.657179627594649e-05, "loss": 0.00013386973179876804, "step": 17375 }, { "epoch": 2.2620904836193447, "grad_norm": 0.0015371774788945913, "learning_rate": 4.6555798427463214e-05, "loss": 0.00012612015008926393, "step": 17400 }, { "epoch": 2.265340613624545, "grad_norm": 0.0025730461347848177, "learning_rate": 4.653976609950702e-05, "loss": 0.00013202549889683722, "step": 17425 }, { "epoch": 2.268590743629745, "grad_norm": 0.003649880411103368, "learning_rate": 4.6523699317722344e-05, "loss": 0.00013057315722107886, "step": 17450 }, { "epoch": 2.2718408736349454, "grad_norm": 0.0028747033793479204, "learning_rate": 4.650759810780872e-05, "loss": 0.00014772376045584678, "step": 17475 }, { "epoch": 2.2750910036401457, "grad_norm": 0.00198904937133193, "learning_rate": 4.6491462495520755e-05, "loss": 0.00013945327140390873, "step": 17500 }, { "epoch": 2.2783411336453456, "grad_norm": 0.0031680921092629433, "learning_rate": 4.64752925066681e-05, "loss": 0.00013854780234396458, "step": 17525 }, { "epoch": 2.281591263650546, "grad_norm": 0.0023765999358147383, "learning_rate": 4.645908816711538e-05, "loss": 0.00015536213293671609, "step": 17550 }, { "epoch": 2.2848413936557463, "grad_norm": 0.002978266216814518, "learning_rate": 4.644284950278217e-05, "loss": 0.00012839575298130514, "step": 17575 }, { "epoch": 2.2880915236609463, "grad_norm": 0.00213080202229321, "learning_rate": 4.6426576539642944e-05, "loss": 0.00013535557314753533, "step": 17600 }, { "epoch": 2.2913416536661466, "grad_norm": 0.001640473841689527, "learning_rate": 4.641026930372703e-05, "loss": 0.0001250910200178623, "step": 17625 }, { "epoch": 2.294591783671347, "grad_norm": 0.001546473940834403, "learning_rate": 4.639392782111861e-05, "loss": 0.00013299187645316124, "step": 17650 }, { "epoch": 2.297841913676547, "grad_norm": 0.0011444675037637353, "learning_rate": 4.6377552117956605e-05, "loss": 0.000139878848567605, "step": 17675 }, { "epoch": 2.3010920436817472, "grad_norm": 0.0017905583372339606, "learning_rate": 4.636114222043471e-05, "loss": 0.0001338920369744301, "step": 17700 }, { "epoch": 2.3043421736869476, "grad_norm": 0.001992162549868226, "learning_rate": 4.634469815480128e-05, "loss": 0.00012586017139256, "step": 17725 }, { "epoch": 2.3075923036921475, "grad_norm": 0.0033574625849723816, "learning_rate": 4.6328219947359345e-05, "loss": 0.00015158464200794696, "step": 17750 }, { "epoch": 2.310842433697348, "grad_norm": 0.0018413373036310077, "learning_rate": 4.631170762446654e-05, "loss": 0.0001398076955229044, "step": 17775 }, { "epoch": 2.3140925637025482, "grad_norm": 0.0013639956014230847, "learning_rate": 4.6295161212535085e-05, "loss": 0.00013965430669486524, "step": 17800 }, { "epoch": 2.317342693707748, "grad_norm": 0.0013880865881219506, "learning_rate": 4.62785807380317e-05, "loss": 0.00012973963283002376, "step": 17825 }, { "epoch": 2.3205928237129485, "grad_norm": 0.002634076401591301, "learning_rate": 4.62619662274776e-05, "loss": 0.00011847912333905697, "step": 17850 }, { "epoch": 2.323842953718149, "grad_norm": 0.0025655420031398535, "learning_rate": 4.624531770744845e-05, "loss": 0.00013092794455587864, "step": 17875 }, { "epoch": 2.3270930837233488, "grad_norm": 0.0011559384874999523, "learning_rate": 4.622863520457431e-05, "loss": 0.00013991005718708038, "step": 17900 }, { "epoch": 2.330343213728549, "grad_norm": 0.001358254812657833, "learning_rate": 4.621191874553961e-05, "loss": 0.0001306273229420185, "step": 17925 }, { "epoch": 2.3335933437337495, "grad_norm": 0.0014580064453184605, "learning_rate": 4.619516835708305e-05, "loss": 0.00012974940240383147, "step": 17950 }, { "epoch": 2.3368434737389494, "grad_norm": 0.0014505706494674087, "learning_rate": 4.617838406599766e-05, "loss": 0.00012352496385574342, "step": 17975 }, { "epoch": 2.3400936037441498, "grad_norm": 0.001112140016630292, "learning_rate": 4.616156589913066e-05, "loss": 0.00015324057079851627, "step": 18000 }, { "epoch": 2.34334373374935, "grad_norm": 0.0038436620961874723, "learning_rate": 4.614471388338346e-05, "loss": 0.00014144724234938622, "step": 18025 }, { "epoch": 2.34659386375455, "grad_norm": 0.0019351233495399356, "learning_rate": 4.612782804571164e-05, "loss": 0.0001533479243516922, "step": 18050 }, { "epoch": 2.3498439937597504, "grad_norm": 0.0018907878547906876, "learning_rate": 4.6110908413124844e-05, "loss": 0.00015710491687059402, "step": 18075 }, { "epoch": 2.3530941237649508, "grad_norm": 0.002069657202810049, "learning_rate": 4.60939550126868e-05, "loss": 0.000148171940818429, "step": 18100 }, { "epoch": 2.3563442537701507, "grad_norm": 0.0029697371646761894, "learning_rate": 4.607696787151522e-05, "loss": 0.0001361760962754488, "step": 18125 }, { "epoch": 2.359594383775351, "grad_norm": 0.0006994548020884395, "learning_rate": 4.605994701678182e-05, "loss": 0.00012747122906148434, "step": 18150 }, { "epoch": 2.3628445137805514, "grad_norm": 0.0012264895485714078, "learning_rate": 4.604289247571222e-05, "loss": 0.00013983145356178284, "step": 18175 }, { "epoch": 2.3660946437857513, "grad_norm": 0.0017523291753605008, "learning_rate": 4.6025804275585923e-05, "loss": 0.0001352354884147644, "step": 18200 }, { "epoch": 2.3693447737909517, "grad_norm": 0.001540504046715796, "learning_rate": 4.600868244373629e-05, "loss": 0.00011708905920386314, "step": 18225 }, { "epoch": 2.372594903796152, "grad_norm": 0.007799025624990463, "learning_rate": 4.599152700755045e-05, "loss": 0.0001339723076671362, "step": 18250 }, { "epoch": 2.375845033801352, "grad_norm": 0.001975638559088111, "learning_rate": 4.597433799446931e-05, "loss": 0.00013622744008898736, "step": 18275 }, { "epoch": 2.3790951638065523, "grad_norm": 0.002473060740157962, "learning_rate": 4.5957115431987456e-05, "loss": 0.00012812127359211446, "step": 18300 }, { "epoch": 2.3823452938117526, "grad_norm": 0.0024872813373804092, "learning_rate": 4.593985934765317e-05, "loss": 0.00016370425000786782, "step": 18325 }, { "epoch": 2.3855954238169526, "grad_norm": 0.0016458655009046197, "learning_rate": 4.5922569769068337e-05, "loss": 0.0001424828264862299, "step": 18350 }, { "epoch": 2.388845553822153, "grad_norm": 0.031232131645083427, "learning_rate": 4.590524672388842e-05, "loss": 0.0001416871976107359, "step": 18375 }, { "epoch": 2.3920956838273533, "grad_norm": 0.0017826862167567015, "learning_rate": 4.5887890239822394e-05, "loss": 0.00012266278266906739, "step": 18400 }, { "epoch": 2.395345813832553, "grad_norm": 0.000492918654344976, "learning_rate": 4.587050034463276e-05, "loss": 0.0001391277275979519, "step": 18425 }, { "epoch": 2.3985959438377535, "grad_norm": 0.005189166869968176, "learning_rate": 4.5853077066135425e-05, "loss": 0.000135421147570014, "step": 18450 }, { "epoch": 2.401846073842954, "grad_norm": 0.0033815971110016108, "learning_rate": 4.583562043219972e-05, "loss": 0.000134381502866745, "step": 18475 }, { "epoch": 2.405096203848154, "grad_norm": 0.012698855251073837, "learning_rate": 4.5818130470748315e-05, "loss": 0.0001342376321554184, "step": 18500 }, { "epoch": 2.408346333853354, "grad_norm": 0.0010202961275354028, "learning_rate": 4.5800607209757195e-05, "loss": 0.0001464000716805458, "step": 18525 }, { "epoch": 2.4115964638585545, "grad_norm": 0.0015058701392263174, "learning_rate": 4.578305067725561e-05, "loss": 0.00014441371895372867, "step": 18550 }, { "epoch": 2.4148465938637544, "grad_norm": 0.004408426117151976, "learning_rate": 4.5765460901326016e-05, "loss": 0.00012546195648610592, "step": 18575 }, { "epoch": 2.418096723868955, "grad_norm": 0.0032601039856672287, "learning_rate": 4.574783791010407e-05, "loss": 0.00012056730687618256, "step": 18600 }, { "epoch": 2.421346853874155, "grad_norm": 0.0019638906233012676, "learning_rate": 4.573018173177853e-05, "loss": 0.00013217531144618988, "step": 18625 }, { "epoch": 2.424596983879355, "grad_norm": 0.002587093273177743, "learning_rate": 4.5712492394591245e-05, "loss": 0.00012486680410802364, "step": 18650 }, { "epoch": 2.4278471138845554, "grad_norm": 0.003023201134055853, "learning_rate": 4.569476992683712e-05, "loss": 0.0001134636066854, "step": 18675 }, { "epoch": 2.431097243889756, "grad_norm": 0.0010909851407632232, "learning_rate": 4.567701435686404e-05, "loss": 0.0001254910882562399, "step": 18700 }, { "epoch": 2.4343473738949557, "grad_norm": 0.0016962402733042836, "learning_rate": 4.565922571307285e-05, "loss": 0.00012230719439685345, "step": 18725 }, { "epoch": 2.437597503900156, "grad_norm": 0.0023738655727356672, "learning_rate": 4.5641404023917274e-05, "loss": 0.00012746294029057027, "step": 18750 }, { "epoch": 2.4408476339053564, "grad_norm": 0.0019502120558172464, "learning_rate": 4.5623549317903915e-05, "loss": 0.00014015112072229385, "step": 18775 }, { "epoch": 2.4440977639105563, "grad_norm": 0.0059543875977396965, "learning_rate": 4.560566162359217e-05, "loss": 0.00013732610270380974, "step": 18800 }, { "epoch": 2.4473478939157567, "grad_norm": 0.0023328778333961964, "learning_rate": 4.558774096959423e-05, "loss": 0.00013245033100247382, "step": 18825 }, { "epoch": 2.450598023920957, "grad_norm": 0.001375131425447762, "learning_rate": 4.556978738457499e-05, "loss": 0.00012461092323064803, "step": 18850 }, { "epoch": 2.453848153926157, "grad_norm": 0.0016843504272401333, "learning_rate": 4.555180089725201e-05, "loss": 0.0001222700998187065, "step": 18875 }, { "epoch": 2.4570982839313573, "grad_norm": 0.0007752921083010733, "learning_rate": 4.5533781536395495e-05, "loss": 0.00012718867510557174, "step": 18900 }, { "epoch": 2.4603484139365577, "grad_norm": 0.0019048528047278523, "learning_rate": 4.551572933082822e-05, "loss": 0.0001389115769416094, "step": 18925 }, { "epoch": 2.4635985439417576, "grad_norm": 0.0028496277518570423, "learning_rate": 4.5497644309425516e-05, "loss": 0.00012886772863566877, "step": 18950 }, { "epoch": 2.466848673946958, "grad_norm": 0.0012810933403670788, "learning_rate": 4.547952650111517e-05, "loss": 0.00014181365258991718, "step": 18975 }, { "epoch": 2.4700988039521583, "grad_norm": 0.002849346725270152, "learning_rate": 4.546137593487746e-05, "loss": 0.00012382476590573786, "step": 19000 }, { "epoch": 2.473348933957358, "grad_norm": 0.0025115942116826773, "learning_rate": 4.5443192639745015e-05, "loss": 0.00013078431598842144, "step": 19025 }, { "epoch": 2.4765990639625586, "grad_norm": 0.004229061305522919, "learning_rate": 4.542497664480284e-05, "loss": 0.00012128566391766072, "step": 19050 }, { "epoch": 2.479849193967759, "grad_norm": 0.0009478461579419672, "learning_rate": 4.5406727979188255e-05, "loss": 0.00010305379517376423, "step": 19075 }, { "epoch": 2.483099323972959, "grad_norm": 0.001231037313118577, "learning_rate": 4.5388446672090814e-05, "loss": 0.0001633635349571705, "step": 19100 }, { "epoch": 2.486349453978159, "grad_norm": 0.0029634146485477686, "learning_rate": 4.5370132752752294e-05, "loss": 0.00015426699072122575, "step": 19125 }, { "epoch": 2.4895995839833596, "grad_norm": 0.0011719039175659418, "learning_rate": 4.5351786250466636e-05, "loss": 0.00014665596187114717, "step": 19150 }, { "epoch": 2.4928497139885595, "grad_norm": 0.0012164535000920296, "learning_rate": 4.53334071945799e-05, "loss": 0.00012682666070759296, "step": 19175 }, { "epoch": 2.49609984399376, "grad_norm": 0.0012999143218621612, "learning_rate": 4.531499561449022e-05, "loss": 0.00010815507732331753, "step": 19200 }, { "epoch": 2.49934997399896, "grad_norm": 0.0025509654078632593, "learning_rate": 4.529655153964775e-05, "loss": 0.00012493634596467019, "step": 19225 }, { "epoch": 2.50260010400416, "grad_norm": 0.0032128184102475643, "learning_rate": 4.52780749995546e-05, "loss": 0.00011340872384607792, "step": 19250 }, { "epoch": 2.5058502340093605, "grad_norm": 0.0019127612467855215, "learning_rate": 4.525956602376486e-05, "loss": 0.00012537105940282344, "step": 19275 }, { "epoch": 2.509100364014561, "grad_norm": 0.005020787473767996, "learning_rate": 4.5241024641884456e-05, "loss": 0.00012422969564795494, "step": 19300 }, { "epoch": 2.5123504940197607, "grad_norm": 0.0008939008112065494, "learning_rate": 4.522245088357116e-05, "loss": 0.00012096607126295567, "step": 19325 }, { "epoch": 2.515600624024961, "grad_norm": 0.0042106895707547665, "learning_rate": 4.5203844778534554e-05, "loss": 0.00012804225087165833, "step": 19350 }, { "epoch": 2.5188507540301615, "grad_norm": 0.0034091793932020664, "learning_rate": 4.518520635653594e-05, "loss": 0.00012403788045048714, "step": 19375 }, { "epoch": 2.5221008840353614, "grad_norm": 0.0009586841333657503, "learning_rate": 4.5166535647388296e-05, "loss": 0.0001262547541409731, "step": 19400 }, { "epoch": 2.5253510140405617, "grad_norm": 0.0019376667914912105, "learning_rate": 4.5147832680956284e-05, "loss": 0.00011265106499195099, "step": 19425 }, { "epoch": 2.528601144045762, "grad_norm": 0.002278760774061084, "learning_rate": 4.512909748715613e-05, "loss": 0.0001353222969919443, "step": 19450 }, { "epoch": 2.531851274050962, "grad_norm": 0.00255572353489697, "learning_rate": 4.511033009595564e-05, "loss": 0.00012048978358507156, "step": 19475 }, { "epoch": 2.5351014040561624, "grad_norm": 0.0012360839173197746, "learning_rate": 4.50915305373741e-05, "loss": 0.00014318311586976052, "step": 19500 }, { "epoch": 2.5383515340613627, "grad_norm": 0.002191453240811825, "learning_rate": 4.507269884148224e-05, "loss": 0.00011643744073808193, "step": 19525 }, { "epoch": 2.5416016640665626, "grad_norm": 0.0020136490929871798, "learning_rate": 4.505383503840221e-05, "loss": 0.000126743670552969, "step": 19550 }, { "epoch": 2.544851794071763, "grad_norm": 0.0034482793416827917, "learning_rate": 4.503493915830753e-05, "loss": 0.00014158072881400585, "step": 19575 }, { "epoch": 2.5481019240769633, "grad_norm": 0.0006676966440863907, "learning_rate": 4.5016011231422995e-05, "loss": 0.00012507325969636442, "step": 19600 }, { "epoch": 2.5513520540821633, "grad_norm": 0.0023069949820637703, "learning_rate": 4.4997051288024686e-05, "loss": 0.00012421890161931515, "step": 19625 }, { "epoch": 2.5546021840873636, "grad_norm": 0.004075527191162109, "learning_rate": 4.497805935843989e-05, "loss": 0.00012232734821736812, "step": 19650 }, { "epoch": 2.557852314092564, "grad_norm": 0.00142563390545547, "learning_rate": 4.4959035473047054e-05, "loss": 0.0001180881354957819, "step": 19675 }, { "epoch": 2.561102444097764, "grad_norm": 0.00250995927490294, "learning_rate": 4.4939979662275745e-05, "loss": 0.00011440288275480271, "step": 19700 }, { "epoch": 2.5643525741029642, "grad_norm": 0.0018000878626480699, "learning_rate": 4.4920891956606594e-05, "loss": 0.00012221713550388812, "step": 19725 }, { "epoch": 2.5676027041081646, "grad_norm": 0.000926925684325397, "learning_rate": 4.490177238657124e-05, "loss": 0.00011894667521119118, "step": 19750 }, { "epoch": 2.5708528341133645, "grad_norm": 0.001865015015937388, "learning_rate": 4.48826209827523e-05, "loss": 0.00012133187614381313, "step": 19775 }, { "epoch": 2.574102964118565, "grad_norm": 0.0020374879240989685, "learning_rate": 4.4863437775783323e-05, "loss": 0.00012800646014511587, "step": 19800 }, { "epoch": 2.577353094123765, "grad_norm": 0.00834053847938776, "learning_rate": 4.48442227963487e-05, "loss": 0.00012342216446995736, "step": 19825 }, { "epoch": 2.580603224128965, "grad_norm": 0.002234078012406826, "learning_rate": 4.4824976075183654e-05, "loss": 0.00013570293784141542, "step": 19850 }, { "epoch": 2.5838533541341655, "grad_norm": 0.002560495166108012, "learning_rate": 4.4805697643074206e-05, "loss": 0.00013679668307304383, "step": 19875 }, { "epoch": 2.5871034841393654, "grad_norm": 0.0011408563004806638, "learning_rate": 4.4786387530857056e-05, "loss": 0.00012191601097583771, "step": 19900 }, { "epoch": 2.5903536141445658, "grad_norm": 0.0033448992762714624, "learning_rate": 4.476704576941961e-05, "loss": 0.00013250913470983506, "step": 19925 }, { "epoch": 2.593603744149766, "grad_norm": 0.0007627570885233581, "learning_rate": 4.47476723896999e-05, "loss": 0.000125507153570652, "step": 19950 }, { "epoch": 2.596853874154966, "grad_norm": 0.0009357262752018869, "learning_rate": 4.4728267422686496e-05, "loss": 0.0001244943216443062, "step": 19975 }, { "epoch": 2.6001040041601664, "grad_norm": 0.0020638012792915106, "learning_rate": 4.4708830899418544e-05, "loss": 0.00011289622634649276, "step": 20000 }, { "epoch": 2.6033541341653668, "grad_norm": 0.0025549668353050947, "learning_rate": 4.4689362850985625e-05, "loss": 0.0001239689625799656, "step": 20025 }, { "epoch": 2.6066042641705667, "grad_norm": 0.001738504390232265, "learning_rate": 4.466986330852777e-05, "loss": 0.00011987220495939255, "step": 20050 }, { "epoch": 2.609854394175767, "grad_norm": 0.0034898375160992146, "learning_rate": 4.465033230323538e-05, "loss": 0.00010324159637093545, "step": 20075 }, { "epoch": 2.6131045241809674, "grad_norm": 0.0032646439503878355, "learning_rate": 4.463076986634916e-05, "loss": 0.00011766684241592884, "step": 20100 }, { "epoch": 2.6163546541861673, "grad_norm": 0.0017099531833082438, "learning_rate": 4.461117602916014e-05, "loss": 0.00011553521268069745, "step": 20125 }, { "epoch": 2.6196047841913677, "grad_norm": 0.001333041349425912, "learning_rate": 4.459155082300952e-05, "loss": 0.00011520256288349628, "step": 20150 }, { "epoch": 2.622854914196568, "grad_norm": 0.0026836670003831387, "learning_rate": 4.457189427928872e-05, "loss": 0.00011987383477389813, "step": 20175 }, { "epoch": 2.626105044201768, "grad_norm": 0.001452404772862792, "learning_rate": 4.455220642943927e-05, "loss": 0.00012432758696377278, "step": 20200 }, { "epoch": 2.6293551742069683, "grad_norm": 0.0016890125116333365, "learning_rate": 4.4532487304952764e-05, "loss": 0.00010978843085467815, "step": 20225 }, { "epoch": 2.6326053042121687, "grad_norm": 0.000463778676930815, "learning_rate": 4.4512736937370844e-05, "loss": 0.00012221131473779678, "step": 20250 }, { "epoch": 2.6358554342173686, "grad_norm": 0.0005282393540255725, "learning_rate": 4.4492955358285104e-05, "loss": 0.00011833841912448407, "step": 20275 }, { "epoch": 2.639105564222569, "grad_norm": 0.007521711755543947, "learning_rate": 4.447314259933708e-05, "loss": 0.00011013507843017578, "step": 20300 }, { "epoch": 2.642355694227769, "grad_norm": 0.001455447869375348, "learning_rate": 4.445329869221817e-05, "loss": 0.00012725085951387883, "step": 20325 }, { "epoch": 2.645605824232969, "grad_norm": 0.000706520804669708, "learning_rate": 4.4433423668669604e-05, "loss": 0.00012050364166498184, "step": 20350 }, { "epoch": 2.6488559542381696, "grad_norm": 0.002538814675062895, "learning_rate": 4.4413517560482376e-05, "loss": 0.0001273483317345381, "step": 20375 }, { "epoch": 2.6521060842433695, "grad_norm": 0.0016709818737581372, "learning_rate": 4.4393580399497214e-05, "loss": 0.00012278759852051734, "step": 20400 }, { "epoch": 2.65535621424857, "grad_norm": 0.0006076059071347117, "learning_rate": 4.4373612217604496e-05, "loss": 0.00011577093973755837, "step": 20425 }, { "epoch": 2.65860634425377, "grad_norm": 0.0018147925147786736, "learning_rate": 4.435361304674423e-05, "loss": 0.0001043164450675249, "step": 20450 }, { "epoch": 2.66185647425897, "grad_norm": 0.003252327674999833, "learning_rate": 4.4333582918906e-05, "loss": 0.00013649925589561462, "step": 20475 }, { "epoch": 2.6651066042641705, "grad_norm": 0.005322558805346489, "learning_rate": 4.431352186612889e-05, "loss": 0.00011188880540430546, "step": 20500 }, { "epoch": 2.668356734269371, "grad_norm": 0.0034299592953175306, "learning_rate": 4.429342992050148e-05, "loss": 0.00012011456303298473, "step": 20525 }, { "epoch": 2.6716068642745707, "grad_norm": 0.0012762858532369137, "learning_rate": 4.427330711416172e-05, "loss": 0.00010836035944521427, "step": 20550 }, { "epoch": 2.674856994279771, "grad_norm": 0.0010440415935590863, "learning_rate": 4.4253153479296964e-05, "loss": 0.00011502891778945923, "step": 20575 }, { "epoch": 2.6781071242849714, "grad_norm": 0.0015414906665682793, "learning_rate": 4.423296904814386e-05, "loss": 0.0001234014518558979, "step": 20600 }, { "epoch": 2.6813572542901714, "grad_norm": 0.0012247645063325763, "learning_rate": 4.4212753852988296e-05, "loss": 0.00011393558233976364, "step": 20625 }, { "epoch": 2.6846073842953717, "grad_norm": 0.001106818439438939, "learning_rate": 4.419250792616542e-05, "loss": 0.00011690087616443634, "step": 20650 }, { "epoch": 2.687857514300572, "grad_norm": 0.002656723605468869, "learning_rate": 4.4172231300059485e-05, "loss": 0.00010846965014934539, "step": 20675 }, { "epoch": 2.691107644305772, "grad_norm": 0.001735582947731018, "learning_rate": 4.415192400710388e-05, "loss": 0.00011780579574406147, "step": 20700 }, { "epoch": 2.691107644305772, "eval_loss": 0.0004374645359348506, "eval_runtime": 9.1661, "eval_samples_per_second": 545.489, "eval_steps_per_second": 4.364, "step": 20700 }, { "epoch": 2.691107644305772, "eval_holdout_avg_strict_f1": 0.11837511902072301, "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": 0.48383561643835615, "eval_holdout_nemotron_pii_strict_f1": 0.3570530000546956, "eval_holdout_open_pii_masking_500k_strict_f1": 0.23175675675675675, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.2294809359781447, "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": 2.6943577743109723, "grad_norm": 0.0015983999473974109, "learning_rate": 4.413158607978104e-05, "loss": 0.00011728547513484955, "step": 20725 }, { "epoch": 2.6976079043161727, "grad_norm": 0.0018345334101468325, "learning_rate": 4.4111217550622385e-05, "loss": 9.05183982104063e-05, "step": 20750 }, { "epoch": 2.7008580343213726, "grad_norm": 0.0007273370865732431, "learning_rate": 4.409081845220831e-05, "loss": 9.845491498708725e-05, "step": 20775 }, { "epoch": 2.704108164326573, "grad_norm": 0.004765399731695652, "learning_rate": 4.407038881716808e-05, "loss": 0.00012204086408019066, "step": 20800 }, { "epoch": 2.7073582943317733, "grad_norm": 0.0012289343867450953, "learning_rate": 4.404992867817983e-05, "loss": 0.00011148681864142418, "step": 20825 }, { "epoch": 2.7106084243369732, "grad_norm": 0.0041665080934762955, "learning_rate": 4.402943806797048e-05, "loss": 0.0001245866809040308, "step": 20850 }, { "epoch": 2.7138585543421736, "grad_norm": 0.0009457609849050641, "learning_rate": 4.4008917019315676e-05, "loss": 0.00011880895122885704, "step": 20875 }, { "epoch": 2.717108684347374, "grad_norm": 0.0019655637443065643, "learning_rate": 4.398836556503976e-05, "loss": 0.00011588115245103836, "step": 20900 }, { "epoch": 2.720358814352574, "grad_norm": 0.0032526394352316856, "learning_rate": 4.3967783738015724e-05, "loss": 0.00011598647572100162, "step": 20925 }, { "epoch": 2.7236089443577742, "grad_norm": 0.0015118825249373913, "learning_rate": 4.394717157116512e-05, "loss": 9.912591427564621e-05, "step": 20950 }, { "epoch": 2.7268590743629746, "grad_norm": 0.0020698097068816423, "learning_rate": 4.392652909745804e-05, "loss": 0.00011991173960268497, "step": 20975 }, { "epoch": 2.7301092043681745, "grad_norm": 0.002521323272958398, "learning_rate": 4.390585634991305e-05, "loss": 0.0001280319970101118, "step": 21000 }, { "epoch": 2.733359334373375, "grad_norm": 0.0008192371460609138, "learning_rate": 4.388515336159716e-05, "loss": 0.00016657285392284392, "step": 21025 }, { "epoch": 2.736609464378575, "grad_norm": 0.0016620284877717495, "learning_rate": 4.386442016562572e-05, "loss": 0.00013518611900508403, "step": 21050 }, { "epoch": 2.739859594383775, "grad_norm": 0.0011725135846063495, "learning_rate": 4.38436567951624e-05, "loss": 0.00011334162205457687, "step": 21075 }, { "epoch": 2.7431097243889755, "grad_norm": 0.001341929892078042, "learning_rate": 4.382286328341918e-05, "loss": 0.00011002503335475921, "step": 21100 }, { "epoch": 2.746359854394176, "grad_norm": 0.0007556485943496227, "learning_rate": 4.38020396636562e-05, "loss": 0.00012014972046017647, "step": 21125 }, { "epoch": 2.7496099843993758, "grad_norm": 0.001568184932693839, "learning_rate": 4.378118596918179e-05, "loss": 0.00011602149344980717, "step": 21150 }, { "epoch": 2.752860114404576, "grad_norm": 0.0007142325048334897, "learning_rate": 4.376030223335237e-05, "loss": 0.00011547482572495937, "step": 21175 }, { "epoch": 2.7561102444097765, "grad_norm": 0.002017251681536436, "learning_rate": 4.3739388489572416e-05, "loss": 0.00011696443893015385, "step": 21200 }, { "epoch": 2.7593603744149764, "grad_norm": 0.0008025502902455628, "learning_rate": 4.371844477129441e-05, "loss": 0.00011482313275337219, "step": 21225 }, { "epoch": 2.7626105044201767, "grad_norm": 0.008052889257669449, "learning_rate": 4.369747111201877e-05, "loss": 0.00011181281879544259, "step": 21250 }, { "epoch": 2.765860634425377, "grad_norm": 0.0014665208291262388, "learning_rate": 4.367646754529383e-05, "loss": 0.0001287536881864071, "step": 21275 }, { "epoch": 2.769110764430577, "grad_norm": 0.0010699396952986717, "learning_rate": 4.365543410471571e-05, "loss": 0.00013060064986348153, "step": 21300 }, { "epoch": 2.7723608944357774, "grad_norm": 0.002420753473415971, "learning_rate": 4.363437082392838e-05, "loss": 0.00011137327179312706, "step": 21325 }, { "epoch": 2.7756110244409777, "grad_norm": 0.0012363316491246223, "learning_rate": 4.361327773662349e-05, "loss": 0.00014740562997758388, "step": 21350 }, { "epoch": 2.7788611544461777, "grad_norm": 0.001054872409440577, "learning_rate": 4.359215487654039e-05, "loss": 0.00010994773358106613, "step": 21375 }, { "epoch": 2.782111284451378, "grad_norm": 0.0021502096205949783, "learning_rate": 4.357100227746606e-05, "loss": 0.00011184143833816052, "step": 21400 }, { "epoch": 2.7853614144565784, "grad_norm": 0.0025471800472587347, "learning_rate": 4.354981997323501e-05, "loss": 0.00011151881888508797, "step": 21425 }, { "epoch": 2.7886115444617783, "grad_norm": 0.001021609059534967, "learning_rate": 4.352860799772931e-05, "loss": 0.00010406337678432464, "step": 21450 }, { "epoch": 2.7918616744669786, "grad_norm": 0.0068647414445877075, "learning_rate": 4.3507366384878486e-05, "loss": 0.00011970474384725094, "step": 21475 }, { "epoch": 2.795111804472179, "grad_norm": 0.006094173062592745, "learning_rate": 4.3486095168659435e-05, "loss": 0.0001264354959130287, "step": 21500 }, { "epoch": 2.798361934477379, "grad_norm": 0.00240479432977736, "learning_rate": 4.346479438309643e-05, "loss": 0.00012017049826681614, "step": 21525 }, { "epoch": 2.8016120644825793, "grad_norm": 0.0014283722266554832, "learning_rate": 4.3443464062261055e-05, "loss": 0.0001104743592441082, "step": 21550 }, { "epoch": 2.8048621944877796, "grad_norm": 0.0019245878793299198, "learning_rate": 4.34221042402721e-05, "loss": 0.00010544533841311932, "step": 21575 }, { "epoch": 2.8081123244929795, "grad_norm": 0.0009432962979190052, "learning_rate": 4.3400714951295586e-05, "loss": 0.00012702370062470436, "step": 21600 }, { "epoch": 2.81136245449818, "grad_norm": 0.0030835135839879513, "learning_rate": 4.337929622954463e-05, "loss": 0.00010390413925051689, "step": 21625 }, { "epoch": 2.8146125845033803, "grad_norm": 0.0016890065744519234, "learning_rate": 4.335784810927945e-05, "loss": 0.00012419668957591056, "step": 21650 }, { "epoch": 2.81786271450858, "grad_norm": 0.0017951803747564554, "learning_rate": 4.3336370624807286e-05, "loss": 0.00012576142325997352, "step": 21675 }, { "epoch": 2.8211128445137805, "grad_norm": 0.002675277879461646, "learning_rate": 4.3314863810482344e-05, "loss": 0.00012105302885174751, "step": 21700 }, { "epoch": 2.824362974518981, "grad_norm": 0.003099619410932064, "learning_rate": 4.3293327700705744e-05, "loss": 0.00012650035321712494, "step": 21725 }, { "epoch": 2.827613104524181, "grad_norm": 0.0013802091125398874, "learning_rate": 4.3271762329925456e-05, "loss": 0.00011229857802391052, "step": 21750 }, { "epoch": 2.830863234529381, "grad_norm": 0.0008018408552743495, "learning_rate": 4.325016773263628e-05, "loss": 0.00011777706444263459, "step": 21775 }, { "epoch": 2.8341133645345815, "grad_norm": 0.0031042713671922684, "learning_rate": 4.322854394337974e-05, "loss": 0.00011567095294594765, "step": 21800 }, { "epoch": 2.8373634945397814, "grad_norm": 0.001013422035612166, "learning_rate": 4.320689099674406e-05, "loss": 0.0001094942819327116, "step": 21825 }, { "epoch": 2.840613624544982, "grad_norm": 0.0008522962452843785, "learning_rate": 4.318520892736412e-05, "loss": 0.00010848546400666237, "step": 21850 }, { "epoch": 2.843863754550182, "grad_norm": 0.0013135053450241685, "learning_rate": 4.316349776992136e-05, "loss": 0.00011342357844114304, "step": 21875 }, { "epoch": 2.847113884555382, "grad_norm": 0.0025406270287930965, "learning_rate": 4.314175755914375e-05, "loss": 0.00012101396918296813, "step": 21900 }, { "epoch": 2.8503640145605824, "grad_norm": 0.0034799096174538136, "learning_rate": 4.311998832980576e-05, "loss": 0.00011799228377640247, "step": 21925 }, { "epoch": 2.8536141445657828, "grad_norm": 0.0035920601803809404, "learning_rate": 4.309819011672823e-05, "loss": 0.00012042688205838204, "step": 21950 }, { "epoch": 2.8568642745709827, "grad_norm": 0.0020514419302344322, "learning_rate": 4.3076362954778393e-05, "loss": 0.00012154130265116691, "step": 21975 }, { "epoch": 2.860114404576183, "grad_norm": 0.0014667565701529384, "learning_rate": 4.3054506878869794e-05, "loss": 0.00012286231853067875, "step": 22000 }, { "epoch": 2.8633645345813834, "grad_norm": 0.0020479902159422636, "learning_rate": 4.3032621923962203e-05, "loss": 0.00011883649975061417, "step": 22025 }, { "epoch": 2.8666146645865833, "grad_norm": 0.001707935007289052, "learning_rate": 4.3010708125061596e-05, "loss": 0.00012006035074591637, "step": 22050 }, { "epoch": 2.8698647945917837, "grad_norm": 0.0016003301134333014, "learning_rate": 4.298876551722008e-05, "loss": 0.0001111164502799511, "step": 22075 }, { "epoch": 2.873114924596984, "grad_norm": 0.0012627223040908575, "learning_rate": 4.296679413553584e-05, "loss": 0.00011253083124756813, "step": 22100 }, { "epoch": 2.876365054602184, "grad_norm": 0.0007519132923334837, "learning_rate": 4.2944794015153114e-05, "loss": 0.00012518050149083138, "step": 22125 }, { "epoch": 2.8796151846073843, "grad_norm": 0.0009976483415812254, "learning_rate": 4.292276519126207e-05, "loss": 0.00012308670207858085, "step": 22150 }, { "epoch": 2.8828653146125847, "grad_norm": 0.0025145686231553555, "learning_rate": 4.290070769909882e-05, "loss": 0.0001339484564960003, "step": 22175 }, { "epoch": 2.8861154446177846, "grad_norm": 0.0014710049144923687, "learning_rate": 4.287862157394531e-05, "loss": 0.00011939244344830513, "step": 22200 }, { "epoch": 2.889365574622985, "grad_norm": 0.00458088144659996, "learning_rate": 4.285650685112929e-05, "loss": 0.00011669550091028213, "step": 22225 }, { "epoch": 2.8926157046281853, "grad_norm": 0.005479548592120409, "learning_rate": 4.283436356602426e-05, "loss": 0.00011207645758986472, "step": 22250 }, { "epoch": 2.895865834633385, "grad_norm": 0.0032126375008374453, "learning_rate": 4.2812191754049416e-05, "loss": 0.00011596095748245717, "step": 22275 }, { "epoch": 2.8991159646385856, "grad_norm": 0.008369572460651398, "learning_rate": 4.278999145066956e-05, "loss": 0.00012018016539514065, "step": 22300 }, { "epoch": 2.902366094643786, "grad_norm": 0.007213692180812359, "learning_rate": 4.27677626913951e-05, "loss": 0.0001279247272759676, "step": 22325 }, { "epoch": 2.905616224648986, "grad_norm": 0.0024194561410695314, "learning_rate": 4.274550551178191e-05, "loss": 0.00012097568251192569, "step": 22350 }, { "epoch": 2.908866354654186, "grad_norm": 0.001562710152938962, "learning_rate": 4.272321994743137e-05, "loss": 0.00011379463598132133, "step": 22375 }, { "epoch": 2.9121164846593866, "grad_norm": 0.000971033878158778, "learning_rate": 4.2700906033990246e-05, "loss": 0.00010655920952558518, "step": 22400 }, { "epoch": 2.9153666146645865, "grad_norm": 0.0017622068990021944, "learning_rate": 4.267856380715065e-05, "loss": 0.00010518478229641915, "step": 22425 }, { "epoch": 2.918616744669787, "grad_norm": 0.0006176725728437304, "learning_rate": 4.2656193302649975e-05, "loss": 9.673822671175003e-05, "step": 22450 }, { "epoch": 2.921866874674987, "grad_norm": 0.0009493599063716829, "learning_rate": 4.2633794556270865e-05, "loss": 0.00012251473963260652, "step": 22475 }, { "epoch": 2.925117004680187, "grad_norm": 0.0012775755021721125, "learning_rate": 4.261136760384112e-05, "loss": 0.00012170745059847832, "step": 22500 }, { "epoch": 2.9283671346853875, "grad_norm": 0.0007665643352083862, "learning_rate": 4.2588912481233666e-05, "loss": 0.00011376162059605122, "step": 22525 }, { "epoch": 2.931617264690588, "grad_norm": 0.0014551812782883644, "learning_rate": 4.256642922436648e-05, "loss": 0.00010671044699847698, "step": 22550 }, { "epoch": 2.9348673946957877, "grad_norm": 0.0019352270755916834, "learning_rate": 4.2543917869202555e-05, "loss": 0.00011777355335652828, "step": 22575 }, { "epoch": 2.938117524700988, "grad_norm": 0.001100274850614369, "learning_rate": 4.2521378451749805e-05, "loss": 0.00011031841859221458, "step": 22600 }, { "epoch": 2.9413676547061884, "grad_norm": 0.0013112631859257817, "learning_rate": 4.249881100806107e-05, "loss": 0.00011953277513384819, "step": 22625 }, { "epoch": 2.9446177847113884, "grad_norm": 0.002739132847636938, "learning_rate": 4.247621557423397e-05, "loss": 0.00011528748087584973, "step": 22650 }, { "epoch": 2.9478679147165887, "grad_norm": 0.0018405403243377805, "learning_rate": 4.245359218641094e-05, "loss": 0.00010743656195700169, "step": 22675 }, { "epoch": 2.951118044721789, "grad_norm": 0.0015506376512348652, "learning_rate": 4.2430940880779096e-05, "loss": 0.00010667442344129085, "step": 22700 }, { "epoch": 2.954368174726989, "grad_norm": 0.0018239638302475214, "learning_rate": 4.240826169357024e-05, "loss": 0.00012290218845009804, "step": 22725 }, { "epoch": 2.9576183047321893, "grad_norm": 0.0006942609907127917, "learning_rate": 4.238555466106074e-05, "loss": 0.0001141014602035284, "step": 22750 }, { "epoch": 2.9608684347373897, "grad_norm": 0.001283511403016746, "learning_rate": 4.236281981957153e-05, "loss": 0.00010799052193760872, "step": 22775 }, { "epoch": 2.9641185647425896, "grad_norm": 0.0018495937110856175, "learning_rate": 4.234005720546801e-05, "loss": 0.00011130035854876042, "step": 22800 }, { "epoch": 2.96736869474779, "grad_norm": 0.0009274588082917035, "learning_rate": 4.231726685516002e-05, "loss": 9.860348887741566e-05, "step": 22825 }, { "epoch": 2.9706188247529903, "grad_norm": 0.001409834367223084, "learning_rate": 4.229444880510174e-05, "loss": 0.00011361884884536266, "step": 22850 }, { "epoch": 2.9738689547581902, "grad_norm": 0.0008306899107992649, "learning_rate": 4.227160309179168e-05, "loss": 9.721308015286922e-05, "step": 22875 }, { "epoch": 2.9771190847633906, "grad_norm": 0.0014764899387955666, "learning_rate": 4.2248729751772586e-05, "loss": 0.00011204950511455536, "step": 22900 }, { "epoch": 2.980369214768591, "grad_norm": 0.0010945445392280817, "learning_rate": 4.22258288216314e-05, "loss": 0.00010479540564119816, "step": 22925 }, { "epoch": 2.983619344773791, "grad_norm": 0.003540492383763194, "learning_rate": 4.2202900337999196e-05, "loss": 0.00011321960017085075, "step": 22950 }, { "epoch": 2.9868694747789912, "grad_norm": 0.00788059365004301, "learning_rate": 4.217994433755111e-05, "loss": 0.0001204497367143631, "step": 22975 }, { "epoch": 2.9901196047841916, "grad_norm": 0.003780391300097108, "learning_rate": 4.215696085700632e-05, "loss": 0.00010514517314732075, "step": 23000 }, { "epoch": 2.9933697347893915, "grad_norm": 0.003067641519010067, "learning_rate": 4.213394993312792e-05, "loss": 0.00011237187311053276, "step": 23025 }, { "epoch": 2.996619864794592, "grad_norm": 0.001331760548055172, "learning_rate": 4.2110911602722937e-05, "loss": 0.0001090239454060793, "step": 23050 }, { "epoch": 2.999869994799792, "grad_norm": 0.0011301770573481917, "learning_rate": 4.208784590264221e-05, "loss": 9.060624986886978e-05, "step": 23075 }, { "epoch": 3.003120124804992, "grad_norm": 0.0005481968400999904, "learning_rate": 4.206475286978037e-05, "loss": 9.929303079843521e-05, "step": 23100 }, { "epoch": 3.0063702548101925, "grad_norm": 0.00205858051776886, "learning_rate": 4.204163254107577e-05, "loss": 0.0001014355756342411, "step": 23125 }, { "epoch": 3.0096203848153924, "grad_norm": 0.0014049686724320054, "learning_rate": 4.201848495351042e-05, "loss": 9.610663168132306e-05, "step": 23150 }, { "epoch": 3.0128705148205928, "grad_norm": 0.002500481205061078, "learning_rate": 4.1995310144109925e-05, "loss": 9.441668167710304e-05, "step": 23175 }, { "epoch": 3.016120644825793, "grad_norm": 0.0015667990082874894, "learning_rate": 4.1972108149943445e-05, "loss": 9.540068916976452e-05, "step": 23200 }, { "epoch": 3.019370774830993, "grad_norm": 0.002018737606704235, "learning_rate": 4.194887900812361e-05, "loss": 0.00012376774102449418, "step": 23225 }, { "epoch": 3.0226209048361934, "grad_norm": 0.0009505741763859987, "learning_rate": 4.19256227558065e-05, "loss": 9.603582322597503e-05, "step": 23250 }, { "epoch": 3.0258710348413937, "grad_norm": 0.0012013164814561605, "learning_rate": 4.190233943019152e-05, "loss": 0.00010708124376833439, "step": 23275 }, { "epoch": 3.0291211648465937, "grad_norm": 0.0015938347205519676, "learning_rate": 4.187902906852141e-05, "loss": 0.00011160518042743205, "step": 23300 }, { "epoch": 3.032371294851794, "grad_norm": 0.0018334237392991781, "learning_rate": 4.185569170808215e-05, "loss": 0.00011199971660971641, "step": 23325 }, { "epoch": 3.0356214248569944, "grad_norm": 0.0013979518553242087, "learning_rate": 4.1832327386202887e-05, "loss": 0.00010286960750818252, "step": 23350 }, { "epoch": 3.0388715548621943, "grad_norm": 0.002501849550753832, "learning_rate": 4.1808936140255914e-05, "loss": 9.838162921369076e-05, "step": 23375 }, { "epoch": 3.0421216848673946, "grad_norm": 0.002554062521085143, "learning_rate": 4.17855180076566e-05, "loss": 9.16569959372282e-05, "step": 23400 }, { "epoch": 3.045371814872595, "grad_norm": 0.0012999202590435743, "learning_rate": 4.176207302586329e-05, "loss": 9.508879855275155e-05, "step": 23425 }, { "epoch": 3.048621944877795, "grad_norm": 0.006127315107733011, "learning_rate": 4.173860123237729e-05, "loss": 0.0001099599339067936, "step": 23450 }, { "epoch": 3.0518720748829953, "grad_norm": 0.0009308779845014215, "learning_rate": 4.171510266474281e-05, "loss": 0.00012838857248425483, "step": 23475 }, { "epoch": 3.0551222048881956, "grad_norm": 0.0015354519709944725, "learning_rate": 4.1691577360546855e-05, "loss": 0.00011543597094714641, "step": 23500 }, { "epoch": 3.0583723348933955, "grad_norm": 0.005569889675825834, "learning_rate": 4.1668025357419216e-05, "loss": 0.00010665758512914181, "step": 23525 }, { "epoch": 3.061622464898596, "grad_norm": 0.0009565159562043846, "learning_rate": 4.164444669303238e-05, "loss": 0.00012459917925298215, "step": 23550 }, { "epoch": 3.0648725949037963, "grad_norm": 0.002009939169511199, "learning_rate": 4.1620841405101495e-05, "loss": 0.00010589437559247017, "step": 23575 }, { "epoch": 3.068122724908996, "grad_norm": 0.002162981778383255, "learning_rate": 4.159720953138428e-05, "loss": 0.0001057141087949276, "step": 23600 }, { "epoch": 3.0713728549141965, "grad_norm": 0.004441654309630394, "learning_rate": 4.1573551109680986e-05, "loss": 0.00010300349444150925, "step": 23625 }, { "epoch": 3.074622984919397, "grad_norm": 0.0010740088764578104, "learning_rate": 4.154986617783433e-05, "loss": 0.00010108290240168572, "step": 23650 }, { "epoch": 3.077873114924597, "grad_norm": 0.0015953021356835961, "learning_rate": 4.152615477372941e-05, "loss": 0.00011523210443556309, "step": 23675 }, { "epoch": 3.081123244929797, "grad_norm": 0.001653257291764021, "learning_rate": 4.1502416935293714e-05, "loss": 0.00010464210063219071, "step": 23700 }, { "epoch": 3.0843733749349975, "grad_norm": 0.0021358870435506105, "learning_rate": 4.147865270049698e-05, "loss": 9.777233004570008e-05, "step": 23725 }, { "epoch": 3.0876235049401974, "grad_norm": 0.0009592963615432382, "learning_rate": 4.145486210735116e-05, "loss": 8.792969398200511e-05, "step": 23750 }, { "epoch": 3.090873634945398, "grad_norm": 0.0017140634590759873, "learning_rate": 4.143104519391039e-05, "loss": 0.00010282695293426514, "step": 23775 }, { "epoch": 3.094123764950598, "grad_norm": 0.0020951353944838047, "learning_rate": 4.1407201998270905e-05, "loss": 0.00010960533283650875, "step": 23800 }, { "epoch": 3.097373894955798, "grad_norm": 0.0013650343753397465, "learning_rate": 4.1383332558570966e-05, "loss": 0.00010544072836637497, "step": 23825 }, { "epoch": 3.1006240249609984, "grad_norm": 0.0005820131045766175, "learning_rate": 4.135943691299082e-05, "loss": 0.00010747028514742851, "step": 23850 }, { "epoch": 3.103874154966199, "grad_norm": 0.0009744393755681813, "learning_rate": 4.133551509975264e-05, "loss": 9.915635921061039e-05, "step": 23875 }, { "epoch": 3.1071242849713987, "grad_norm": 0.001790615962818265, "learning_rate": 4.131156715712043e-05, "loss": 9.722976945340633e-05, "step": 23900 }, { "epoch": 3.110374414976599, "grad_norm": 0.001490483758971095, "learning_rate": 4.1287593123400024e-05, "loss": 9.300995618104934e-05, "step": 23925 }, { "epoch": 3.1136245449817994, "grad_norm": 0.001756942830979824, "learning_rate": 4.126359303693896e-05, "loss": 0.0001124845165759325, "step": 23950 }, { "epoch": 3.1168746749869993, "grad_norm": 0.0029301128815859556, "learning_rate": 4.123956693612646e-05, "loss": 0.0001009349711239338, "step": 23975 }, { "epoch": 3.1201248049921997, "grad_norm": 0.0005423895199783146, "learning_rate": 4.1215514859393364e-05, "loss": 9.993207640945911e-05, "step": 24000 }, { "epoch": 3.1233749349974, "grad_norm": 0.0011979271657764912, "learning_rate": 4.119143684521204e-05, "loss": 0.000112836305052042, "step": 24025 }, { "epoch": 3.1266250650026, "grad_norm": 0.0007727962802164257, "learning_rate": 4.116733293209638e-05, "loss": 8.280262351036072e-05, "step": 24050 }, { "epoch": 3.1298751950078003, "grad_norm": 0.002150925574824214, "learning_rate": 4.1143203158601665e-05, "loss": 9.501841850578785e-05, "step": 24075 }, { "epoch": 3.1331253250130007, "grad_norm": 0.0019343640888109803, "learning_rate": 4.1119047563324566e-05, "loss": 9.378094226121903e-05, "step": 24100 }, { "epoch": 3.1363754550182006, "grad_norm": 0.003619915572926402, "learning_rate": 4.109486618490305e-05, "loss": 0.00010194934904575348, "step": 24125 }, { "epoch": 3.139625585023401, "grad_norm": 0.0018030067440122366, "learning_rate": 4.107065906201631e-05, "loss": 0.00010059256106615067, "step": 24150 }, { "epoch": 3.139625585023401, "eval_loss": 0.0003573755093384534, "eval_runtime": 9.2535, "eval_samples_per_second": 540.334, "eval_steps_per_second": 4.323, "step": 24150 }, { "epoch": 3.139625585023401, "eval_holdout_avg_strict_f1": 0.1397550944220317, "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": 0.48018769551616264, "eval_holdout_nemotron_pii_strict_f1": 0.5093420574336606, "eval_holdout_open_pii_masking_500k_strict_f1": 0.2637963437553391, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.28397994193718656, "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": 3.1428757150286013, "grad_norm": 0.0022272595670074224, "learning_rate": 4.104642623338474e-05, "loss": 8.644469082355499e-05, "step": 24175 }, { "epoch": 3.146125845033801, "grad_norm": 0.0015068324282765388, "learning_rate": 4.1022167737769856e-05, "loss": 9.011005982756615e-05, "step": 24200 }, { "epoch": 3.1493759750390016, "grad_norm": 0.0012898758286610246, "learning_rate": 4.09978836139742e-05, "loss": 9.324708953499794e-05, "step": 24225 }, { "epoch": 3.152626105044202, "grad_norm": 0.0012354605132713914, "learning_rate": 4.097357390084133e-05, "loss": 9.656554087996483e-05, "step": 24250 }, { "epoch": 3.155876235049402, "grad_norm": 0.0025429408997297287, "learning_rate": 4.0949238637255726e-05, "loss": 9.083126671612263e-05, "step": 24275 }, { "epoch": 3.159126365054602, "grad_norm": 0.0011318862671032548, "learning_rate": 4.092487786214275e-05, "loss": 0.00010068341158330441, "step": 24300 }, { "epoch": 3.1623764950598026, "grad_norm": 0.0010923799127340317, "learning_rate": 4.0900491614468553e-05, "loss": 9.02609433978796e-05, "step": 24325 }, { "epoch": 3.1656266250650025, "grad_norm": 0.0010643497807905078, "learning_rate": 4.087607993324005e-05, "loss": 8.680823259055615e-05, "step": 24350 }, { "epoch": 3.168876755070203, "grad_norm": 0.0005180038278922439, "learning_rate": 4.085164285750481e-05, "loss": 9.202626533806324e-05, "step": 24375 }, { "epoch": 3.172126885075403, "grad_norm": 0.0018096473067998886, "learning_rate": 4.0827180426351066e-05, "loss": 0.0001069906447082758, "step": 24400 }, { "epoch": 3.175377015080603, "grad_norm": 0.0014822091907262802, "learning_rate": 4.080269267890755e-05, "loss": 9.759834967553615e-05, "step": 24425 }, { "epoch": 3.1786271450858035, "grad_norm": 0.001157595543190837, "learning_rate": 4.077817965434354e-05, "loss": 9.52710583806038e-05, "step": 24450 }, { "epoch": 3.181877275091004, "grad_norm": 0.0011253149714320898, "learning_rate": 4.075364139186872e-05, "loss": 9.487990289926529e-05, "step": 24475 }, { "epoch": 3.1851274050962037, "grad_norm": 0.0015978071605786681, "learning_rate": 4.072907793073316e-05, "loss": 9.730068035423755e-05, "step": 24500 }, { "epoch": 3.188377535101404, "grad_norm": 0.003416168736293912, "learning_rate": 4.07044893102272e-05, "loss": 9.626764804124833e-05, "step": 24525 }, { "epoch": 3.1916276651066045, "grad_norm": 0.0009533712291158736, "learning_rate": 4.067987556968147e-05, "loss": 0.00010094074532389641, "step": 24550 }, { "epoch": 3.1948777951118044, "grad_norm": 0.0026549645699560642, "learning_rate": 4.0655236748466754e-05, "loss": 9.18536726385355e-05, "step": 24575 }, { "epoch": 3.1981279251170047, "grad_norm": 0.0012051406083628535, "learning_rate": 4.063057288599395e-05, "loss": 9.321017190814019e-05, "step": 24600 }, { "epoch": 3.201378055122205, "grad_norm": 0.00318434601649642, "learning_rate": 4.0605884021714035e-05, "loss": 0.0001070852018892765, "step": 24625 }, { "epoch": 3.204628185127405, "grad_norm": 0.001234089257195592, "learning_rate": 4.0581170195117944e-05, "loss": 8.66824947297573e-05, "step": 24650 }, { "epoch": 3.2078783151326054, "grad_norm": 0.0012107540387660265, "learning_rate": 4.055643144573658e-05, "loss": 9.805122390389442e-05, "step": 24675 }, { "epoch": 3.2111284451378057, "grad_norm": 0.0005088862963020802, "learning_rate": 4.053166781314068e-05, "loss": 8.618056774139404e-05, "step": 24700 }, { "epoch": 3.2143785751430056, "grad_norm": 0.0008655544370412827, "learning_rate": 4.050687933694078e-05, "loss": 8.605234324932098e-05, "step": 24725 }, { "epoch": 3.217628705148206, "grad_norm": 0.0025494717992842197, "learning_rate": 4.048206605678719e-05, "loss": 8.945774286985398e-05, "step": 24750 }, { "epoch": 3.2208788351534063, "grad_norm": 0.0014393593883141875, "learning_rate": 4.045722801236986e-05, "loss": 8.181542158126831e-05, "step": 24775 }, { "epoch": 3.2241289651586063, "grad_norm": 0.0010358111467212439, "learning_rate": 4.043236524341836e-05, "loss": 0.00010851303115487098, "step": 24800 }, { "epoch": 3.2273790951638066, "grad_norm": 0.0012653307057917118, "learning_rate": 4.0407477789701806e-05, "loss": 9.024911560118198e-05, "step": 24825 }, { "epoch": 3.230629225169007, "grad_norm": 0.0016321642324328423, "learning_rate": 4.038256569102883e-05, "loss": 8.718301542103291e-05, "step": 24850 }, { "epoch": 3.233879355174207, "grad_norm": 0.0015622553182765841, "learning_rate": 4.035762898724744e-05, "loss": 0.00010265909135341644, "step": 24875 }, { "epoch": 3.2371294851794072, "grad_norm": 0.00211538840085268, "learning_rate": 4.0332667718245014e-05, "loss": 9.500089101493358e-05, "step": 24900 }, { "epoch": 3.240379615184607, "grad_norm": 0.0011446785647422075, "learning_rate": 4.030768192394824e-05, "loss": 9.393981657922268e-05, "step": 24925 }, { "epoch": 3.2436297451898075, "grad_norm": 0.0007954405155032873, "learning_rate": 4.028267164432302e-05, "loss": 8.584290742874145e-05, "step": 24950 }, { "epoch": 3.246879875195008, "grad_norm": 0.0009709447040222585, "learning_rate": 4.025763691937443e-05, "loss": 9.127996861934661e-05, "step": 24975 }, { "epoch": 3.250130005200208, "grad_norm": 0.002814921783283353, "learning_rate": 4.023257778914664e-05, "loss": 8.975589647889138e-05, "step": 25000 }, { "epoch": 3.253380135205408, "grad_norm": 0.0012137200683355331, "learning_rate": 4.020749429372286e-05, "loss": 8.445031009614468e-05, "step": 25025 }, { "epoch": 3.2566302652106085, "grad_norm": 0.0009105433127842844, "learning_rate": 4.018238647322528e-05, "loss": 9.277639910578727e-05, "step": 25050 }, { "epoch": 3.2598803952158084, "grad_norm": 0.0009155139559879899, "learning_rate": 4.0157254367814974e-05, "loss": 8.492943830788135e-05, "step": 25075 }, { "epoch": 3.2631305252210088, "grad_norm": 0.00200066901743412, "learning_rate": 4.013209801769189e-05, "loss": 9.576305747032166e-05, "step": 25100 }, { "epoch": 3.266380655226209, "grad_norm": 0.0017065186984837055, "learning_rate": 4.010691746309476e-05, "loss": 9.05652903020382e-05, "step": 25125 }, { "epoch": 3.269630785231409, "grad_norm": 0.0015295983757823706, "learning_rate": 4.0081712744300996e-05, "loss": 0.00010271692648530007, "step": 25150 }, { "epoch": 3.2728809152366094, "grad_norm": 0.0013383182231336832, "learning_rate": 4.005648390162669e-05, "loss": 9.401886723935605e-05, "step": 25175 }, { "epoch": 3.2761310452418098, "grad_norm": 0.002408167812973261, "learning_rate": 4.003123097542654e-05, "loss": 9.396607987582683e-05, "step": 25200 }, { "epoch": 3.2793811752470097, "grad_norm": 0.0014908835291862488, "learning_rate": 4.00059540060937e-05, "loss": 9.457217529416085e-05, "step": 25225 }, { "epoch": 3.28263130525221, "grad_norm": 0.0030781037639826536, "learning_rate": 3.998065303405985e-05, "loss": 9.87585075199604e-05, "step": 25250 }, { "epoch": 3.2858814352574104, "grad_norm": 0.001484910026192665, "learning_rate": 3.995532809979503e-05, "loss": 0.00010128175839781762, "step": 25275 }, { "epoch": 3.2891315652626103, "grad_norm": 0.0012540844036266208, "learning_rate": 3.992997924380763e-05, "loss": 8.949914015829563e-05, "step": 25300 }, { "epoch": 3.2923816952678107, "grad_norm": 0.0007909370469860733, "learning_rate": 3.990460650664426e-05, "loss": 8.675048127770423e-05, "step": 25325 }, { "epoch": 3.295631825273011, "grad_norm": 0.001990570919588208, "learning_rate": 3.9879209928889785e-05, "loss": 7.9526137560606e-05, "step": 25350 }, { "epoch": 3.298881955278211, "grad_norm": 0.001366597367450595, "learning_rate": 3.985378955116716e-05, "loss": 9.136821143329143e-05, "step": 25375 }, { "epoch": 3.3021320852834113, "grad_norm": 0.0011415251065045595, "learning_rate": 3.9828345414137436e-05, "loss": 7.96469021588564e-05, "step": 25400 }, { "epoch": 3.3053822152886116, "grad_norm": 0.0013105026446282864, "learning_rate": 3.980287755849966e-05, "loss": 0.00010866396129131317, "step": 25425 }, { "epoch": 3.3086323452938116, "grad_norm": 0.0012291978346183896, "learning_rate": 3.9777386024990824e-05, "loss": 8.885829709470272e-05, "step": 25450 }, { "epoch": 3.311882475299012, "grad_norm": 0.0016505079111084342, "learning_rate": 3.9751870854385775e-05, "loss": 9.675594978034497e-05, "step": 25475 }, { "epoch": 3.3151326053042123, "grad_norm": 0.0013598862569779158, "learning_rate": 3.972633208749719e-05, "loss": 8.392428047955036e-05, "step": 25500 }, { "epoch": 3.318382735309412, "grad_norm": 0.0012548116501420736, "learning_rate": 3.970076976517546e-05, "loss": 8.289668709039688e-05, "step": 25525 }, { "epoch": 3.3216328653146125, "grad_norm": 0.0025023315101861954, "learning_rate": 3.967518392830869e-05, "loss": 8.268818259239196e-05, "step": 25550 }, { "epoch": 3.324882995319813, "grad_norm": 0.0019125125836580992, "learning_rate": 3.964957461782259e-05, "loss": 9.039330296218396e-05, "step": 25575 }, { "epoch": 3.328133125325013, "grad_norm": 0.0034130453132092953, "learning_rate": 3.962394187468039e-05, "loss": 9.451045654714108e-05, "step": 25600 }, { "epoch": 3.331383255330213, "grad_norm": 0.002288531744852662, "learning_rate": 3.959828573988283e-05, "loss": 8.54935497045517e-05, "step": 25625 }, { "epoch": 3.3346333853354135, "grad_norm": 0.0010565639240667224, "learning_rate": 3.957260625446805e-05, "loss": 8.880363777279853e-05, "step": 25650 }, { "epoch": 3.3378835153406134, "grad_norm": 0.0006295223138295114, "learning_rate": 3.954690345951155e-05, "loss": 9.864924475550652e-05, "step": 25675 }, { "epoch": 3.341133645345814, "grad_norm": 0.0014672139659523964, "learning_rate": 3.952117739612612e-05, "loss": 8.892581798136234e-05, "step": 25700 }, { "epoch": 3.344383775351014, "grad_norm": 0.0020077088847756386, "learning_rate": 3.9495428105461746e-05, "loss": 9.933626279234886e-05, "step": 25725 }, { "epoch": 3.347633905356214, "grad_norm": 0.0013749367790296674, "learning_rate": 3.9469655628705587e-05, "loss": 8.753219619393348e-05, "step": 25750 }, { "epoch": 3.3508840353614144, "grad_norm": 0.0015395390801131725, "learning_rate": 3.944386000708189e-05, "loss": 8.806441910564899e-05, "step": 25775 }, { "epoch": 3.354134165366615, "grad_norm": 0.0020228589419275522, "learning_rate": 3.9418041281851894e-05, "loss": 7.905742153525352e-05, "step": 25800 }, { "epoch": 3.3573842953718147, "grad_norm": 0.0004365215718280524, "learning_rate": 3.939219949431384e-05, "loss": 8.859971538186073e-05, "step": 25825 }, { "epoch": 3.360634425377015, "grad_norm": 0.0007324684993363917, "learning_rate": 3.9366334685802824e-05, "loss": 8.911256678402424e-05, "step": 25850 }, { "epoch": 3.3638845553822154, "grad_norm": 0.001915088971145451, "learning_rate": 3.9340446897690775e-05, "loss": 8.725855499505997e-05, "step": 25875 }, { "epoch": 3.3671346853874153, "grad_norm": 0.001042870688252151, "learning_rate": 3.9314536171386386e-05, "loss": 9.229985065758229e-05, "step": 25900 }, { "epoch": 3.3703848153926157, "grad_norm": 0.0010240324772894382, "learning_rate": 3.9288602548335026e-05, "loss": 9.08229686319828e-05, "step": 25925 }, { "epoch": 3.373634945397816, "grad_norm": 0.0013166600838303566, "learning_rate": 3.9262646070018696e-05, "loss": 8.227393962442875e-05, "step": 25950 }, { "epoch": 3.376885075403016, "grad_norm": 0.0009171381825581193, "learning_rate": 3.923666677795596e-05, "loss": 8.806684985756874e-05, "step": 25975 }, { "epoch": 3.3801352054082163, "grad_norm": 0.004048086702823639, "learning_rate": 3.921066471370186e-05, "loss": 9.581565856933594e-05, "step": 26000 }, { "epoch": 3.3833853354134167, "grad_norm": 0.0007828929810784757, "learning_rate": 3.918463991884789e-05, "loss": 9.049317799508571e-05, "step": 26025 }, { "epoch": 3.3866354654186166, "grad_norm": 0.0014416170306503773, "learning_rate": 3.9158592435021864e-05, "loss": 8.525493554770946e-05, "step": 26050 }, { "epoch": 3.389885595423817, "grad_norm": 0.0009380407864227891, "learning_rate": 3.913252230388792e-05, "loss": 8.111022412776947e-05, "step": 26075 }, { "epoch": 3.3931357254290173, "grad_norm": 0.0017842461820691824, "learning_rate": 3.91064295671464e-05, "loss": 9.758899919688702e-05, "step": 26100 }, { "epoch": 3.3963858554342172, "grad_norm": 0.001130752032622695, "learning_rate": 3.908031426653383e-05, "loss": 8.735067211091519e-05, "step": 26125 }, { "epoch": 3.3996359854394176, "grad_norm": 0.0013672503409907222, "learning_rate": 3.90541764438228e-05, "loss": 8.133364841341972e-05, "step": 26150 }, { "epoch": 3.402886115444618, "grad_norm": 0.0006493767141364515, "learning_rate": 3.902801614082194e-05, "loss": 8.178262040019035e-05, "step": 26175 }, { "epoch": 3.406136245449818, "grad_norm": 0.0011602912563830614, "learning_rate": 3.9001833399375845e-05, "loss": 8.842766284942627e-05, "step": 26200 }, { "epoch": 3.409386375455018, "grad_norm": 0.003776392200961709, "learning_rate": 3.8975628261364975e-05, "loss": 8.810076862573623e-05, "step": 26225 }, { "epoch": 3.4126365054602186, "grad_norm": 0.0022605257108807564, "learning_rate": 3.8949400768705646e-05, "loss": 9.550930000841618e-05, "step": 26250 }, { "epoch": 3.4158866354654185, "grad_norm": 0.001133409095928073, "learning_rate": 3.892315096334992e-05, "loss": 8.409831672906876e-05, "step": 26275 }, { "epoch": 3.419136765470619, "grad_norm": 0.002654965966939926, "learning_rate": 3.889687888728553e-05, "loss": 8.769823238253593e-05, "step": 26300 }, { "epoch": 3.422386895475819, "grad_norm": 0.005250709597021341, "learning_rate": 3.8870584582535854e-05, "loss": 8.699395693838597e-05, "step": 26325 }, { "epoch": 3.425637025481019, "grad_norm": 0.0009391547064296901, "learning_rate": 3.884426809115982e-05, "loss": 9.910277090966701e-05, "step": 26350 }, { "epoch": 3.4288871554862195, "grad_norm": 0.0032367976382374763, "learning_rate": 3.8817929455251856e-05, "loss": 9.812760166823865e-05, "step": 26375 }, { "epoch": 3.43213728549142, "grad_norm": 0.0031146358232945204, "learning_rate": 3.879156871694179e-05, "loss": 0.00011471210978925228, "step": 26400 }, { "epoch": 3.4353874154966197, "grad_norm": 0.0014995039673522115, "learning_rate": 3.87651859183948e-05, "loss": 9.841899387538433e-05, "step": 26425 }, { "epoch": 3.43863754550182, "grad_norm": 0.00410782964900136, "learning_rate": 3.8738781101811386e-05, "loss": 8.709435351192952e-05, "step": 26450 }, { "epoch": 3.4418876755070205, "grad_norm": 0.0019997924100607634, "learning_rate": 3.8712354309427234e-05, "loss": 8.032403886318207e-05, "step": 26475 }, { "epoch": 3.4451378055122204, "grad_norm": 0.0017105770530179143, "learning_rate": 3.8685905583513186e-05, "loss": 7.696736138314008e-05, "step": 26500 }, { "epoch": 3.4483879355174207, "grad_norm": 0.0009137568413279951, "learning_rate": 3.8659434966375184e-05, "loss": 9.458622895181179e-05, "step": 26525 }, { "epoch": 3.451638065522621, "grad_norm": 0.0014752584975212812, "learning_rate": 3.8632942500354175e-05, "loss": 8.823718875646592e-05, "step": 26550 }, { "epoch": 3.454888195527821, "grad_norm": 0.0016514305025339127, "learning_rate": 3.8606428227826045e-05, "loss": 9.795199148356914e-05, "step": 26575 }, { "epoch": 3.4581383255330214, "grad_norm": 0.0011647139908745885, "learning_rate": 3.8579892191201585e-05, "loss": 9.997363202273845e-05, "step": 26600 }, { "epoch": 3.4613884555382217, "grad_norm": 0.0011244380148127675, "learning_rate": 3.855333443292637e-05, "loss": 9.549089707434178e-05, "step": 26625 }, { "epoch": 3.4646385855434216, "grad_norm": 0.0005215658457018435, "learning_rate": 3.852675499548073e-05, "loss": 8.603068999946117e-05, "step": 26650 }, { "epoch": 3.467888715548622, "grad_norm": 0.001083909417502582, "learning_rate": 3.850015392137969e-05, "loss": 7.394642569124698e-05, "step": 26675 }, { "epoch": 3.4711388455538223, "grad_norm": 0.00046778665273450315, "learning_rate": 3.847353125317287e-05, "loss": 8.790808729827404e-05, "step": 26700 }, { "epoch": 3.4743889755590223, "grad_norm": 0.0009438974084332585, "learning_rate": 3.844688703344441e-05, "loss": 8.239398710429668e-05, "step": 26725 }, { "epoch": 3.4776391055642226, "grad_norm": 0.0010166841093450785, "learning_rate": 3.8420221304812964e-05, "loss": 8.285310119390487e-05, "step": 26750 }, { "epoch": 3.480889235569423, "grad_norm": 0.0014629833167418838, "learning_rate": 3.839353410993156e-05, "loss": 9.326372295618058e-05, "step": 26775 }, { "epoch": 3.484139365574623, "grad_norm": 0.0010927970288321376, "learning_rate": 3.8366825491487576e-05, "loss": 9.683207608759403e-05, "step": 26800 }, { "epoch": 3.4873894955798233, "grad_norm": 0.0009596556192263961, "learning_rate": 3.834009549220264e-05, "loss": 8.885123766958713e-05, "step": 26825 }, { "epoch": 3.4906396255850236, "grad_norm": 0.0014347662217915058, "learning_rate": 3.8313344154832607e-05, "loss": 9.393858723342418e-05, "step": 26850 }, { "epoch": 3.4938897555902235, "grad_norm": 0.001051784842275083, "learning_rate": 3.8286571522167434e-05, "loss": 9.417968802154064e-05, "step": 26875 }, { "epoch": 3.497139885595424, "grad_norm": 0.0013369976077228785, "learning_rate": 3.825977763703118e-05, "loss": 9.227429516613484e-05, "step": 26900 }, { "epoch": 3.5003900156006242, "grad_norm": 0.0024364141281694174, "learning_rate": 3.8232962542281844e-05, "loss": 9.361395612359047e-05, "step": 26925 }, { "epoch": 3.503640145605824, "grad_norm": 0.0007169967866502702, "learning_rate": 3.8206126280811417e-05, "loss": 8.765165694057941e-05, "step": 26950 }, { "epoch": 3.5068902756110245, "grad_norm": 0.0004670530033763498, "learning_rate": 3.817926889554567e-05, "loss": 7.003902923315764e-05, "step": 26975 }, { "epoch": 3.510140405616225, "grad_norm": 0.0006450461223721504, "learning_rate": 3.815239042944424e-05, "loss": 9.642457589507104e-05, "step": 27000 }, { "epoch": 3.513390535621425, "grad_norm": 0.0017854358302429318, "learning_rate": 3.8125490925500425e-05, "loss": 8.500628173351288e-05, "step": 27025 }, { "epoch": 3.516640665626625, "grad_norm": 0.0023985118605196476, "learning_rate": 3.8098570426741195e-05, "loss": 8.679967373609543e-05, "step": 27050 }, { "epoch": 3.5198907956318255, "grad_norm": 0.0015156366862356663, "learning_rate": 3.807162897622712e-05, "loss": 8.453194051980972e-05, "step": 27075 }, { "epoch": 3.5231409256370254, "grad_norm": 0.0009398155380040407, "learning_rate": 3.804466661705226e-05, "loss": 7.888783700764179e-05, "step": 27100 }, { "epoch": 3.5263910556422258, "grad_norm": 0.0015724748373031616, "learning_rate": 3.8017683392344117e-05, "loss": 9.179246611893177e-05, "step": 27125 }, { "epoch": 3.529641185647426, "grad_norm": 0.0005494868382811546, "learning_rate": 3.799067934526358e-05, "loss": 8.492620661854745e-05, "step": 27150 }, { "epoch": 3.532891315652626, "grad_norm": 0.0018184686778113246, "learning_rate": 3.7963654519004854e-05, "loss": 9.416356682777405e-05, "step": 27175 }, { "epoch": 3.5361414456578264, "grad_norm": 0.0008792959852144122, "learning_rate": 3.793660895679536e-05, "loss": 8.669727481901646e-05, "step": 27200 }, { "epoch": 3.5393915756630268, "grad_norm": 0.001098624779842794, "learning_rate": 3.79095427018957e-05, "loss": 9.742262773215771e-05, "step": 27225 }, { "epoch": 3.5426417056682267, "grad_norm": 0.0010761888697743416, "learning_rate": 3.7882455797599554e-05, "loss": 8.075978606939316e-05, "step": 27250 }, { "epoch": 3.545891835673427, "grad_norm": 0.0008260676986537874, "learning_rate": 3.7855348287233664e-05, "loss": 7.844830863177776e-05, "step": 27275 }, { "epoch": 3.5491419656786274, "grad_norm": 0.0010481172939762473, "learning_rate": 3.782822021415772e-05, "loss": 8.028430864214897e-05, "step": 27300 }, { "epoch": 3.5523920956838273, "grad_norm": 0.0014507677406072617, "learning_rate": 3.780107162176429e-05, "loss": 8.239995688199997e-05, "step": 27325 }, { "epoch": 3.5556422256890277, "grad_norm": 0.0010632973862811923, "learning_rate": 3.777390255347878e-05, "loss": 7.860777899622918e-05, "step": 27350 }, { "epoch": 3.558892355694228, "grad_norm": 0.0009585049701854587, "learning_rate": 3.774671305275934e-05, "loss": 7.838768884539604e-05, "step": 27375 }, { "epoch": 3.562142485699428, "grad_norm": 0.0009723177063278854, "learning_rate": 3.77195031630968e-05, "loss": 7.683489937335253e-05, "step": 27400 }, { "epoch": 3.5653926157046283, "grad_norm": 0.0011632716050371528, "learning_rate": 3.769227292801462e-05, "loss": 7.261374965310097e-05, "step": 27425 }, { "epoch": 3.5686427457098286, "grad_norm": 0.0014631982194259763, "learning_rate": 3.766502239106877e-05, "loss": 8.62064678221941e-05, "step": 27450 }, { "epoch": 3.5718928757150286, "grad_norm": 0.002669555600732565, "learning_rate": 3.763775159584773e-05, "loss": 9.272622875869274e-05, "step": 27475 }, { "epoch": 3.575143005720229, "grad_norm": 0.0005132995429448783, "learning_rate": 3.7610460585972364e-05, "loss": 7.46492575854063e-05, "step": 27500 }, { "epoch": 3.5783931357254293, "grad_norm": 0.0003810037160292268, "learning_rate": 3.7583149405095875e-05, "loss": 8.257728070020675e-05, "step": 27525 }, { "epoch": 3.581643265730629, "grad_norm": 0.0024093142710626125, "learning_rate": 3.755581809690373e-05, "loss": 7.34195439144969e-05, "step": 27550 }, { "epoch": 3.5848933957358295, "grad_norm": 0.0010794025147333741, "learning_rate": 3.7528466705113585e-05, "loss": 7.935967296361923e-05, "step": 27575 }, { "epoch": 3.58814352574103, "grad_norm": 0.0017068680608645082, "learning_rate": 3.750109527347524e-05, "loss": 9.63863730430603e-05, "step": 27600 }, { "epoch": 3.58814352574103, "eval_loss": 0.00032223135349340737, "eval_runtime": 9.5337, "eval_samples_per_second": 524.458, "eval_steps_per_second": 4.196, "step": 27600 }, { "epoch": 3.58814352574103, "eval_holdout_avg_strict_f1": 0.14984492256443052, "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": 0.586391991875816, "eval_holdout_nemotron_pii_strict_f1": 0.476081593357001, "eval_holdout_open_pii_masking_500k_strict_f1": 0.2910511122431652, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.2947694507327535, "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": 3.59139365574623, "grad_norm": 0.0016995969926938415, "learning_rate": 3.7473703845770524e-05, "loss": 7.67542514950037e-05, "step": 27625 }, { "epoch": 3.59464378575143, "grad_norm": 0.0015318798832595348, "learning_rate": 3.744629246581326e-05, "loss": 8.480370044708252e-05, "step": 27650 }, { "epoch": 3.5978939157566305, "grad_norm": 0.0005722929490730166, "learning_rate": 3.7418861177449196e-05, "loss": 8.193565532565117e-05, "step": 27675 }, { "epoch": 3.6011440457618304, "grad_norm": 0.0014626308111473918, "learning_rate": 3.7391410024555915e-05, "loss": 8.080227300524712e-05, "step": 27700 }, { "epoch": 3.604394175767031, "grad_norm": 0.0014939573593437672, "learning_rate": 3.736393905104277e-05, "loss": 0.00014468187466263772, "step": 27725 }, { "epoch": 3.607644305772231, "grad_norm": 0.0005051989573985338, "learning_rate": 3.733644830085084e-05, "loss": 0.00010755314491689205, "step": 27750 }, { "epoch": 3.610894435777431, "grad_norm": 0.0005451402394101024, "learning_rate": 3.7308937817952794e-05, "loss": 9.664349257946015e-05, "step": 27775 }, { "epoch": 3.6141445657826314, "grad_norm": 0.0014758232282474637, "learning_rate": 3.7281407646352916e-05, "loss": 8.116085082292557e-05, "step": 27800 }, { "epoch": 3.6173946957878313, "grad_norm": 0.0014693525154143572, "learning_rate": 3.7253857830086943e-05, "loss": 8.168880827724934e-05, "step": 27825 }, { "epoch": 3.6206448257930317, "grad_norm": 0.003670844715088606, "learning_rate": 3.722628841322207e-05, "loss": 8.323997259140015e-05, "step": 27850 }, { "epoch": 3.623894955798232, "grad_norm": 0.0026250716764479876, "learning_rate": 3.71986994398568e-05, "loss": 9.673465974628926e-05, "step": 27875 }, { "epoch": 3.627145085803432, "grad_norm": 0.0005755139281973243, "learning_rate": 3.717109095412095e-05, "loss": 8.408916182816029e-05, "step": 27900 }, { "epoch": 3.6303952158086323, "grad_norm": 0.0012429039925336838, "learning_rate": 3.7143463000175546e-05, "loss": 9.075323119759559e-05, "step": 27925 }, { "epoch": 3.6336453458138327, "grad_norm": 0.018939530476927757, "learning_rate": 3.7115815622212746e-05, "loss": 9.085914120078086e-05, "step": 27950 }, { "epoch": 3.6368954758190326, "grad_norm": 0.001749672694131732, "learning_rate": 3.708814886445577e-05, "loss": 9.89038310945034e-05, "step": 27975 }, { "epoch": 3.640145605824233, "grad_norm": 0.0005961256683804095, "learning_rate": 3.706046277115886e-05, "loss": 9.209554642438888e-05, "step": 28000 }, { "epoch": 3.6433957358294333, "grad_norm": 0.001502865576185286, "learning_rate": 3.703275738660717e-05, "loss": 9.113331325352191e-05, "step": 28025 }, { "epoch": 3.6466458658346332, "grad_norm": 0.0010488522239029408, "learning_rate": 3.7005032755116696e-05, "loss": 9.097951464354991e-05, "step": 28050 }, { "epoch": 3.6498959958398336, "grad_norm": 0.0008806945406831801, "learning_rate": 3.697728892103426e-05, "loss": 8.132515475153923e-05, "step": 28075 }, { "epoch": 3.653146125845034, "grad_norm": 0.0007168630254454911, "learning_rate": 3.694952592873737e-05, "loss": 7.51268770545721e-05, "step": 28100 }, { "epoch": 3.656396255850234, "grad_norm": 0.001532200025394559, "learning_rate": 3.6921743822634184e-05, "loss": 9.932891465723515e-05, "step": 28125 }, { "epoch": 3.6596463858554342, "grad_norm": 0.0012276668567210436, "learning_rate": 3.689394264716344e-05, "loss": 8.382413536310196e-05, "step": 28150 }, { "epoch": 3.6628965158606346, "grad_norm": 0.0012731992173939943, "learning_rate": 3.686612244679436e-05, "loss": 7.727231830358506e-05, "step": 28175 }, { "epoch": 3.6661466458658345, "grad_norm": 0.0005765740061178803, "learning_rate": 3.6838283266026624e-05, "loss": 7.391300518065691e-05, "step": 28200 }, { "epoch": 3.669396775871035, "grad_norm": 0.0033778974320739508, "learning_rate": 3.6810425149390256e-05, "loss": 7.922178134322167e-05, "step": 28225 }, { "epoch": 3.672646905876235, "grad_norm": 0.0010250177001580596, "learning_rate": 3.678254814144557e-05, "loss": 8.13920982182026e-05, "step": 28250 }, { "epoch": 3.675897035881435, "grad_norm": 0.0009328502928838134, "learning_rate": 3.6754652286783094e-05, "loss": 8.174529299139976e-05, "step": 28275 }, { "epoch": 3.6791471658866355, "grad_norm": 0.0014251635875552893, "learning_rate": 3.6726737630023516e-05, "loss": 7.999413646757603e-05, "step": 28300 }, { "epoch": 3.6823972958918354, "grad_norm": 0.001929958933033049, "learning_rate": 3.669880421581759e-05, "loss": 7.84589722752571e-05, "step": 28325 }, { "epoch": 3.6856474258970358, "grad_norm": 0.001463289954699576, "learning_rate": 3.667085208884606e-05, "loss": 7.355836220085621e-05, "step": 28350 }, { "epoch": 3.688897555902236, "grad_norm": 0.003322105621919036, "learning_rate": 3.6642881293819645e-05, "loss": 8.263408206403255e-05, "step": 28375 }, { "epoch": 3.692147685907436, "grad_norm": 0.0007955364999361336, "learning_rate": 3.661489187547886e-05, "loss": 7.547639310359955e-05, "step": 28400 }, { "epoch": 3.6953978159126364, "grad_norm": 0.0010878805769607425, "learning_rate": 3.658688387859406e-05, "loss": 7.967890240252019e-05, "step": 28425 }, { "epoch": 3.6986479459178367, "grad_norm": 0.0026648633647710085, "learning_rate": 3.655885734796529e-05, "loss": 7.459086365997791e-05, "step": 28450 }, { "epoch": 3.7018980759230367, "grad_norm": 0.0019076071912422776, "learning_rate": 3.653081232842227e-05, "loss": 0.0001022458728402853, "step": 28475 }, { "epoch": 3.705148205928237, "grad_norm": 0.0012685914989560843, "learning_rate": 3.650274886482427e-05, "loss": 9.14644543081522e-05, "step": 28500 }, { "epoch": 3.7083983359334374, "grad_norm": 0.002095115603879094, "learning_rate": 3.6474667002060046e-05, "loss": 8.594589307904243e-05, "step": 28525 }, { "epoch": 3.7116484659386373, "grad_norm": 0.0011235276469960809, "learning_rate": 3.644656678504784e-05, "loss": 8.033460937440396e-05, "step": 28550 }, { "epoch": 3.7148985959438376, "grad_norm": 0.0038093829061836004, "learning_rate": 3.641844825873518e-05, "loss": 8.802492171525955e-05, "step": 28575 }, { "epoch": 3.718148725949038, "grad_norm": 0.0012695316690951586, "learning_rate": 3.6390311468098955e-05, "loss": 7.752737030386925e-05, "step": 28600 }, { "epoch": 3.721398855954238, "grad_norm": 0.0013351093512028456, "learning_rate": 3.636215645814521e-05, "loss": 7.955263368785382e-05, "step": 28625 }, { "epoch": 3.7246489859594383, "grad_norm": 0.001240126439370215, "learning_rate": 3.633398327390916e-05, "loss": 8.126482367515564e-05, "step": 28650 }, { "epoch": 3.7278991159646386, "grad_norm": 0.0029572658240795135, "learning_rate": 3.630579196045508e-05, "loss": 8.826878853142261e-05, "step": 28675 }, { "epoch": 3.7311492459698385, "grad_norm": 0.006022770423442125, "learning_rate": 3.6277582562876254e-05, "loss": 8.073903620243073e-05, "step": 28700 }, { "epoch": 3.734399375975039, "grad_norm": 0.0028404744807630777, "learning_rate": 3.624935512629489e-05, "loss": 9.142857976257801e-05, "step": 28725 }, { "epoch": 3.7376495059802393, "grad_norm": 0.0008018063381314278, "learning_rate": 3.622110969586205e-05, "loss": 7.36030237749219e-05, "step": 28750 }, { "epoch": 3.740899635985439, "grad_norm": 0.002236901316791773, "learning_rate": 3.6192846316757575e-05, "loss": 7.741847541183233e-05, "step": 28775 }, { "epoch": 3.7441497659906395, "grad_norm": 0.0010127603309229016, "learning_rate": 3.6164565034190004e-05, "loss": 7.822388783097267e-05, "step": 28800 }, { "epoch": 3.74739989599584, "grad_norm": 0.002036145655438304, "learning_rate": 3.613626589339653e-05, "loss": 7.977954111993313e-05, "step": 28825 }, { "epoch": 3.75065002600104, "grad_norm": 0.001071872073225677, "learning_rate": 3.610794893964291e-05, "loss": 8.531208150088787e-05, "step": 28850 }, { "epoch": 3.75390015600624, "grad_norm": 0.000600636238232255, "learning_rate": 3.607961421822339e-05, "loss": 8.655735291540623e-05, "step": 28875 }, { "epoch": 3.7571502860114405, "grad_norm": 0.0019876689184457064, "learning_rate": 3.605126177446064e-05, "loss": 7.865568622946739e-05, "step": 28900 }, { "epoch": 3.7604004160166404, "grad_norm": 0.0021251984871923923, "learning_rate": 3.602289165370567e-05, "loss": 7.581463549286127e-05, "step": 28925 }, { "epoch": 3.763650546021841, "grad_norm": 0.0008780233329162002, "learning_rate": 3.5994503901337765e-05, "loss": 8.923771791160107e-05, "step": 28950 }, { "epoch": 3.766900676027041, "grad_norm": 0.0008787247352302074, "learning_rate": 3.5966098562764423e-05, "loss": 8.166352286934852e-05, "step": 28975 }, { "epoch": 3.770150806032241, "grad_norm": 0.0011290276888757944, "learning_rate": 3.593767568342126e-05, "loss": 8.3440775051713e-05, "step": 29000 }, { "epoch": 3.7734009360374414, "grad_norm": 0.0011521888663992286, "learning_rate": 3.590923530877196e-05, "loss": 7.839494384825229e-05, "step": 29025 }, { "epoch": 3.776651066042642, "grad_norm": 0.001516430638730526, "learning_rate": 3.588077748430819e-05, "loss": 8.722963742911816e-05, "step": 29050 }, { "epoch": 3.7799011960478417, "grad_norm": 0.0006980146281421185, "learning_rate": 3.5852302255549516e-05, "loss": 7.413743995130062e-05, "step": 29075 }, { "epoch": 3.783151326053042, "grad_norm": 0.002265922026708722, "learning_rate": 3.582380966804336e-05, "loss": 8.241371251642704e-05, "step": 29100 }, { "epoch": 3.7864014560582424, "grad_norm": 0.0028364320751279593, "learning_rate": 3.5795299767364894e-05, "loss": 7.837379351258278e-05, "step": 29125 }, { "epoch": 3.7896515860634423, "grad_norm": 0.0009335685754194856, "learning_rate": 3.5766772599116996e-05, "loss": 9.143225848674774e-05, "step": 29150 }, { "epoch": 3.7929017160686427, "grad_norm": 0.0010557163041085005, "learning_rate": 3.5738228208930156e-05, "loss": 8.227193728089333e-05, "step": 29175 }, { "epoch": 3.796151846073843, "grad_norm": 0.0007759054424241185, "learning_rate": 3.5709666642462424e-05, "loss": 8.972428739070892e-05, "step": 29200 }, { "epoch": 3.799401976079043, "grad_norm": 0.0016463302308693528, "learning_rate": 3.568108794539931e-05, "loss": 7.660722360014916e-05, "step": 29225 }, { "epoch": 3.8026521060842433, "grad_norm": 0.0008348121191374958, "learning_rate": 3.565249216345373e-05, "loss": 7.436392828822136e-05, "step": 29250 }, { "epoch": 3.8059022360894437, "grad_norm": 0.0007473694276995957, "learning_rate": 3.562387934236593e-05, "loss": 6.69125560671091e-05, "step": 29275 }, { "epoch": 3.8091523660946436, "grad_norm": 0.0017282611224800348, "learning_rate": 3.5595249527903406e-05, "loss": 8.107975125312805e-05, "step": 29300 }, { "epoch": 3.812402496099844, "grad_norm": 0.0011013239854946733, "learning_rate": 3.556660276586084e-05, "loss": 8.663397282361985e-05, "step": 29325 }, { "epoch": 3.8156526261050443, "grad_norm": 0.0008493324276059866, "learning_rate": 3.553793910206003e-05, "loss": 8.318833075463771e-05, "step": 29350 }, { "epoch": 3.818902756110244, "grad_norm": 0.0006455110851675272, "learning_rate": 3.550925858234979e-05, "loss": 8.138788864016533e-05, "step": 29375 }, { "epoch": 3.8221528861154446, "grad_norm": 0.0015816809609532356, "learning_rate": 3.5480561252605906e-05, "loss": 7.323618512600661e-05, "step": 29400 }, { "epoch": 3.825403016120645, "grad_norm": 0.0008560042479075491, "learning_rate": 3.5451847158731054e-05, "loss": 7.628916762769222e-05, "step": 29425 }, { "epoch": 3.828653146125845, "grad_norm": 0.0011194800026714802, "learning_rate": 3.542311634665473e-05, "loss": 8.497213944792747e-05, "step": 29450 }, { "epoch": 3.831903276131045, "grad_norm": 0.0010577706852927804, "learning_rate": 3.539436886233316e-05, "loss": 7.002291735261679e-05, "step": 29475 }, { "epoch": 3.8351534061362456, "grad_norm": 0.003524581901729107, "learning_rate": 3.5365604751749245e-05, "loss": 8.350278250873088e-05, "step": 29500 }, { "epoch": 3.8384035361414455, "grad_norm": 0.0008983128936961293, "learning_rate": 3.533682406091248e-05, "loss": 8.222048170864583e-05, "step": 29525 }, { "epoch": 3.841653666146646, "grad_norm": 0.0009674655739217997, "learning_rate": 3.5308026835858874e-05, "loss": 7.983214221894741e-05, "step": 29550 }, { "epoch": 3.844903796151846, "grad_norm": 0.0007690418278798461, "learning_rate": 3.5279213122650894e-05, "loss": 8.400308899581433e-05, "step": 29575 }, { "epoch": 3.848153926157046, "grad_norm": 0.004106997977942228, "learning_rate": 3.525038296737738e-05, "loss": 8.842778392136097e-05, "step": 29600 }, { "epoch": 3.8514040561622465, "grad_norm": 0.0006912638782523572, "learning_rate": 3.522153641615345e-05, "loss": 7.831327617168427e-05, "step": 29625 }, { "epoch": 3.854654186167447, "grad_norm": 0.002170062391087413, "learning_rate": 3.5192673515120484e-05, "loss": 9.548653848469257e-05, "step": 29650 }, { "epoch": 3.8579043161726467, "grad_norm": 0.0013719502603635192, "learning_rate": 3.516379431044598e-05, "loss": 8.584879338741303e-05, "step": 29675 }, { "epoch": 3.861154446177847, "grad_norm": 0.0006119845784269273, "learning_rate": 3.513489884832354e-05, "loss": 8.014463819563388e-05, "step": 29700 }, { "epoch": 3.8644045761830474, "grad_norm": 0.0007846109219826758, "learning_rate": 3.510598717497276e-05, "loss": 7.363354787230491e-05, "step": 29725 }, { "epoch": 3.8676547061882474, "grad_norm": 0.0009278793004341424, "learning_rate": 3.507705933663916e-05, "loss": 8.178746327757835e-05, "step": 29750 }, { "epoch": 3.8709048361934477, "grad_norm": 0.0007604494458064437, "learning_rate": 3.504811537959414e-05, "loss": 7.301840465515851e-05, "step": 29775 }, { "epoch": 3.874154966198648, "grad_norm": 0.0009544129716232419, "learning_rate": 3.501915535013485e-05, "loss": 8.304501883685589e-05, "step": 29800 }, { "epoch": 3.877405096203848, "grad_norm": 0.0018528492655605078, "learning_rate": 3.4990179294584166e-05, "loss": 7.820844650268554e-05, "step": 29825 }, { "epoch": 3.8806552262090483, "grad_norm": 0.0015553454868495464, "learning_rate": 3.4961187259290606e-05, "loss": 0.00012987982481718063, "step": 29850 }, { "epoch": 3.8839053562142487, "grad_norm": 0.001331554027274251, "learning_rate": 3.493217929062823e-05, "loss": 0.00010472028516232968, "step": 29875 }, { "epoch": 3.8871554862194486, "grad_norm": 0.0014781735371798277, "learning_rate": 3.49031554349966e-05, "loss": 9.942575357854366e-05, "step": 29900 }, { "epoch": 3.890405616224649, "grad_norm": 0.0014309566468000412, "learning_rate": 3.4874115738820687e-05, "loss": 8.31100344657898e-05, "step": 29925 }, { "epoch": 3.8936557462298493, "grad_norm": 0.000907737819943577, "learning_rate": 3.484506024855078e-05, "loss": 8.806889876723289e-05, "step": 29950 }, { "epoch": 3.8969058762350492, "grad_norm": 0.0008521126001141965, "learning_rate": 3.481598901066247e-05, "loss": 7.747408468276262e-05, "step": 29975 }, { "epoch": 3.9001560062402496, "grad_norm": 0.0016188147710636258, "learning_rate": 3.4786902071656496e-05, "loss": 9.130414575338364e-05, "step": 30000 }, { "epoch": 3.90340613624545, "grad_norm": 0.0007106683333404362, "learning_rate": 3.475779947805874e-05, "loss": 7.427001837641e-05, "step": 30025 }, { "epoch": 3.90665626625065, "grad_norm": 0.002296186052262783, "learning_rate": 3.472868127642011e-05, "loss": 7.889092899858952e-05, "step": 30050 }, { "epoch": 3.9099063962558502, "grad_norm": 0.0019059969345107675, "learning_rate": 3.469954751331649e-05, "loss": 8.481208235025406e-05, "step": 30075 }, { "epoch": 3.9131565262610506, "grad_norm": 0.001279445830732584, "learning_rate": 3.467039823534864e-05, "loss": 7.35194655135274e-05, "step": 30100 }, { "epoch": 3.9164066562662505, "grad_norm": 0.0010255196830257773, "learning_rate": 3.4641233489142154e-05, "loss": 8.548852987587452e-05, "step": 30125 }, { "epoch": 3.919656786271451, "grad_norm": 0.0005961660644970834, "learning_rate": 3.4612053321347365e-05, "loss": 7.394544780254365e-05, "step": 30150 }, { "epoch": 3.9229069162766512, "grad_norm": 0.0008104104781523347, "learning_rate": 3.458285777863926e-05, "loss": 9.327253326773643e-05, "step": 30175 }, { "epoch": 3.926157046281851, "grad_norm": 0.0010921406792476773, "learning_rate": 3.455364690771743e-05, "loss": 7.931427098810673e-05, "step": 30200 }, { "epoch": 3.9294071762870515, "grad_norm": 0.0025246755685657263, "learning_rate": 3.4524420755305987e-05, "loss": 8.281460031867027e-05, "step": 30225 }, { "epoch": 3.932657306292252, "grad_norm": 0.000928930938243866, "learning_rate": 3.4495179368153476e-05, "loss": 7.46610714122653e-05, "step": 30250 }, { "epoch": 3.9359074362974518, "grad_norm": 0.0016174782067537308, "learning_rate": 3.446592279303282e-05, "loss": 8.274312131106853e-05, "step": 30275 }, { "epoch": 3.939157566302652, "grad_norm": 0.0006382741848938167, "learning_rate": 3.443665107674122e-05, "loss": 8.21766909211874e-05, "step": 30300 }, { "epoch": 3.9424076963078525, "grad_norm": 0.0024584117345511913, "learning_rate": 3.440736426610013e-05, "loss": 8.371950127184391e-05, "step": 30325 }, { "epoch": 3.9456578263130524, "grad_norm": 0.001819056924432516, "learning_rate": 3.43780624079551e-05, "loss": 8.248968981206418e-05, "step": 30350 }, { "epoch": 3.9489079563182528, "grad_norm": 0.001260749762877822, "learning_rate": 3.43487455491758e-05, "loss": 8.0506457015872e-05, "step": 30375 }, { "epoch": 3.952158086323453, "grad_norm": 0.0009403774747624993, "learning_rate": 3.431941373665585e-05, "loss": 8.048071525990962e-05, "step": 30400 }, { "epoch": 3.955408216328653, "grad_norm": 0.000907227979041636, "learning_rate": 3.429006701731282e-05, "loss": 7.522930856794119e-05, "step": 30425 }, { "epoch": 3.9586583463338534, "grad_norm": 0.0015064789913594723, "learning_rate": 3.426070543808811e-05, "loss": 7.221014704555272e-05, "step": 30450 }, { "epoch": 3.9619084763390537, "grad_norm": 0.0013556279009208083, "learning_rate": 3.42313290459469e-05, "loss": 7.65854911878705e-05, "step": 30475 }, { "epoch": 3.9651586063442537, "grad_norm": 0.000956767937168479, "learning_rate": 3.420193788787803e-05, "loss": 8.619870990514756e-05, "step": 30500 }, { "epoch": 3.968408736349454, "grad_norm": 0.0008600545697845519, "learning_rate": 3.4172532010894015e-05, "loss": 7.468197029083967e-05, "step": 30525 }, { "epoch": 3.9716588663546544, "grad_norm": 0.0005848151631653309, "learning_rate": 3.4143111462030864e-05, "loss": 7.99325667321682e-05, "step": 30550 }, { "epoch": 3.9749089963598543, "grad_norm": 0.0009903964819386601, "learning_rate": 3.411367628834808e-05, "loss": 6.98615750297904e-05, "step": 30575 }, { "epoch": 3.9781591263650546, "grad_norm": 0.000848200696054846, "learning_rate": 3.4084226536928547e-05, "loss": 7.596367970108986e-05, "step": 30600 }, { "epoch": 3.981409256370255, "grad_norm": 0.0005758678889833391, "learning_rate": 3.4054762254878476e-05, "loss": 7.448483258485794e-05, "step": 30625 }, { "epoch": 3.984659386375455, "grad_norm": 0.0008015372441150248, "learning_rate": 3.402528348932732e-05, "loss": 6.706314161419868e-05, "step": 30650 }, { "epoch": 3.9879095163806553, "grad_norm": 0.0004955961485393345, "learning_rate": 3.399579028742769e-05, "loss": 8.095981553196907e-05, "step": 30675 }, { "epoch": 3.9911596463858556, "grad_norm": 0.0010895032901316881, "learning_rate": 3.3966282696355304e-05, "loss": 8.056768216192722e-05, "step": 30700 }, { "epoch": 3.9944097763910555, "grad_norm": 0.002075731521472335, "learning_rate": 3.3936760763308884e-05, "loss": 7.773005869239569e-05, "step": 30725 }, { "epoch": 3.997659906396256, "grad_norm": 0.000709125364664942, "learning_rate": 3.390722453551008e-05, "loss": 7.511952426284552e-05, "step": 30750 }, { "epoch": 4.000910036401456, "grad_norm": 0.0020600375719368458, "learning_rate": 3.387767406020343e-05, "loss": 9.272047318518162e-05, "step": 30775 }, { "epoch": 4.004160166406656, "grad_norm": 0.001420293585397303, "learning_rate": 3.384810938465626e-05, "loss": 8.263667114078998e-05, "step": 30800 }, { "epoch": 4.007410296411856, "grad_norm": 0.0016311830841004848, "learning_rate": 3.38185305561586e-05, "loss": 8.060414344072341e-05, "step": 30825 }, { "epoch": 4.010660426417057, "grad_norm": 0.0004694838135037571, "learning_rate": 3.3788937622023116e-05, "loss": 7.489171810448169e-05, "step": 30850 }, { "epoch": 4.013910556422257, "grad_norm": 0.000784584553912282, "learning_rate": 3.375933062958505e-05, "loss": 7.076043169945478e-05, "step": 30875 }, { "epoch": 4.017160686427457, "grad_norm": 0.001142620574682951, "learning_rate": 3.372970962620212e-05, "loss": 7.493474520742894e-05, "step": 30900 }, { "epoch": 4.0204108164326575, "grad_norm": 0.0008813472231850028, "learning_rate": 3.370007465925446e-05, "loss": 7.569323293864728e-05, "step": 30925 }, { "epoch": 4.023660946437857, "grad_norm": 0.001360319321975112, "learning_rate": 3.367042577614454e-05, "loss": 7.24804401397705e-05, "step": 30950 }, { "epoch": 4.026911076443057, "grad_norm": 0.001041976734995842, "learning_rate": 3.3640763024297076e-05, "loss": 8.400308899581433e-05, "step": 30975 }, { "epoch": 4.030161206448258, "grad_norm": 0.0008661148604005575, "learning_rate": 3.3611086451158997e-05, "loss": 7.251626346260309e-05, "step": 31000 }, { "epoch": 4.033411336453458, "grad_norm": 0.0004520591755863279, "learning_rate": 3.35813961041993e-05, "loss": 6.694044917821884e-05, "step": 31025 }, { "epoch": 4.036661466458658, "grad_norm": 0.004920448176562786, "learning_rate": 3.3551692030909056e-05, "loss": 7.289521396160126e-05, "step": 31050 }, { "epoch": 4.036661466458658, "eval_loss": 0.0002873882476706058, "eval_runtime": 9.1029, "eval_samples_per_second": 549.274, "eval_steps_per_second": 4.394, "step": 31050 }, { "epoch": 4.036661466458658, "eval_holdout_avg_strict_f1": 0.15510844119056533, "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": 0.5479814692256784, "eval_holdout_nemotron_pii_strict_f1": 0.4819488257974063, "eval_holdout_open_pii_masking_500k_strict_f1": 0.3187874750166556, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.35747508305647835, "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": 4.039911596463859, "grad_norm": 0.0005819352227263153, "learning_rate": 3.352197427880126e-05, "loss": 6.840810645371676e-05, "step": 31075 }, { "epoch": 4.043161726469059, "grad_norm": 0.0009865663014352322, "learning_rate": 3.34922428954108e-05, "loss": 7.054964546114206e-05, "step": 31100 }, { "epoch": 4.046411856474259, "grad_norm": 0.0008192884852178395, "learning_rate": 3.346249792829437e-05, "loss": 7.376757450401783e-05, "step": 31125 }, { "epoch": 4.049661986479459, "grad_norm": 0.002754847053438425, "learning_rate": 3.343273942503039e-05, "loss": 7.94669147580862e-05, "step": 31150 }, { "epoch": 4.052912116484659, "grad_norm": 0.0017335007432848215, "learning_rate": 3.3402967433218926e-05, "loss": 8.13637301325798e-05, "step": 31175 }, { "epoch": 4.056162246489859, "grad_norm": 0.0018598970491439104, "learning_rate": 3.3373182000481614e-05, "loss": 7.311056368052959e-05, "step": 31200 }, { "epoch": 4.05941237649506, "grad_norm": 0.002089673187583685, "learning_rate": 3.3343383174461604e-05, "loss": 7.52323865890503e-05, "step": 31225 }, { "epoch": 4.06266250650026, "grad_norm": 0.001117464853450656, "learning_rate": 3.331357100282348e-05, "loss": 7.69305368885398e-05, "step": 31250 }, { "epoch": 4.06591263650546, "grad_norm": 0.0014985912712290883, "learning_rate": 3.3283745533253133e-05, "loss": 7.312553469091654e-05, "step": 31275 }, { "epoch": 4.069162766510661, "grad_norm": 0.0006476125563494861, "learning_rate": 3.325390681345777e-05, "loss": 7.213594857603311e-05, "step": 31300 }, { "epoch": 4.072412896515861, "grad_norm": 0.0011100006522610784, "learning_rate": 3.322405489116575e-05, "loss": 6.674138363450766e-05, "step": 31325 }, { "epoch": 4.0756630265210605, "grad_norm": 0.002162210876122117, "learning_rate": 3.319418981412659e-05, "loss": 7.710619829595088e-05, "step": 31350 }, { "epoch": 4.078913156526261, "grad_norm": 0.003410377074033022, "learning_rate": 3.3164311630110805e-05, "loss": 6.340686697512865e-05, "step": 31375 }, { "epoch": 4.082163286531461, "grad_norm": 0.006712953560054302, "learning_rate": 3.3134420386909926e-05, "loss": 6.907242350280285e-05, "step": 31400 }, { "epoch": 4.085413416536661, "grad_norm": 0.0009235776960849762, "learning_rate": 3.3104516132336326e-05, "loss": 6.928778719156981e-05, "step": 31425 }, { "epoch": 4.088663546541862, "grad_norm": 0.0004635594377759844, "learning_rate": 3.3074598914223224e-05, "loss": 7.534044329077005e-05, "step": 31450 }, { "epoch": 4.091913676547062, "grad_norm": 0.001596367103047669, "learning_rate": 3.304466878042456e-05, "loss": 6.67356513440609e-05, "step": 31475 }, { "epoch": 4.095163806552262, "grad_norm": 0.0021209949627518654, "learning_rate": 3.301472577881492e-05, "loss": 7.547556422650814e-05, "step": 31500 }, { "epoch": 4.0984139365574626, "grad_norm": 0.0012377817183732986, "learning_rate": 3.29847699572895e-05, "loss": 7.087042555212974e-05, "step": 31525 }, { "epoch": 4.1016640665626625, "grad_norm": 0.002419000957161188, "learning_rate": 3.295480136376399e-05, "loss": 8.605346083641052e-05, "step": 31550 }, { "epoch": 4.104914196567862, "grad_norm": 0.0013647719752043486, "learning_rate": 3.292482004617451e-05, "loss": 9.243563748896121e-05, "step": 31575 }, { "epoch": 4.108164326573063, "grad_norm": 0.0023896677885204554, "learning_rate": 3.289482605247752e-05, "loss": 7.718338165432214e-05, "step": 31600 }, { "epoch": 4.111414456578263, "grad_norm": 0.0005467410082928836, "learning_rate": 3.2864819430649775e-05, "loss": 7.932960987091065e-05, "step": 31625 }, { "epoch": 4.114664586583463, "grad_norm": 0.0010001611663028598, "learning_rate": 3.2834800228688216e-05, "loss": 8.005588315427304e-05, "step": 31650 }, { "epoch": 4.117914716588664, "grad_norm": 0.0011496787192299962, "learning_rate": 3.280476849460992e-05, "loss": 8.036359213292599e-05, "step": 31675 }, { "epoch": 4.121164846593864, "grad_norm": 0.0021631084382534027, "learning_rate": 3.2774724276452e-05, "loss": 6.893615238368512e-05, "step": 31700 }, { "epoch": 4.124414976599064, "grad_norm": 0.0013708403566852212, "learning_rate": 3.274466762227154e-05, "loss": 7.0151686668396e-05, "step": 31725 }, { "epoch": 4.1276651066042644, "grad_norm": 0.0006080871680751443, "learning_rate": 3.2714598580145505e-05, "loss": 6.49232231080532e-05, "step": 31750 }, { "epoch": 4.130915236609464, "grad_norm": 0.0016242151614278555, "learning_rate": 3.2684517198170705e-05, "loss": 7.715562824159861e-05, "step": 31775 }, { "epoch": 4.134165366614664, "grad_norm": 0.0009387978352606297, "learning_rate": 3.265442352446365e-05, "loss": 6.690743379294872e-05, "step": 31800 }, { "epoch": 4.137415496619865, "grad_norm": 0.001892568776383996, "learning_rate": 3.262431760716054e-05, "loss": 6.513912696391344e-05, "step": 31825 }, { "epoch": 4.140665626625065, "grad_norm": 0.0011885743588209152, "learning_rate": 3.259419949441714e-05, "loss": 7.222800515592098e-05, "step": 31850 }, { "epoch": 4.143915756630265, "grad_norm": 0.0007558875367976725, "learning_rate": 3.256406923440874e-05, "loss": 6.76156161352992e-05, "step": 31875 }, { "epoch": 4.147165886635466, "grad_norm": 0.002682020189240575, "learning_rate": 3.2533926875330056e-05, "loss": 7.038368377834558e-05, "step": 31900 }, { "epoch": 4.150416016640666, "grad_norm": 0.00114258227404207, "learning_rate": 3.250377246539515e-05, "loss": 7.856021635234356e-05, "step": 31925 }, { "epoch": 4.1536661466458655, "grad_norm": 0.0008295118459500372, "learning_rate": 3.247360605283735e-05, "loss": 6.718468386679888e-05, "step": 31950 }, { "epoch": 4.156916276651066, "grad_norm": 0.0007342782337218523, "learning_rate": 3.24434276859092e-05, "loss": 7.861767895519733e-05, "step": 31975 }, { "epoch": 4.160166406656266, "grad_norm": 0.0008441967074759305, "learning_rate": 3.2413237412882366e-05, "loss": 7.098865695297719e-05, "step": 32000 }, { "epoch": 4.163416536661466, "grad_norm": 0.0008892750483937562, "learning_rate": 3.2383035282047545e-05, "loss": 6.286534946411848e-05, "step": 32025 }, { "epoch": 4.166666666666667, "grad_norm": 0.0014242432080209255, "learning_rate": 3.2352821341714426e-05, "loss": 7.48683512210846e-05, "step": 32050 }, { "epoch": 4.169916796671867, "grad_norm": 0.0010998628567904234, "learning_rate": 3.232259564021156e-05, "loss": 7.685932330787183e-05, "step": 32075 }, { "epoch": 4.173166926677067, "grad_norm": 0.003284201957285404, "learning_rate": 3.229235822588631e-05, "loss": 7.155606523156167e-05, "step": 32100 }, { "epoch": 4.176417056682268, "grad_norm": 0.0009338667150586843, "learning_rate": 3.2262109147104803e-05, "loss": 7.295009680092335e-05, "step": 32125 }, { "epoch": 4.1796671866874675, "grad_norm": 0.002807129640132189, "learning_rate": 3.22318484522518e-05, "loss": 6.244916003197431e-05, "step": 32150 }, { "epoch": 4.182917316692667, "grad_norm": 0.0007692663930356503, "learning_rate": 3.2201576189730645e-05, "loss": 6.9206478074193e-05, "step": 32175 }, { "epoch": 4.186167446697868, "grad_norm": 0.002361661521717906, "learning_rate": 3.21712924079632e-05, "loss": 7.42186838760972e-05, "step": 32200 }, { "epoch": 4.189417576703068, "grad_norm": 0.0003642249503172934, "learning_rate": 3.214099715538973e-05, "loss": 6.872778758406639e-05, "step": 32225 }, { "epoch": 4.192667706708268, "grad_norm": 0.0018344545969739556, "learning_rate": 3.2110690480468865e-05, "loss": 8.386795409023762e-05, "step": 32250 }, { "epoch": 4.195917836713469, "grad_norm": 0.0021783558186143637, "learning_rate": 3.2080372431677496e-05, "loss": 7.376997731626034e-05, "step": 32275 }, { "epoch": 4.199167966718669, "grad_norm": 0.0008691028342582285, "learning_rate": 3.2050043057510716e-05, "loss": 7.056792266666889e-05, "step": 32300 }, { "epoch": 4.202418096723869, "grad_norm": 0.0006064671324566007, "learning_rate": 3.201970240648172e-05, "loss": 7.047259714454412e-05, "step": 32325 }, { "epoch": 4.2056682267290695, "grad_norm": 0.0034978974144905806, "learning_rate": 3.198935052712176e-05, "loss": 6.496015470474958e-05, "step": 32350 }, { "epoch": 4.208918356734269, "grad_norm": 0.009503806009888649, "learning_rate": 3.195898746798003e-05, "loss": 7.913276553153992e-05, "step": 32375 }, { "epoch": 4.212168486739469, "grad_norm": 0.0017762493807822466, "learning_rate": 3.192861327762362e-05, "loss": 8.03293101489544e-05, "step": 32400 }, { "epoch": 4.21541861674467, "grad_norm": 0.0011062795529142022, "learning_rate": 3.189822800463742e-05, "loss": 7.656308822333813e-05, "step": 32425 }, { "epoch": 4.21866874674987, "grad_norm": 0.0016560786170884967, "learning_rate": 3.186783169762403e-05, "loss": 6.770490668714046e-05, "step": 32450 }, { "epoch": 4.22191887675507, "grad_norm": 0.0002770320570562035, "learning_rate": 3.183742440520373e-05, "loss": 7.064026780426503e-05, "step": 32475 }, { "epoch": 4.225169006760271, "grad_norm": 0.0015412888024002314, "learning_rate": 3.180700617601436e-05, "loss": 0.00010730857029557228, "step": 32500 }, { "epoch": 4.228419136765471, "grad_norm": 0.001178896171040833, "learning_rate": 3.177657705871124e-05, "loss": 7.500328589230775e-05, "step": 32525 }, { "epoch": 4.231669266770671, "grad_norm": 0.0017002853564918041, "learning_rate": 3.174613710196713e-05, "loss": 8.516143076121807e-05, "step": 32550 }, { "epoch": 4.234919396775871, "grad_norm": 0.0011254933197051287, "learning_rate": 3.171568635447211e-05, "loss": 6.78203534334898e-05, "step": 32575 }, { "epoch": 4.238169526781071, "grad_norm": 0.0012039182474836707, "learning_rate": 3.1685224864933517e-05, "loss": 7.041552104055881e-05, "step": 32600 }, { "epoch": 4.241419656786271, "grad_norm": 0.0012506545754149556, "learning_rate": 3.1654752682075885e-05, "loss": 7.032568100839853e-05, "step": 32625 }, { "epoch": 4.244669786791472, "grad_norm": 0.0025638029910624027, "learning_rate": 3.162426985464085e-05, "loss": 7.057664450258017e-05, "step": 32650 }, { "epoch": 4.247919916796672, "grad_norm": 0.0018599980976432562, "learning_rate": 3.159377643138708e-05, "loss": 7.640935946255923e-05, "step": 32675 }, { "epoch": 4.251170046801872, "grad_norm": 0.0008776045870035887, "learning_rate": 3.156327246109016e-05, "loss": 7.54679273813963e-05, "step": 32700 }, { "epoch": 4.254420176807073, "grad_norm": 0.0009330817847512662, "learning_rate": 3.1532757992542575e-05, "loss": 6.080750841647387e-05, "step": 32725 }, { "epoch": 4.2576703068122725, "grad_norm": 0.0007624085410498083, "learning_rate": 3.15022330745536e-05, "loss": 6.751069333404302e-05, "step": 32750 }, { "epoch": 4.2609204368174725, "grad_norm": 0.0022527030669152737, "learning_rate": 3.147169775594923e-05, "loss": 8.357520215213299e-05, "step": 32775 }, { "epoch": 4.264170566822673, "grad_norm": 0.0011428833240643144, "learning_rate": 3.1441152085572054e-05, "loss": 7.788263726979494e-05, "step": 32800 }, { "epoch": 4.267420696827873, "grad_norm": 0.0018148204544559121, "learning_rate": 3.141059611228129e-05, "loss": 7.87031464278698e-05, "step": 32825 }, { "epoch": 4.270670826833073, "grad_norm": 0.0022266933228820562, "learning_rate": 3.138002988495257e-05, "loss": 7.555637508630752e-05, "step": 32850 }, { "epoch": 4.273920956838274, "grad_norm": 0.001447651069611311, "learning_rate": 3.134945345247797e-05, "loss": 7.402165327221156e-05, "step": 32875 }, { "epoch": 4.277171086843474, "grad_norm": 0.0005547028849832714, "learning_rate": 3.131886686376586e-05, "loss": 6.614552810788155e-05, "step": 32900 }, { "epoch": 4.280421216848674, "grad_norm": 0.0018264839891344309, "learning_rate": 3.128827016774088e-05, "loss": 8.111506700515747e-05, "step": 32925 }, { "epoch": 4.2836713468538745, "grad_norm": 0.0013230888871476054, "learning_rate": 3.125766341334382e-05, "loss": 7.36689753830433e-05, "step": 32950 }, { "epoch": 4.286921476859074, "grad_norm": 0.000849420961458236, "learning_rate": 3.122704664953158e-05, "loss": 6.798305548727512e-05, "step": 32975 }, { "epoch": 4.290171606864274, "grad_norm": 0.0010081349173560739, "learning_rate": 3.119641992527703e-05, "loss": 7.016693241894245e-05, "step": 33000 }, { "epoch": 4.293421736869475, "grad_norm": 0.0004972627502866089, "learning_rate": 3.116578328956903e-05, "loss": 7.320473436266184e-05, "step": 33025 }, { "epoch": 4.296671866874675, "grad_norm": 0.0014238492585718632, "learning_rate": 3.113513679141224e-05, "loss": 7.343586068600416e-05, "step": 33050 }, { "epoch": 4.299921996879875, "grad_norm": 0.0012314782943576574, "learning_rate": 3.1104480479827135e-05, "loss": 6.0565206222236153e-05, "step": 33075 }, { "epoch": 4.303172126885076, "grad_norm": 0.0009021238656714559, "learning_rate": 3.107381440384985e-05, "loss": 7.746850606054068e-05, "step": 33100 }, { "epoch": 4.306422256890276, "grad_norm": 0.0007674912340007722, "learning_rate": 3.104313861253217e-05, "loss": 7.687054574489593e-05, "step": 33125 }, { "epoch": 4.309672386895476, "grad_norm": 0.001065621618181467, "learning_rate": 3.10124531549414e-05, "loss": 7.722481153905391e-05, "step": 33150 }, { "epoch": 4.312922516900676, "grad_norm": 0.001404304406605661, "learning_rate": 3.0981758080160326e-05, "loss": 6.954610347747803e-05, "step": 33175 }, { "epoch": 4.316172646905876, "grad_norm": 0.0012276703491806984, "learning_rate": 3.0951053437287095e-05, "loss": 6.748052313923836e-05, "step": 33200 }, { "epoch": 4.319422776911076, "grad_norm": 0.0010297219268977642, "learning_rate": 3.092033927543518e-05, "loss": 6.8206787109375e-05, "step": 33225 }, { "epoch": 4.322672906916277, "grad_norm": 0.0009843558073043823, "learning_rate": 3.088961564373327e-05, "loss": 7.76890804991126e-05, "step": 33250 }, { "epoch": 4.325923036921477, "grad_norm": 0.0010191283654421568, "learning_rate": 3.085888259132519e-05, "loss": 7.24683701992035e-05, "step": 33275 }, { "epoch": 4.329173166926677, "grad_norm": 0.001333385705947876, "learning_rate": 3.082814016736985e-05, "loss": 6.133537739515305e-05, "step": 33300 }, { "epoch": 4.332423296931878, "grad_norm": 0.0014119314728304744, "learning_rate": 3.079738842104115e-05, "loss": 7.292392197996378e-05, "step": 33325 }, { "epoch": 4.335673426937078, "grad_norm": 0.0006599660264328122, "learning_rate": 3.076662740152789e-05, "loss": 6.633304990828038e-05, "step": 33350 }, { "epoch": 4.3389235569422775, "grad_norm": 0.001252208836376667, "learning_rate": 3.073585715803372e-05, "loss": 7.384988944977522e-05, "step": 33375 }, { "epoch": 4.342173686947478, "grad_norm": 0.000824449525680393, "learning_rate": 3.070507773977702e-05, "loss": 6.711858790367842e-05, "step": 33400 }, { "epoch": 4.345423816952678, "grad_norm": 0.0010422038612887263, "learning_rate": 3.067428919599087e-05, "loss": 6.458114832639694e-05, "step": 33425 }, { "epoch": 4.348673946957878, "grad_norm": 0.0016275184461846948, "learning_rate": 3.064349157592293e-05, "loss": 6.544307805597782e-05, "step": 33450 }, { "epoch": 4.351924076963079, "grad_norm": 0.0073488433845341206, "learning_rate": 3.061268492883539e-05, "loss": 8.463803678750991e-05, "step": 33475 }, { "epoch": 4.355174206968279, "grad_norm": 0.0004096855118405074, "learning_rate": 3.058186930400487e-05, "loss": 9.082852862775326e-05, "step": 33500 }, { "epoch": 4.358424336973479, "grad_norm": 0.003094717161729932, "learning_rate": 3.0551044750722346e-05, "loss": 8.269848302006722e-05, "step": 33525 }, { "epoch": 4.3616744669786796, "grad_norm": 0.0005997383268550038, "learning_rate": 3.05202113182931e-05, "loss": 6.518665701150894e-05, "step": 33550 }, { "epoch": 4.3649245969838795, "grad_norm": 0.0006943507469259202, "learning_rate": 3.048936905603658e-05, "loss": 6.297872867435217e-05, "step": 33575 }, { "epoch": 4.368174726989079, "grad_norm": 0.00043755234219133854, "learning_rate": 3.0458518013286392e-05, "loss": 7.018671371042729e-05, "step": 33600 }, { "epoch": 4.37142485699428, "grad_norm": 0.001621562521904707, "learning_rate": 3.0427658239390168e-05, "loss": 6.255894433706999e-05, "step": 33625 }, { "epoch": 4.37467498699948, "grad_norm": 0.003957741428166628, "learning_rate": 3.03967897837095e-05, "loss": 6.937870290130377e-05, "step": 33650 }, { "epoch": 4.37792511700468, "grad_norm": 0.00034722499549388885, "learning_rate": 3.0365912695619892e-05, "loss": 6.293841172009706e-05, "step": 33675 }, { "epoch": 4.38117524700988, "grad_norm": 0.0010667316382750869, "learning_rate": 3.033502702451063e-05, "loss": 6.356877274811268e-05, "step": 33700 }, { "epoch": 4.384425377015081, "grad_norm": 0.0008346835384145379, "learning_rate": 3.030413281978475e-05, "loss": 6.956177297979593e-05, "step": 33725 }, { "epoch": 4.387675507020281, "grad_norm": 0.0007427301025018096, "learning_rate": 3.0273230130858908e-05, "loss": 8.246550336480141e-05, "step": 33750 }, { "epoch": 4.3909256370254806, "grad_norm": 0.0011975241359323263, "learning_rate": 3.0242319007163373e-05, "loss": 7.534813601523638e-05, "step": 33775 }, { "epoch": 4.394175767030681, "grad_norm": 0.0007207951857708395, "learning_rate": 3.021139949814187e-05, "loss": 6.338434293866157e-05, "step": 33800 }, { "epoch": 4.397425897035881, "grad_norm": 0.0011049676686525345, "learning_rate": 3.0180471653251552e-05, "loss": 6.375552155077458e-05, "step": 33825 }, { "epoch": 4.400676027041081, "grad_norm": 0.011930102482438087, "learning_rate": 3.01495355219629e-05, "loss": 6.643995642662048e-05, "step": 33850 }, { "epoch": 4.403926157046282, "grad_norm": 0.0005073669017292559, "learning_rate": 3.0118591153759664e-05, "loss": 7.037329953163863e-05, "step": 33875 }, { "epoch": 4.407176287051482, "grad_norm": 0.0015900670550763607, "learning_rate": 3.0087638598138747e-05, "loss": 7.197164464741945e-05, "step": 33900 }, { "epoch": 4.410426417056682, "grad_norm": 0.0004043809312861413, "learning_rate": 3.0056677904610164e-05, "loss": 6.28564553335309e-05, "step": 33925 }, { "epoch": 4.413676547061883, "grad_norm": 0.00050264602759853, "learning_rate": 3.0025709122696945e-05, "loss": 6.819895934313535e-05, "step": 33950 }, { "epoch": 4.4169266770670825, "grad_norm": 0.0009463509195484221, "learning_rate": 2.999473230193505e-05, "loss": 6.800481118261814e-05, "step": 33975 }, { "epoch": 4.420176807072282, "grad_norm": 0.0005180768202990294, "learning_rate": 2.99637474918733e-05, "loss": 5.902091506868601e-05, "step": 34000 }, { "epoch": 4.423426937077483, "grad_norm": 0.0006364054861478508, "learning_rate": 2.993275474207331e-05, "loss": 6.439710967242717e-05, "step": 34025 }, { "epoch": 4.426677067082683, "grad_norm": 0.002112042624503374, "learning_rate": 2.990175410210937e-05, "loss": 6.835741922259331e-05, "step": 34050 }, { "epoch": 4.429927197087883, "grad_norm": 0.0008045727154240012, "learning_rate": 2.9870745621568408e-05, "loss": 7.046137936413288e-05, "step": 34075 }, { "epoch": 4.433177327093084, "grad_norm": 0.0006316539365798235, "learning_rate": 2.9839729350049895e-05, "loss": 5.8857793919742105e-05, "step": 34100 }, { "epoch": 4.436427457098284, "grad_norm": 0.0010720092104747891, "learning_rate": 2.9808705337165742e-05, "loss": 6.762383040040732e-05, "step": 34125 }, { "epoch": 4.439677587103484, "grad_norm": 0.000524127040989697, "learning_rate": 2.9777673632540275e-05, "loss": 6.676311139017344e-05, "step": 34150 }, { "epoch": 4.4429277171086845, "grad_norm": 0.0004570476885419339, "learning_rate": 2.9746634285810103e-05, "loss": 6.116405129432678e-05, "step": 34175 }, { "epoch": 4.446177847113884, "grad_norm": 0.0008246056968346238, "learning_rate": 2.9715587346624058e-05, "loss": 5.428229458630085e-05, "step": 34200 }, { "epoch": 4.449427977119084, "grad_norm": 0.0014650013763457537, "learning_rate": 2.9684532864643122e-05, "loss": 6.027763243764639e-05, "step": 34225 }, { "epoch": 4.452678107124285, "grad_norm": 0.0004909266135655344, "learning_rate": 2.965347088954034e-05, "loss": 5.618277005851269e-05, "step": 34250 }, { "epoch": 4.455928237129485, "grad_norm": 0.0013517390470951796, "learning_rate": 2.962240147100075e-05, "loss": 6.547479424625635e-05, "step": 34275 }, { "epoch": 4.459178367134685, "grad_norm": 0.002162858145311475, "learning_rate": 2.9591324658721282e-05, "loss": 7.535898592323065e-05, "step": 34300 }, { "epoch": 4.462428497139886, "grad_norm": 0.0018275585025548935, "learning_rate": 2.9560240502410706e-05, "loss": 8.12382996082306e-05, "step": 34325 }, { "epoch": 4.465678627145086, "grad_norm": 0.00240133935585618, "learning_rate": 2.9529149051789535e-05, "loss": 6.386293098330498e-05, "step": 34350 }, { "epoch": 4.468928757150286, "grad_norm": 0.0009532092954032123, "learning_rate": 2.9498050356589935e-05, "loss": 6.744758691638708e-05, "step": 34375 }, { "epoch": 4.472178887155486, "grad_norm": 0.002347285859286785, "learning_rate": 2.946694446655569e-05, "loss": 7.080703042447567e-05, "step": 34400 }, { "epoch": 4.475429017160686, "grad_norm": 0.0014698836021125317, "learning_rate": 2.9435831431442075e-05, "loss": 7.233583834022283e-05, "step": 34425 }, { "epoch": 4.478679147165886, "grad_norm": 0.0011077711824327707, "learning_rate": 2.940471130101578e-05, "loss": 6.786911748349667e-05, "step": 34450 }, { "epoch": 4.481929277171087, "grad_norm": 0.0007867019157856703, "learning_rate": 2.937358412505487e-05, "loss": 6.875400431454182e-05, "step": 34475 }, { "epoch": 4.485179407176287, "grad_norm": 0.00043417932465672493, "learning_rate": 2.9342449953348667e-05, "loss": 5.524996668100357e-05, "step": 34500 }, { "epoch": 4.485179407176287, "eval_loss": 0.0002626277564559132, "eval_runtime": 8.8241, "eval_samples_per_second": 566.63, "eval_steps_per_second": 4.533, "step": 34500 }, { "epoch": 4.485179407176287, "eval_holdout_avg_strict_f1": 0.1710718043093922, "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": 0.5921034900956744, "eval_holdout_nemotron_pii_strict_f1": 0.5540787073234298, "eval_holdout_open_pii_masking_500k_strict_f1": 0.36469755925008845, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.37091009073412157, "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": 4.488429537181487, "grad_norm": 0.0050007072277367115, "learning_rate": 2.931130883569768e-05, "loss": 7.213897537440061e-05, "step": 34525 }, { "epoch": 4.491679667186688, "grad_norm": 0.0013735825195908546, "learning_rate": 2.9280160821913543e-05, "loss": 6.763716228306294e-05, "step": 34550 }, { "epoch": 4.494929797191888, "grad_norm": 0.002128597116097808, "learning_rate": 2.92490059618189e-05, "loss": 7.539727259427309e-05, "step": 34575 }, { "epoch": 4.4981799271970875, "grad_norm": 0.0019502391805872321, "learning_rate": 2.9217844305247368e-05, "loss": 7.264959625899792e-05, "step": 34600 }, { "epoch": 4.501430057202288, "grad_norm": 0.0012415129458531737, "learning_rate": 2.918667590204341e-05, "loss": 6.482439581304788e-05, "step": 34625 }, { "epoch": 4.504680187207488, "grad_norm": 0.001397572923451662, "learning_rate": 2.9155500802062297e-05, "loss": 6.341881584376097e-05, "step": 34650 }, { "epoch": 4.507930317212688, "grad_norm": 0.0011171397054567933, "learning_rate": 2.9124319055170014e-05, "loss": 6.575839594006538e-05, "step": 34675 }, { "epoch": 4.511180447217889, "grad_norm": 0.0010864014038816094, "learning_rate": 2.909313071124317e-05, "loss": 8.120859973132611e-05, "step": 34700 }, { "epoch": 4.514430577223089, "grad_norm": 0.0013123005628585815, "learning_rate": 2.9061935820168934e-05, "loss": 6.464146543294191e-05, "step": 34725 }, { "epoch": 4.517680707228289, "grad_norm": 0.0012272520689293742, "learning_rate": 2.903073443184494e-05, "loss": 7.06417765468359e-05, "step": 34750 }, { "epoch": 4.5209308372334895, "grad_norm": 0.002135935937985778, "learning_rate": 2.8999526596179217e-05, "loss": 6.810509134083987e-05, "step": 34775 }, { "epoch": 4.5241809672386895, "grad_norm": 0.0015886285109445453, "learning_rate": 2.89683123630901e-05, "loss": 6.667341105639934e-05, "step": 34800 }, { "epoch": 4.527431097243889, "grad_norm": 0.0007710204226896167, "learning_rate": 2.8937091782506177e-05, "loss": 6.692296825349331e-05, "step": 34825 }, { "epoch": 4.53068122724909, "grad_norm": 0.00315717700868845, "learning_rate": 2.8905864904366177e-05, "loss": 7.040122523903847e-05, "step": 34850 }, { "epoch": 4.53393135725429, "grad_norm": 0.0006826577591709793, "learning_rate": 2.8874631778618887e-05, "loss": 6.727957632392645e-05, "step": 34875 }, { "epoch": 4.53718148725949, "grad_norm": 0.00047710430226288736, "learning_rate": 2.8843392455223116e-05, "loss": 6.639788392931223e-05, "step": 34900 }, { "epoch": 4.540431617264691, "grad_norm": 0.0011190577642992139, "learning_rate": 2.881214698414757e-05, "loss": 5.233802367001772e-05, "step": 34925 }, { "epoch": 4.543681747269891, "grad_norm": 0.0007910833810456097, "learning_rate": 2.8780895415370785e-05, "loss": 7.0255515165627e-05, "step": 34950 }, { "epoch": 4.546931877275091, "grad_norm": 0.001661584130488336, "learning_rate": 2.8749637798881057e-05, "loss": 6.544696632772684e-05, "step": 34975 }, { "epoch": 4.550182007280291, "grad_norm": 0.0009588557877577841, "learning_rate": 2.8718374184676362e-05, "loss": 6.619788240641355e-05, "step": 35000 }, { "epoch": 4.553432137285491, "grad_norm": 0.0016610921593382955, "learning_rate": 2.8687104622764253e-05, "loss": 6.836332846432924e-05, "step": 35025 }, { "epoch": 4.556682267290691, "grad_norm": 0.0011575801763683558, "learning_rate": 2.8655829163161812e-05, "loss": 5.8920616284012793e-05, "step": 35050 }, { "epoch": 4.559932397295892, "grad_norm": 0.002647529123350978, "learning_rate": 2.8624547855895557e-05, "loss": 7.262295112013817e-05, "step": 35075 }, { "epoch": 4.563182527301092, "grad_norm": 0.0004154951893724501, "learning_rate": 2.8593260751001332e-05, "loss": 6.549081299453974e-05, "step": 35100 }, { "epoch": 4.566432657306292, "grad_norm": 0.0008943718858063221, "learning_rate": 2.856196789852429e-05, "loss": 7.400969974696636e-05, "step": 35125 }, { "epoch": 4.569682787311493, "grad_norm": 0.0010560338851064444, "learning_rate": 2.8530669348518753e-05, "loss": 6.197745446115733e-05, "step": 35150 }, { "epoch": 4.572932917316693, "grad_norm": 0.005451032426208258, "learning_rate": 2.8499365151048168e-05, "loss": 6.321805529296398e-05, "step": 35175 }, { "epoch": 4.5761830473218925, "grad_norm": 0.002585024805739522, "learning_rate": 2.8468055356185018e-05, "loss": 7.65845738351345e-05, "step": 35200 }, { "epoch": 4.579433177327093, "grad_norm": 0.000924839754588902, "learning_rate": 2.8436740014010722e-05, "loss": 6.654016673564911e-05, "step": 35225 }, { "epoch": 4.582683307332293, "grad_norm": 0.0006979155587032437, "learning_rate": 2.8405419174615594e-05, "loss": 6.627691444009542e-05, "step": 35250 }, { "epoch": 4.585933437337493, "grad_norm": 0.002353587420657277, "learning_rate": 2.8374092888098725e-05, "loss": 6.443125195801258e-05, "step": 35275 }, { "epoch": 4.589183567342694, "grad_norm": 0.002653116127476096, "learning_rate": 2.834276120456793e-05, "loss": 7.338677067309619e-05, "step": 35300 }, { "epoch": 4.592433697347894, "grad_norm": 0.0015000364510342479, "learning_rate": 2.8311424174139644e-05, "loss": 7.603114936500787e-05, "step": 35325 }, { "epoch": 4.595683827353094, "grad_norm": 0.00032468876452185214, "learning_rate": 2.828008184693886e-05, "loss": 5.6803682819008825e-05, "step": 35350 }, { "epoch": 4.598933957358295, "grad_norm": 0.0008008645963855088, "learning_rate": 2.824873427309907e-05, "loss": 5.6365733034908774e-05, "step": 35375 }, { "epoch": 4.6021840873634945, "grad_norm": 0.0010024989023804665, "learning_rate": 2.8217381502762108e-05, "loss": 6.573958322405815e-05, "step": 35400 }, { "epoch": 4.605434217368694, "grad_norm": 0.0009154781000688672, "learning_rate": 2.8186023586078146e-05, "loss": 6.708182394504547e-05, "step": 35425 }, { "epoch": 4.608684347373895, "grad_norm": 0.0007549818838015199, "learning_rate": 2.8154660573205604e-05, "loss": 6.994929630309343e-05, "step": 35450 }, { "epoch": 4.611934477379095, "grad_norm": 0.0004310717049520463, "learning_rate": 2.8123292514311027e-05, "loss": 6.132998969405889e-05, "step": 35475 }, { "epoch": 4.615184607384295, "grad_norm": 0.0003819706616923213, "learning_rate": 2.8091919459569045e-05, "loss": 5.5117150768637654e-05, "step": 35500 }, { "epoch": 4.618434737389496, "grad_norm": 0.0008963666623458266, "learning_rate": 2.8060541459162272e-05, "loss": 7.339431438595056e-05, "step": 35525 }, { "epoch": 4.621684867394696, "grad_norm": 0.0016095273895189166, "learning_rate": 2.8029158563281234e-05, "loss": 6.601024884730577e-05, "step": 35550 }, { "epoch": 4.624934997399896, "grad_norm": 0.0007765444461256266, "learning_rate": 2.7997770822124296e-05, "loss": 6.596875842660665e-05, "step": 35575 }, { "epoch": 4.6281851274050965, "grad_norm": 0.0010687289759516716, "learning_rate": 2.796637828589757e-05, "loss": 6.627935450524091e-05, "step": 35600 }, { "epoch": 4.631435257410296, "grad_norm": 0.0007167328731156886, "learning_rate": 2.793498100481483e-05, "loss": 6.437895819544793e-05, "step": 35625 }, { "epoch": 4.634685387415496, "grad_norm": 0.0025304120499640703, "learning_rate": 2.7903579029097443e-05, "loss": 6.663076113909483e-05, "step": 35650 }, { "epoch": 4.637935517420697, "grad_norm": 0.0013128159334883094, "learning_rate": 2.7872172408974294e-05, "loss": 6.157911848276853e-05, "step": 35675 }, { "epoch": 4.641185647425897, "grad_norm": 0.0005178859573788941, "learning_rate": 2.7840761194681686e-05, "loss": 6.613705772906542e-05, "step": 35700 }, { "epoch": 4.644435777431097, "grad_norm": 0.0010814396664500237, "learning_rate": 2.780934543646327e-05, "loss": 6.667557172477246e-05, "step": 35725 }, { "epoch": 4.647685907436298, "grad_norm": 0.0010666303569450974, "learning_rate": 2.7777925184569976e-05, "loss": 6.853212136775255e-05, "step": 35750 }, { "epoch": 4.650936037441498, "grad_norm": 0.0008469424210488796, "learning_rate": 2.7746500489259908e-05, "loss": 7.454086095094681e-05, "step": 35775 }, { "epoch": 4.6541861674466976, "grad_norm": 0.0033673078287392855, "learning_rate": 2.7715071400798297e-05, "loss": 5.8289198204874995e-05, "step": 35800 }, { "epoch": 4.657436297451898, "grad_norm": 0.0016550614964216948, "learning_rate": 2.768363796945739e-05, "loss": 6.524975877255202e-05, "step": 35825 }, { "epoch": 4.660686427457098, "grad_norm": 0.0011834707111120224, "learning_rate": 2.765220024551636e-05, "loss": 6.959627848118543e-05, "step": 35850 }, { "epoch": 4.663936557462298, "grad_norm": 0.0009146461961790919, "learning_rate": 2.7620758279261294e-05, "loss": 6.776462309062482e-05, "step": 35875 }, { "epoch": 4.667186687467499, "grad_norm": 0.0018492500530555844, "learning_rate": 2.7589312120985012e-05, "loss": 7.188308052718639e-05, "step": 35900 }, { "epoch": 4.670436817472699, "grad_norm": 0.0024739722721278667, "learning_rate": 2.7557861820987073e-05, "loss": 7.81868677586317e-05, "step": 35925 }, { "epoch": 4.673686947477899, "grad_norm": 0.000834846927318722, "learning_rate": 2.7526407429573657e-05, "loss": 7.363265380263329e-05, "step": 35950 }, { "epoch": 4.6769370774831, "grad_norm": 0.0010680978884920478, "learning_rate": 2.749494899705748e-05, "loss": 6.671987473964691e-05, "step": 35975 }, { "epoch": 4.6801872074882995, "grad_norm": 0.00080632115714252, "learning_rate": 2.7463486573757724e-05, "loss": 6.838168017566204e-05, "step": 36000 }, { "epoch": 4.683437337493499, "grad_norm": 0.0010747809428721666, "learning_rate": 2.7432020209999955e-05, "loss": 7.027352228760719e-05, "step": 36025 }, { "epoch": 4.6866874674987, "grad_norm": 0.00073421181878075, "learning_rate": 2.7400549956116046e-05, "loss": 6.565522402524948e-05, "step": 36050 }, { "epoch": 4.6899375975039, "grad_norm": 0.0006620884523727, "learning_rate": 2.7369075862444082e-05, "loss": 6.663437467068434e-05, "step": 36075 }, { "epoch": 4.6931877275091, "grad_norm": 0.0006301242392510176, "learning_rate": 2.7337597979328305e-05, "loss": 7.043350022286177e-05, "step": 36100 }, { "epoch": 4.696437857514301, "grad_norm": 0.0007874320144765079, "learning_rate": 2.730611635711901e-05, "loss": 6.838295143097639e-05, "step": 36125 }, { "epoch": 4.699687987519501, "grad_norm": 0.006593848112970591, "learning_rate": 2.727463104617247e-05, "loss": 6.305585149675608e-05, "step": 36150 }, { "epoch": 4.702938117524701, "grad_norm": 0.001832361682318151, "learning_rate": 2.7243142096850867e-05, "loss": 6.419236306101083e-05, "step": 36175 }, { "epoch": 4.7061882475299015, "grad_norm": 0.0014722492778673768, "learning_rate": 2.721164955952218e-05, "loss": 6.906359922140837e-05, "step": 36200 }, { "epoch": 4.709438377535101, "grad_norm": 0.0010777778225019574, "learning_rate": 2.7180153484560162e-05, "loss": 6.267963908612728e-05, "step": 36225 }, { "epoch": 4.712688507540301, "grad_norm": 0.003285577753558755, "learning_rate": 2.7148653922344203e-05, "loss": 7.048216182738543e-05, "step": 36250 }, { "epoch": 4.715938637545502, "grad_norm": 0.002132392954081297, "learning_rate": 2.7117150923259277e-05, "loss": 7.771116215735674e-05, "step": 36275 }, { "epoch": 4.719188767550702, "grad_norm": 0.0025605186820030212, "learning_rate": 2.7085644537695848e-05, "loss": 6.870559882372617e-05, "step": 36300 }, { "epoch": 4.722438897555902, "grad_norm": 0.0007586965220980346, "learning_rate": 2.705413481604981e-05, "loss": 6.357957143336534e-05, "step": 36325 }, { "epoch": 4.725689027561103, "grad_norm": 0.001235252944752574, "learning_rate": 2.7022621808722377e-05, "loss": 6.0271150432527064e-05, "step": 36350 }, { "epoch": 4.728939157566303, "grad_norm": 0.001036791829392314, "learning_rate": 2.6991105566120027e-05, "loss": 6.458689924329519e-05, "step": 36375 }, { "epoch": 4.732189287571503, "grad_norm": 0.0005155526450835168, "learning_rate": 2.6959586138654418e-05, "loss": 5.817084107547998e-05, "step": 36400 }, { "epoch": 4.735439417576703, "grad_norm": 0.002390142995864153, "learning_rate": 2.69280635767423e-05, "loss": 7.033259142190218e-05, "step": 36425 }, { "epoch": 4.738689547581903, "grad_norm": 0.002106266561895609, "learning_rate": 2.689653793080543e-05, "loss": 6.17976114153862e-05, "step": 36450 }, { "epoch": 4.741939677587103, "grad_norm": 0.0012684621615335345, "learning_rate": 2.6865009251270507e-05, "loss": 5.90147590264678e-05, "step": 36475 }, { "epoch": 4.745189807592304, "grad_norm": 0.0013750838115811348, "learning_rate": 2.6833477588569067e-05, "loss": 6.673329044133424e-05, "step": 36500 }, { "epoch": 4.748439937597504, "grad_norm": 0.002269568620249629, "learning_rate": 2.6801942993137437e-05, "loss": 7.370650302618742e-05, "step": 36525 }, { "epoch": 4.751690067602704, "grad_norm": 0.000475414126412943, "learning_rate": 2.6770405515416625e-05, "loss": 6.08504144474864e-05, "step": 36550 }, { "epoch": 4.754940197607905, "grad_norm": 0.002138950163498521, "learning_rate": 2.673886520585225e-05, "loss": 7.143612019717693e-05, "step": 36575 }, { "epoch": 4.758190327613105, "grad_norm": 0.00072441779775545, "learning_rate": 2.6707322114894457e-05, "loss": 6.221023388206958e-05, "step": 36600 }, { "epoch": 4.7614404576183045, "grad_norm": 0.000739539333153516, "learning_rate": 2.6675776292997852e-05, "loss": 6.52548624202609e-05, "step": 36625 }, { "epoch": 4.764690587623505, "grad_norm": 0.0007322261808440089, "learning_rate": 2.6644227790621395e-05, "loss": 6.215126253664494e-05, "step": 36650 }, { "epoch": 4.767940717628705, "grad_norm": 0.002976820105686784, "learning_rate": 2.6612676658228346e-05, "loss": 7.096732966601848e-05, "step": 36675 }, { "epoch": 4.771190847633905, "grad_norm": 0.000959955679718405, "learning_rate": 2.6581122946286163e-05, "loss": 6.370789837092162e-05, "step": 36700 }, { "epoch": 4.774440977639106, "grad_norm": 0.0012413421645760536, "learning_rate": 2.6549566705266433e-05, "loss": 7.569785695523024e-05, "step": 36725 }, { "epoch": 4.777691107644306, "grad_norm": 0.00044488467392511666, "learning_rate": 2.6518007985644778e-05, "loss": 7.349029649049043e-05, "step": 36750 }, { "epoch": 4.780941237649506, "grad_norm": 0.0008330970304086804, "learning_rate": 2.6486446837900814e-05, "loss": 6.018154788762331e-05, "step": 36775 }, { "epoch": 4.7841913676547065, "grad_norm": 0.0027245476376265287, "learning_rate": 2.6454883312518013e-05, "loss": 6.396370939910411e-05, "step": 36800 }, { "epoch": 4.7874414976599065, "grad_norm": 0.0008515659719705582, "learning_rate": 2.6423317459983666e-05, "loss": 5.9261946007609366e-05, "step": 36825 }, { "epoch": 4.790691627665106, "grad_norm": 0.0006951336399652064, "learning_rate": 2.6391749330788762e-05, "loss": 5.30688650906086e-05, "step": 36850 }, { "epoch": 4.793941757670307, "grad_norm": 0.0023076869547367096, "learning_rate": 2.636017897542797e-05, "loss": 6.475947331637144e-05, "step": 36875 }, { "epoch": 4.797191887675507, "grad_norm": 0.001707522664219141, "learning_rate": 2.632860644439948e-05, "loss": 6.538453511893749e-05, "step": 36900 }, { "epoch": 4.800442017680707, "grad_norm": 0.0012062370078638196, "learning_rate": 2.6297031788205002e-05, "loss": 6.058998871594667e-05, "step": 36925 }, { "epoch": 4.803692147685908, "grad_norm": 0.005782189778983593, "learning_rate": 2.6265455057349604e-05, "loss": 7.403844967484474e-05, "step": 36950 }, { "epoch": 4.806942277691108, "grad_norm": 0.0010345455957576632, "learning_rate": 2.62338763023417e-05, "loss": 6.92962808534503e-05, "step": 36975 }, { "epoch": 4.810192407696308, "grad_norm": 0.001299795345403254, "learning_rate": 2.6202295573692936e-05, "loss": 7.124431431293488e-05, "step": 37000 }, { "epoch": 4.813442537701508, "grad_norm": 0.0022029755637049675, "learning_rate": 2.617071292191811e-05, "loss": 6.28599664196372e-05, "step": 37025 }, { "epoch": 4.816692667706708, "grad_norm": 0.0007655113004148006, "learning_rate": 2.6139128397535105e-05, "loss": 6.371065508574247e-05, "step": 37050 }, { "epoch": 4.819942797711908, "grad_norm": 0.0018312166212126613, "learning_rate": 2.61075420510648e-05, "loss": 6.410414353013039e-05, "step": 37075 }, { "epoch": 4.823192927717109, "grad_norm": 0.0011137286201119423, "learning_rate": 2.607595393303096e-05, "loss": 6.716392002999783e-05, "step": 37100 }, { "epoch": 4.826443057722309, "grad_norm": 0.0023307502269744873, "learning_rate": 2.6044364093960232e-05, "loss": 7.157537154853344e-05, "step": 37125 }, { "epoch": 4.829693187727509, "grad_norm": 0.0013290181523188949, "learning_rate": 2.6012772584381972e-05, "loss": 6.385131273418665e-05, "step": 37150 }, { "epoch": 4.83294331773271, "grad_norm": 0.0008490880136378109, "learning_rate": 2.598117945482823e-05, "loss": 7.067201659083366e-05, "step": 37175 }, { "epoch": 4.83619344773791, "grad_norm": 0.0015049075009301305, "learning_rate": 2.594958475583365e-05, "loss": 0.0001306710485368967, "step": 37200 }, { "epoch": 4.8394435777431095, "grad_norm": 0.0013614078052341938, "learning_rate": 2.5917988537935374e-05, "loss": 0.00011650861240923405, "step": 37225 }, { "epoch": 4.84269370774831, "grad_norm": 0.001129299751482904, "learning_rate": 2.5886390851672983e-05, "loss": 8.235435001552105e-05, "step": 37250 }, { "epoch": 4.84594383775351, "grad_norm": 0.00264424504712224, "learning_rate": 2.5854791747588393e-05, "loss": 9.034343995153904e-05, "step": 37275 }, { "epoch": 4.84919396775871, "grad_norm": 0.0023385502863675356, "learning_rate": 2.5823191276225812e-05, "loss": 7.238839752972126e-05, "step": 37300 }, { "epoch": 4.852444097763911, "grad_norm": 0.0012885435717180371, "learning_rate": 2.579158948813161e-05, "loss": 8.416576310992241e-05, "step": 37325 }, { "epoch": 4.855694227769111, "grad_norm": 0.0014486487489193678, "learning_rate": 2.5759986433854283e-05, "loss": 7.933174259960651e-05, "step": 37350 }, { "epoch": 4.858944357774311, "grad_norm": 0.0010103452950716019, "learning_rate": 2.5728382163944338e-05, "loss": 6.741130258888007e-05, "step": 37375 }, { "epoch": 4.862194487779512, "grad_norm": 0.0005659220041707158, "learning_rate": 2.569677672895423e-05, "loss": 6.615045480430126e-05, "step": 37400 }, { "epoch": 4.8654446177847115, "grad_norm": 0.0006711652386002243, "learning_rate": 2.566517017943828e-05, "loss": 8.213939145207405e-05, "step": 37425 }, { "epoch": 4.868694747789911, "grad_norm": 0.0005519745172932744, "learning_rate": 2.5633562565952596e-05, "loss": 7.343144156038761e-05, "step": 37450 }, { "epoch": 4.871944877795112, "grad_norm": 0.0009449325152672827, "learning_rate": 2.560195393905498e-05, "loss": 7.98861775547266e-05, "step": 37475 }, { "epoch": 4.875195007800312, "grad_norm": 0.0012089458759874105, "learning_rate": 2.5570344349304853e-05, "loss": 7.317102514207363e-05, "step": 37500 }, { "epoch": 4.878445137805512, "grad_norm": 0.0010644930880516768, "learning_rate": 2.5538733847263185e-05, "loss": 7.968700490891934e-05, "step": 37525 }, { "epoch": 4.881695267810713, "grad_norm": 0.0008672529947943985, "learning_rate": 2.550712248349241e-05, "loss": 7.723178714513779e-05, "step": 37550 }, { "epoch": 4.884945397815913, "grad_norm": 0.0024585153441876173, "learning_rate": 2.5475510308556316e-05, "loss": 7.431228645145894e-05, "step": 37575 }, { "epoch": 4.888195527821113, "grad_norm": 0.0019768665079027414, "learning_rate": 2.544389737302002e-05, "loss": 7.329282816499471e-05, "step": 37600 }, { "epoch": 4.8914456578263135, "grad_norm": 0.005287298001348972, "learning_rate": 2.5412283727449826e-05, "loss": 7.963689044117928e-05, "step": 37625 }, { "epoch": 4.894695787831513, "grad_norm": 0.0005583606543950737, "learning_rate": 2.5380669422413194e-05, "loss": 8.182317949831486e-05, "step": 37650 }, { "epoch": 4.897945917836713, "grad_norm": 0.0004756931448355317, "learning_rate": 2.5349054508478637e-05, "loss": 7.887644693255425e-05, "step": 37675 }, { "epoch": 4.901196047841914, "grad_norm": 0.0012598712928593159, "learning_rate": 2.5317439036215628e-05, "loss": 6.247265730053187e-05, "step": 37700 }, { "epoch": 4.904446177847114, "grad_norm": 0.0010609568562358618, "learning_rate": 2.5285823056194545e-05, "loss": 5.8952146209776403e-05, "step": 37725 }, { "epoch": 4.907696307852314, "grad_norm": 0.0004977969801984727, "learning_rate": 2.525420661898658e-05, "loss": 5.8344551362097264e-05, "step": 37750 }, { "epoch": 4.910946437857515, "grad_norm": 0.001094143488444388, "learning_rate": 2.5222589775163653e-05, "loss": 6.393542513251305e-05, "step": 37775 }, { "epoch": 4.914196567862715, "grad_norm": 0.0006351473275572062, "learning_rate": 2.5190972575298323e-05, "loss": 6.604257971048354e-05, "step": 37800 }, { "epoch": 4.9174466978679146, "grad_norm": 0.0012149979593232274, "learning_rate": 2.515935506996374e-05, "loss": 6.716839969158173e-05, "step": 37825 }, { "epoch": 4.920696827873115, "grad_norm": 0.00048554412205703557, "learning_rate": 2.5127737309733523e-05, "loss": 6.935502402484417e-05, "step": 37850 }, { "epoch": 4.923946957878315, "grad_norm": 0.00109668483491987, "learning_rate": 2.509611934518172e-05, "loss": 7.536136545240879e-05, "step": 37875 }, { "epoch": 4.927197087883515, "grad_norm": 0.0009254797478206456, "learning_rate": 2.5064501226882674e-05, "loss": 7.172001525759697e-05, "step": 37900 }, { "epoch": 4.930447217888716, "grad_norm": 0.002026086673140526, "learning_rate": 2.5032883005411008e-05, "loss": 6.710975430905819e-05, "step": 37925 }, { "epoch": 4.933697347893916, "grad_norm": 0.00255165109410882, "learning_rate": 2.500126473134149e-05, "loss": 7.439780980348586e-05, "step": 37950 }, { "epoch": 4.933697347893916, "eval_loss": 0.0002660644822753966, "eval_runtime": 8.9068, "eval_samples_per_second": 561.367, "eval_steps_per_second": 4.491, "step": 37950 }, { "epoch": 4.933697347893916, "eval_holdout_avg_strict_f1": 0.18507852244878517, "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": 0.6328818989369448, "eval_holdout_nemotron_pii_strict_f1": 0.5491249918070393, "eval_holdout_open_pii_masking_500k_strict_f1": 0.42654612697760425, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.42731072921504876, "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": 4.936947477899116, "grad_norm": 0.00047708131023682654, "learning_rate": 2.4969646455248975e-05, "loss": 6.501973140984774e-05, "step": 37975 }, { "epoch": 4.940197607904317, "grad_norm": 0.0008133681840263307, "learning_rate": 2.493802822770833e-05, "loss": 6.207791622728109e-05, "step": 38000 }, { "epoch": 4.9434477379095165, "grad_norm": 0.002417011884972453, "learning_rate": 2.4906410099294328e-05, "loss": 6.960322614759207e-05, "step": 38025 }, { "epoch": 4.946697867914716, "grad_norm": 0.0017333560390397906, "learning_rate": 2.48747921205816e-05, "loss": 6.67269341647625e-05, "step": 38050 }, { "epoch": 4.949947997919917, "grad_norm": 0.0012988337548449636, "learning_rate": 2.4843174342144527e-05, "loss": 7.065784651786089e-05, "step": 38075 }, { "epoch": 4.953198127925117, "grad_norm": 0.0009990998078137636, "learning_rate": 2.481155681455718e-05, "loss": 7.185543887317181e-05, "step": 38100 }, { "epoch": 4.956448257930317, "grad_norm": 0.0007689963094890118, "learning_rate": 2.477993958839321e-05, "loss": 6.873281206935644e-05, "step": 38125 }, { "epoch": 4.959698387935518, "grad_norm": 0.0007804227061569691, "learning_rate": 2.4748322714225806e-05, "loss": 6.586054805666209e-05, "step": 38150 }, { "epoch": 4.962948517940718, "grad_norm": 0.0005098772817291319, "learning_rate": 2.4716706242627587e-05, "loss": 6.465470418334008e-05, "step": 38175 }, { "epoch": 4.966198647945918, "grad_norm": 0.0016135829500854015, "learning_rate": 2.468509022417053e-05, "loss": 6.748332642018795e-05, "step": 38200 }, { "epoch": 4.9694487779511185, "grad_norm": 0.0009325720020569861, "learning_rate": 2.465347470942587e-05, "loss": 6.928218528628349e-05, "step": 38225 }, { "epoch": 4.972698907956318, "grad_norm": 0.0009267816203646362, "learning_rate": 2.462185974896407e-05, "loss": 6.834064610302449e-05, "step": 38250 }, { "epoch": 4.975949037961518, "grad_norm": 0.0010793053079396486, "learning_rate": 2.4590245393354667e-05, "loss": 6.687688175588847e-05, "step": 38275 }, { "epoch": 4.979199167966719, "grad_norm": 0.0010313320672139525, "learning_rate": 2.4558631693166265e-05, "loss": 6.617801263928414e-05, "step": 38300 }, { "epoch": 4.982449297971919, "grad_norm": 0.0016741253202781081, "learning_rate": 2.4527018698966397e-05, "loss": 6.414902396500111e-05, "step": 38325 }, { "epoch": 4.985699427977119, "grad_norm": 0.0018179324688389897, "learning_rate": 2.4495406461321478e-05, "loss": 6.080948282033205e-05, "step": 38350 }, { "epoch": 4.98894955798232, "grad_norm": 0.0013099426869302988, "learning_rate": 2.4463795030796706e-05, "loss": 7.24906986579299e-05, "step": 38375 }, { "epoch": 4.99219968798752, "grad_norm": 0.000997967435978353, "learning_rate": 2.4432184457956e-05, "loss": 6.626686081290245e-05, "step": 38400 }, { "epoch": 4.99544981799272, "grad_norm": 0.000756479857955128, "learning_rate": 2.4400574793361884e-05, "loss": 6.625952664762735e-05, "step": 38425 }, { "epoch": 4.99869994799792, "grad_norm": 0.001142664346843958, "learning_rate": 2.436896608757546e-05, "loss": 6.302195135504007e-05, "step": 38450 }, { "epoch": 5.00195007800312, "grad_norm": 0.0005513379583135247, "learning_rate": 2.433735839115627e-05, "loss": 6.0201981104910376e-05, "step": 38475 }, { "epoch": 5.00520020800832, "grad_norm": 0.002525976626202464, "learning_rate": 2.4305751754662256e-05, "loss": 6.107116118073464e-05, "step": 38500 }, { "epoch": 5.00845033801352, "grad_norm": 0.001213611918501556, "learning_rate": 2.4274146228649657e-05, "loss": 6.27683661878109e-05, "step": 38525 }, { "epoch": 5.011700468018721, "grad_norm": 0.002832310041412711, "learning_rate": 2.4242541863672943e-05, "loss": 6.445209495723248e-05, "step": 38550 }, { "epoch": 5.014950598023921, "grad_norm": 0.0012207417748868465, "learning_rate": 2.421093871028472e-05, "loss": 6.0855308547616004e-05, "step": 38575 }, { "epoch": 5.018200728029121, "grad_norm": 0.0011743773939087987, "learning_rate": 2.4179336819035658e-05, "loss": 5.6310133077204226e-05, "step": 38600 }, { "epoch": 5.021450858034322, "grad_norm": 0.0012346054427325726, "learning_rate": 2.414773624047441e-05, "loss": 7.102150935679674e-05, "step": 38625 }, { "epoch": 5.0247009880395215, "grad_norm": 0.0004297153791412711, "learning_rate": 2.411613702514753e-05, "loss": 5.839323624968529e-05, "step": 38650 }, { "epoch": 5.027951118044721, "grad_norm": 0.0005115574458613992, "learning_rate": 2.4084539223599384e-05, "loss": 6.422112695872784e-05, "step": 38675 }, { "epoch": 5.031201248049922, "grad_norm": 0.000994372647255659, "learning_rate": 2.405294288637209e-05, "loss": 5.650877952575683e-05, "step": 38700 }, { "epoch": 5.034451378055122, "grad_norm": 0.0004449627595022321, "learning_rate": 2.4021348064005412e-05, "loss": 6.231083068996667e-05, "step": 38725 }, { "epoch": 5.037701508060322, "grad_norm": 0.0006160998018458486, "learning_rate": 2.3989754807036698e-05, "loss": 5.447376985102892e-05, "step": 38750 }, { "epoch": 5.040951638065523, "grad_norm": 0.0012017415137961507, "learning_rate": 2.3958163166000788e-05, "loss": 6.043573841452598e-05, "step": 38775 }, { "epoch": 5.044201768070723, "grad_norm": 0.0004771240637637675, "learning_rate": 2.3926573191429936e-05, "loss": 6.245787721127271e-05, "step": 38800 }, { "epoch": 5.047451898075923, "grad_norm": 0.0007645422592759132, "learning_rate": 2.3894984933853733e-05, "loss": 5.51736680790782e-05, "step": 38825 }, { "epoch": 5.0507020280811235, "grad_norm": 0.0006372421630658209, "learning_rate": 2.386339844379903e-05, "loss": 6.595884915441274e-05, "step": 38850 }, { "epoch": 5.053952158086323, "grad_norm": 0.0007916389149613678, "learning_rate": 2.383181377178984e-05, "loss": 5.565902683883906e-05, "step": 38875 }, { "epoch": 5.057202288091523, "grad_norm": 0.002152933506295085, "learning_rate": 2.3800230968347268e-05, "loss": 6.73787947744131e-05, "step": 38900 }, { "epoch": 5.060452418096724, "grad_norm": 0.0012068359646946192, "learning_rate": 2.3768650083989434e-05, "loss": 6.601266097277402e-05, "step": 38925 }, { "epoch": 5.063702548101924, "grad_norm": 0.0011412979802116752, "learning_rate": 2.3737071169231393e-05, "loss": 6.27844175323844e-05, "step": 38950 }, { "epoch": 5.066952678107124, "grad_norm": 0.0006128262029960752, "learning_rate": 2.3705494274585034e-05, "loss": 6.925367284566164e-05, "step": 38975 }, { "epoch": 5.070202808112325, "grad_norm": 0.0007975806947797537, "learning_rate": 2.3673919450559043e-05, "loss": 6.264681462198496e-05, "step": 39000 }, { "epoch": 5.073452938117525, "grad_norm": 0.0018756975186988711, "learning_rate": 2.364234674765877e-05, "loss": 5.7247858494520186e-05, "step": 39025 }, { "epoch": 5.0767030681227245, "grad_norm": 0.0010705108288675547, "learning_rate": 2.3610776216386176e-05, "loss": 6.284035742282868e-05, "step": 39050 }, { "epoch": 5.079953198127925, "grad_norm": 0.0005160068976692855, "learning_rate": 2.3579207907239756e-05, "loss": 5.8641512878239156e-05, "step": 39075 }, { "epoch": 5.083203328133125, "grad_norm": 0.0004460135824047029, "learning_rate": 2.354764187071444e-05, "loss": 5.702284630388022e-05, "step": 39100 }, { "epoch": 5.086453458138325, "grad_norm": 0.0009392926003783941, "learning_rate": 2.3516078157301536e-05, "loss": 5.45249180868268e-05, "step": 39125 }, { "epoch": 5.089703588143526, "grad_norm": 0.0009654202149249613, "learning_rate": 2.3484516817488623e-05, "loss": 5.112948827445507e-05, "step": 39150 }, { "epoch": 5.092953718148726, "grad_norm": 0.000505730917211622, "learning_rate": 2.3452957901759488e-05, "loss": 5.78081700950861e-05, "step": 39175 }, { "epoch": 5.096203848153926, "grad_norm": 0.0007816599099896848, "learning_rate": 2.342140146059405e-05, "loss": 5.61412563547492e-05, "step": 39200 }, { "epoch": 5.099453978159127, "grad_norm": 0.0005796216428279877, "learning_rate": 2.338984754446825e-05, "loss": 6.590408738702536e-05, "step": 39225 }, { "epoch": 5.1027041081643265, "grad_norm": 0.0008724643266759813, "learning_rate": 2.3358296203854012e-05, "loss": 5.939528346061706e-05, "step": 39250 }, { "epoch": 5.105954238169526, "grad_norm": 0.001242554048076272, "learning_rate": 2.3326747489219125e-05, "loss": 5.9855100698769095e-05, "step": 39275 }, { "epoch": 5.109204368174727, "grad_norm": 0.0010903629008680582, "learning_rate": 2.3295201451027185e-05, "loss": 6.209945306181908e-05, "step": 39300 }, { "epoch": 5.112454498179927, "grad_norm": 0.001684054615907371, "learning_rate": 2.3263658139737503e-05, "loss": 6.636929232627153e-05, "step": 39325 }, { "epoch": 5.115704628185127, "grad_norm": 0.0009577211458235979, "learning_rate": 2.3232117605805025e-05, "loss": 6.370286457240581e-05, "step": 39350 }, { "epoch": 5.118954758190328, "grad_norm": 0.0009318781085312366, "learning_rate": 2.320057989968027e-05, "loss": 6.186097860336304e-05, "step": 39375 }, { "epoch": 5.122204888195528, "grad_norm": 0.0015340611571446061, "learning_rate": 2.3169045071809215e-05, "loss": 6.637581158429384e-05, "step": 39400 }, { "epoch": 5.125455018200728, "grad_norm": 0.001176076359115541, "learning_rate": 2.3137513172633242e-05, "loss": 7.419874891638756e-05, "step": 39425 }, { "epoch": 5.1287051482059285, "grad_norm": 0.0007610661559738219, "learning_rate": 2.3105984252589048e-05, "loss": 5.502564832568168e-05, "step": 39450 }, { "epoch": 5.131955278211128, "grad_norm": 0.000539597007445991, "learning_rate": 2.3074458362108566e-05, "loss": 6.365050096064806e-05, "step": 39475 }, { "epoch": 5.135205408216328, "grad_norm": 0.001447614748030901, "learning_rate": 2.304293555161888e-05, "loss": 6.31519453600049e-05, "step": 39500 }, { "epoch": 5.138455538221529, "grad_norm": 0.0010392138501629233, "learning_rate": 2.3011415871542143e-05, "loss": 6.335626356303692e-05, "step": 39525 }, { "epoch": 5.141705668226729, "grad_norm": 0.0007247169851325452, "learning_rate": 2.297989937229552e-05, "loss": 7.087746635079384e-05, "step": 39550 }, { "epoch": 5.144955798231929, "grad_norm": 0.0007250991184264421, "learning_rate": 2.2948386104291068e-05, "loss": 6.104196887463331e-05, "step": 39575 }, { "epoch": 5.14820592823713, "grad_norm": 0.0005206424393691123, "learning_rate": 2.291687611793568e-05, "loss": 6.241408176720142e-05, "step": 39600 }, { "epoch": 5.15145605824233, "grad_norm": 0.001097095781005919, "learning_rate": 2.2885369463631e-05, "loss": 6.069290917366743e-05, "step": 39625 }, { "epoch": 5.15470618824753, "grad_norm": 0.0009309182642027736, "learning_rate": 2.285386619177335e-05, "loss": 6.439030170440674e-05, "step": 39650 }, { "epoch": 5.15795631825273, "grad_norm": 0.0020443762186914682, "learning_rate": 2.2822366352753638e-05, "loss": 6.539658177644014e-05, "step": 39675 }, { "epoch": 5.16120644825793, "grad_norm": 0.0008835718035697937, "learning_rate": 2.279086999695727e-05, "loss": 6.0877217911183835e-05, "step": 39700 }, { "epoch": 5.16445657826313, "grad_norm": 0.0006918638828210533, "learning_rate": 2.2759377174764095e-05, "loss": 5.955258384346962e-05, "step": 39725 }, { "epoch": 5.167706708268331, "grad_norm": 0.0012945515336468816, "learning_rate": 2.2727887936548298e-05, "loss": 6.760535296052695e-05, "step": 39750 }, { "epoch": 5.170956838273531, "grad_norm": 0.002242049900814891, "learning_rate": 2.2696402332678347e-05, "loss": 6.101199425756931e-05, "step": 39775 }, { "epoch": 5.174206968278731, "grad_norm": 0.0005490010371431708, "learning_rate": 2.266492041351688e-05, "loss": 6.477469578385353e-05, "step": 39800 }, { "epoch": 5.177457098283932, "grad_norm": 0.005858373828232288, "learning_rate": 2.263344222942065e-05, "loss": 6.595073733478785e-05, "step": 39825 }, { "epoch": 5.1807072282891315, "grad_norm": 0.000794338237028569, "learning_rate": 2.2601967830740436e-05, "loss": 7.186425849795342e-05, "step": 39850 }, { "epoch": 5.1839573582943315, "grad_norm": 0.0009814545046538115, "learning_rate": 2.2570497267820958e-05, "loss": 5.974030122160912e-05, "step": 39875 }, { "epoch": 5.187207488299532, "grad_norm": 0.000853481178637594, "learning_rate": 2.2539030591000804e-05, "loss": 7.025693077594041e-05, "step": 39900 }, { "epoch": 5.190457618304732, "grad_norm": 0.0036579021252691746, "learning_rate": 2.250756785061234e-05, "loss": 6.02720957249403e-05, "step": 39925 }, { "epoch": 5.193707748309932, "grad_norm": 0.0009623486548662186, "learning_rate": 2.2476109096981645e-05, "loss": 7.156397681683302e-05, "step": 39950 }, { "epoch": 5.196957878315133, "grad_norm": 0.0021726966369897127, "learning_rate": 2.2444654380428412e-05, "loss": 5.652899853885174e-05, "step": 39975 }, { "epoch": 5.200208008320333, "grad_norm": 0.0017043486004695296, "learning_rate": 2.2413203751265883e-05, "loss": 5.537141114473343e-05, "step": 40000 }, { "epoch": 5.203458138325533, "grad_norm": 0.0010900800116360188, "learning_rate": 2.238175725980076e-05, "loss": 7.046089973300696e-05, "step": 40025 }, { "epoch": 5.2067082683307335, "grad_norm": 0.0008605215116403997, "learning_rate": 2.2350314956333117e-05, "loss": 6.62853056564927e-05, "step": 40050 }, { "epoch": 5.209958398335933, "grad_norm": 0.0015605987282469869, "learning_rate": 2.2318876891156356e-05, "loss": 6.555632688105107e-05, "step": 40075 }, { "epoch": 5.213208528341133, "grad_norm": 0.0027469098567962646, "learning_rate": 2.2287443114557066e-05, "loss": 6.670702714473009e-05, "step": 40100 }, { "epoch": 5.216458658346334, "grad_norm": 0.0005820749211125076, "learning_rate": 2.2256013676815002e-05, "loss": 6.469960790127516e-05, "step": 40125 }, { "epoch": 5.219708788351534, "grad_norm": 0.001203511143103242, "learning_rate": 2.2224588628202962e-05, "loss": 6.542638875544071e-05, "step": 40150 }, { "epoch": 5.222958918356734, "grad_norm": 0.0007547543500550091, "learning_rate": 2.2193168018986733e-05, "loss": 5.608570761978626e-05, "step": 40175 }, { "epoch": 5.226209048361935, "grad_norm": 0.011421939358115196, "learning_rate": 2.2161751899425002e-05, "loss": 6.276545114815235e-05, "step": 40200 }, { "epoch": 5.229459178367135, "grad_norm": 0.00112789252307266, "learning_rate": 2.2130340319769263e-05, "loss": 6.392063107341528e-05, "step": 40225 }, { "epoch": 5.232709308372335, "grad_norm": 0.0006383080035448074, "learning_rate": 2.2098933330263763e-05, "loss": 6.0908854939043524e-05, "step": 40250 }, { "epoch": 5.235959438377535, "grad_norm": 0.0010087327100336552, "learning_rate": 2.2067530981145395e-05, "loss": 6.512999068945646e-05, "step": 40275 }, { "epoch": 5.239209568382735, "grad_norm": 0.0015667449915781617, "learning_rate": 2.2036133322643636e-05, "loss": 6.5370574593544e-05, "step": 40300 }, { "epoch": 5.242459698387935, "grad_norm": 0.0011047483421862125, "learning_rate": 2.2004740404980458e-05, "loss": 6.676575634628534e-05, "step": 40325 }, { "epoch": 5.245709828393136, "grad_norm": 0.002648902591317892, "learning_rate": 2.197335227837025e-05, "loss": 6.497833877801896e-05, "step": 40350 }, { "epoch": 5.248959958398336, "grad_norm": 0.0008240414317697287, "learning_rate": 2.1941968993019743e-05, "loss": 6.151726003736257e-05, "step": 40375 }, { "epoch": 5.252210088403536, "grad_norm": 0.0007656759698875248, "learning_rate": 2.1910590599127914e-05, "loss": 6.054287776350975e-05, "step": 40400 }, { "epoch": 5.255460218408737, "grad_norm": 0.0011521076085045934, "learning_rate": 2.1879217146885923e-05, "loss": 6.831946782767773e-05, "step": 40425 }, { "epoch": 5.258710348413937, "grad_norm": 0.0009830573108047247, "learning_rate": 2.1847848686477024e-05, "loss": 6.561238784343004e-05, "step": 40450 }, { "epoch": 5.2619604784191365, "grad_norm": 0.0005134244565851986, "learning_rate": 2.1816485268076478e-05, "loss": 6.163103505969048e-05, "step": 40475 }, { "epoch": 5.265210608424337, "grad_norm": 0.0014326471136882901, "learning_rate": 2.1785126941851496e-05, "loss": 6.518505048006772e-05, "step": 40500 }, { "epoch": 5.268460738429537, "grad_norm": 0.0017757224850356579, "learning_rate": 2.175377375796114e-05, "loss": 5.2353674545884134e-05, "step": 40525 }, { "epoch": 5.271710868434737, "grad_norm": 0.0009811309864744544, "learning_rate": 2.1722425766556234e-05, "loss": 6.050402764230967e-05, "step": 40550 }, { "epoch": 5.274960998439938, "grad_norm": 0.0004563611000776291, "learning_rate": 2.1691083017779313e-05, "loss": 5.5510876700282096e-05, "step": 40575 }, { "epoch": 5.278211128445138, "grad_norm": 0.001924261450767517, "learning_rate": 2.1659745561764517e-05, "loss": 5.839752033352852e-05, "step": 40600 }, { "epoch": 5.281461258450338, "grad_norm": 0.0021068344358354807, "learning_rate": 2.1628413448637523e-05, "loss": 6.663444917649031e-05, "step": 40625 }, { "epoch": 5.284711388455539, "grad_norm": 0.0011178330751135945, "learning_rate": 2.1597086728515456e-05, "loss": 5.6270579807460305e-05, "step": 40650 }, { "epoch": 5.2879615184607385, "grad_norm": 0.001430419273674488, "learning_rate": 2.1565765451506827e-05, "loss": 6.729376502335072e-05, "step": 40675 }, { "epoch": 5.291211648465938, "grad_norm": 0.0005863550468347967, "learning_rate": 2.1534449667711426e-05, "loss": 6.156966555863619e-05, "step": 40700 }, { "epoch": 5.294461778471139, "grad_norm": 0.0008192643872462213, "learning_rate": 2.1503139427220265e-05, "loss": 6.627590395510197e-05, "step": 40725 }, { "epoch": 5.297711908476339, "grad_norm": 0.0010169829474762082, "learning_rate": 2.147183478011549e-05, "loss": 5.806534551084042e-05, "step": 40750 }, { "epoch": 5.300962038481539, "grad_norm": 0.0011287251254543662, "learning_rate": 2.1440535776470297e-05, "loss": 6.101178005337715e-05, "step": 40775 }, { "epoch": 5.30421216848674, "grad_norm": 0.0009104765485972166, "learning_rate": 2.1409242466348856e-05, "loss": 6.949730683118104e-05, "step": 40800 }, { "epoch": 5.30746229849194, "grad_norm": 0.0006840076530352235, "learning_rate": 2.1377954899806226e-05, "loss": 6.06228644028306e-05, "step": 40825 }, { "epoch": 5.31071242849714, "grad_norm": 0.0007110993610695004, "learning_rate": 2.1346673126888283e-05, "loss": 6.562966387718916e-05, "step": 40850 }, { "epoch": 5.3139625585023404, "grad_norm": 0.0005786907277069986, "learning_rate": 2.1315397197631636e-05, "loss": 6.51052175089717e-05, "step": 40875 }, { "epoch": 5.31721268850754, "grad_norm": 0.0010109076974913478, "learning_rate": 2.1284127162063545e-05, "loss": 6.066393107175827e-05, "step": 40900 }, { "epoch": 5.32046281851274, "grad_norm": 0.0005702113267034292, "learning_rate": 2.125286307020185e-05, "loss": 6.328210700303316e-05, "step": 40925 }, { "epoch": 5.323712948517941, "grad_norm": 0.0009006196050904691, "learning_rate": 2.1221604972054876e-05, "loss": 5.689309909939766e-05, "step": 40950 }, { "epoch": 5.326963078523141, "grad_norm": 0.0012936403509229422, "learning_rate": 2.1190352917621358e-05, "loss": 6.078897509723902e-05, "step": 40975 }, { "epoch": 5.330213208528341, "grad_norm": 0.0012246010592207313, "learning_rate": 2.1159106956890368e-05, "loss": 5.769701208919287e-05, "step": 41000 }, { "epoch": 5.333463338533542, "grad_norm": 0.001197915873490274, "learning_rate": 2.1127867139841234e-05, "loss": 6.156977731734514e-05, "step": 41025 }, { "epoch": 5.336713468538742, "grad_norm": 0.0005474579520523548, "learning_rate": 2.1096633516443456e-05, "loss": 5.5623245425522325e-05, "step": 41050 }, { "epoch": 5.3399635985439415, "grad_norm": 0.000913277908693999, "learning_rate": 2.106540613665662e-05, "loss": 5.8074542321264746e-05, "step": 41075 }, { "epoch": 5.343213728549142, "grad_norm": 0.0019106860272586346, "learning_rate": 2.1034185050430334e-05, "loss": 5.577001720666885e-05, "step": 41100 }, { "epoch": 5.346463858554342, "grad_norm": 0.0013206831645220518, "learning_rate": 2.1002970307704132e-05, "loss": 5.9173721820116046e-05, "step": 41125 }, { "epoch": 5.349713988559542, "grad_norm": 0.0006840279093012214, "learning_rate": 2.0971761958407403e-05, "loss": 6.991295143961907e-05, "step": 41150 }, { "epoch": 5.352964118564743, "grad_norm": 0.0013189595192670822, "learning_rate": 2.0940560052459317e-05, "loss": 5.8485125191509726e-05, "step": 41175 }, { "epoch": 5.356214248569943, "grad_norm": 0.0009240724029950798, "learning_rate": 2.090936463976873e-05, "loss": 5.183733999729156e-05, "step": 41200 }, { "epoch": 5.359464378575143, "grad_norm": 0.0009573042043484747, "learning_rate": 2.087817577023411e-05, "loss": 5.4758829064667226e-05, "step": 41225 }, { "epoch": 5.362714508580344, "grad_norm": 0.00027000028057955205, "learning_rate": 2.084699349374346e-05, "loss": 4.936017096042633e-05, "step": 41250 }, { "epoch": 5.3659646385855435, "grad_norm": 0.0008269459940493107, "learning_rate": 2.0815817860174248e-05, "loss": 6.427704822272062e-05, "step": 41275 }, { "epoch": 5.369214768590743, "grad_norm": 0.005018285010010004, "learning_rate": 2.0784648919393297e-05, "loss": 5.90758677572012e-05, "step": 41300 }, { "epoch": 5.372464898595944, "grad_norm": 0.0010663915891200304, "learning_rate": 2.0753486721256746e-05, "loss": 5.85422059521079e-05, "step": 41325 }, { "epoch": 5.375715028601144, "grad_norm": 0.0004653829091694206, "learning_rate": 2.072233131560993e-05, "loss": 5.375548265874386e-05, "step": 41350 }, { "epoch": 5.378965158606344, "grad_norm": 0.001182987354695797, "learning_rate": 2.069118275228733e-05, "loss": 5.584987811744213e-05, "step": 41375 }, { "epoch": 5.382215288611545, "grad_norm": 0.0013821728061884642, "learning_rate": 2.066004108111248e-05, "loss": 6.34827883914113e-05, "step": 41400 }, { "epoch": 5.382215288611545, "eval_loss": 0.00024248554836958647, "eval_runtime": 9.4115, "eval_samples_per_second": 531.267, "eval_steps_per_second": 4.25, "step": 41400 }, { "epoch": 5.382215288611545, "eval_holdout_avg_strict_f1": 0.20752269415183966, "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": 0.7075933864053889, "eval_holdout_nemotron_pii_strict_f1": 0.614900614900615, "eval_holdout_open_pii_masking_500k_strict_f1": 0.49017728797316723, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.47007834639106516, "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": 5.385465418616745, "grad_norm": 0.0006580271292477846, "learning_rate": 2.0628906351897888e-05, "loss": 6.276192609220743e-05, "step": 41425 }, { "epoch": 5.388715548621945, "grad_norm": 0.0015499951550737023, "learning_rate": 2.0597778614444955e-05, "loss": 5.55687677115202e-05, "step": 41450 }, { "epoch": 5.3919656786271455, "grad_norm": 0.000589130213484168, "learning_rate": 2.056665791854391e-05, "loss": 4.834540188312531e-05, "step": 41475 }, { "epoch": 5.395215808632345, "grad_norm": 0.0006286009447649121, "learning_rate": 2.053554431397371e-05, "loss": 6.339486222714185e-05, "step": 41500 }, { "epoch": 5.398465938637545, "grad_norm": 0.00041498971404507756, "learning_rate": 2.050443785050197e-05, "loss": 5.754095036536455e-05, "step": 41525 }, { "epoch": 5.401716068642746, "grad_norm": 0.0014956302475184202, "learning_rate": 2.0473338577884884e-05, "loss": 6.147898267954587e-05, "step": 41550 }, { "epoch": 5.404966198647946, "grad_norm": 0.0014752921415492892, "learning_rate": 2.044224654586714e-05, "loss": 6.444765720516444e-05, "step": 41575 }, { "epoch": 5.408216328653146, "grad_norm": 0.0014514337526634336, "learning_rate": 2.0411161804181844e-05, "loss": 6.264119409024716e-05, "step": 41600 }, { "epoch": 5.411466458658347, "grad_norm": 0.0009340330143459141, "learning_rate": 2.0380084402550454e-05, "loss": 5.665707401931286e-05, "step": 41625 }, { "epoch": 5.414716588663547, "grad_norm": 0.0008117153192870319, "learning_rate": 2.0349014390682667e-05, "loss": 5.79241244122386e-05, "step": 41650 }, { "epoch": 5.417966718668747, "grad_norm": 0.001143178902566433, "learning_rate": 2.0317951818276372e-05, "loss": 5.805785302072763e-05, "step": 41675 }, { "epoch": 5.4212168486739465, "grad_norm": 0.0012510400265455246, "learning_rate": 2.0286896735017563e-05, "loss": 6.4342743717134e-05, "step": 41700 }, { "epoch": 5.424466978679147, "grad_norm": 0.001156181562691927, "learning_rate": 2.025584919058024e-05, "loss": 5.601177457720041e-05, "step": 41725 }, { "epoch": 5.427717108684347, "grad_norm": 0.001382984803058207, "learning_rate": 2.022480923462636e-05, "loss": 5.5407709442079065e-05, "step": 41750 }, { "epoch": 5.430967238689547, "grad_norm": 0.0016516821924597025, "learning_rate": 2.019377691680572e-05, "loss": 6.258914712816477e-05, "step": 41775 }, { "epoch": 5.434217368694748, "grad_norm": 0.0008544135489501059, "learning_rate": 2.016275228675593e-05, "loss": 5.594514310359955e-05, "step": 41800 }, { "epoch": 5.437467498699948, "grad_norm": 0.0007914748857729137, "learning_rate": 2.0131735394102284e-05, "loss": 6.384796928614378e-05, "step": 41825 }, { "epoch": 5.440717628705148, "grad_norm": 0.0006955398712307215, "learning_rate": 2.010072628845769e-05, "loss": 5.337091162800789e-05, "step": 41850 }, { "epoch": 5.4439677587103485, "grad_norm": 0.001853955676779151, "learning_rate": 2.0069725019422625e-05, "loss": 5.6641856208443645e-05, "step": 41875 }, { "epoch": 5.4472178887155485, "grad_norm": 0.0009247317211702466, "learning_rate": 2.0038731636585016e-05, "loss": 6.59527676180005e-05, "step": 41900 }, { "epoch": 5.450468018720748, "grad_norm": 0.00041612202767282724, "learning_rate": 2.000774618952017e-05, "loss": 5.553998518735171e-05, "step": 41925 }, { "epoch": 5.453718148725949, "grad_norm": 0.0004276034305803478, "learning_rate": 1.9976768727790723e-05, "loss": 5.2575897425413134e-05, "step": 41950 }, { "epoch": 5.456968278731149, "grad_norm": 0.0012745120329782367, "learning_rate": 1.994579930094652e-05, "loss": 6.280757021158934e-05, "step": 41975 }, { "epoch": 5.460218408736349, "grad_norm": 0.0008658504812046885, "learning_rate": 1.9914837958524546e-05, "loss": 6.290251854807139e-05, "step": 42000 }, { "epoch": 5.46346853874155, "grad_norm": 0.001016497379168868, "learning_rate": 1.9883884750048875e-05, "loss": 5.7980306446552274e-05, "step": 42025 }, { "epoch": 5.46671866874675, "grad_norm": 0.0020551716443151236, "learning_rate": 1.985293972503056e-05, "loss": 6.366518326103687e-05, "step": 42050 }, { "epoch": 5.46996879875195, "grad_norm": 0.00039351131999865174, "learning_rate": 1.982200293296757e-05, "loss": 6.696846801787615e-05, "step": 42075 }, { "epoch": 5.47321892875715, "grad_norm": 0.0012514322297647595, "learning_rate": 1.9791074423344695e-05, "loss": 5.791934672743082e-05, "step": 42100 }, { "epoch": 5.47646905876235, "grad_norm": 0.0005775552126578987, "learning_rate": 1.9760154245633485e-05, "loss": 6.386735942214727e-05, "step": 42125 }, { "epoch": 5.47971918876755, "grad_norm": 0.0010766626801341772, "learning_rate": 1.9729242449292163e-05, "loss": 5.7820803485810755e-05, "step": 42150 }, { "epoch": 5.482969318772751, "grad_norm": 0.0013583037070930004, "learning_rate": 1.969833908376554e-05, "loss": 5.9676454402506354e-05, "step": 42175 }, { "epoch": 5.486219448777951, "grad_norm": 0.0005255290307104588, "learning_rate": 1.966744419848494e-05, "loss": 5.15066972002387e-05, "step": 42200 }, { "epoch": 5.489469578783151, "grad_norm": 0.0005459468811750412, "learning_rate": 1.963655784286814e-05, "loss": 5.9043294750154016e-05, "step": 42225 }, { "epoch": 5.492719708788352, "grad_norm": 0.000921316328458488, "learning_rate": 1.9605680066319247e-05, "loss": 5.866277497261763e-05, "step": 42250 }, { "epoch": 5.495969838793552, "grad_norm": 0.0013653083005920053, "learning_rate": 1.9574810918228667e-05, "loss": 6.509856786578893e-05, "step": 42275 }, { "epoch": 5.4992199687987515, "grad_norm": 0.000608226633630693, "learning_rate": 1.954395044797299e-05, "loss": 5.740199238061905e-05, "step": 42300 }, { "epoch": 5.502470098803952, "grad_norm": 0.0007167744333855808, "learning_rate": 1.951309870491494e-05, "loss": 6.871962454169988e-05, "step": 42325 }, { "epoch": 5.505720228809152, "grad_norm": 0.0030588265508413315, "learning_rate": 1.9482255738403264e-05, "loss": 6.720874458551407e-05, "step": 42350 }, { "epoch": 5.508970358814352, "grad_norm": 0.0008640607120469213, "learning_rate": 1.945142159777269e-05, "loss": 6.106444634497165e-05, "step": 42375 }, { "epoch": 5.512220488819553, "grad_norm": 0.0006588752148672938, "learning_rate": 1.942059633234381e-05, "loss": 5.619806237518787e-05, "step": 42400 }, { "epoch": 5.515470618824753, "grad_norm": 0.0006791576161049306, "learning_rate": 1.938977999142303e-05, "loss": 5.153771489858627e-05, "step": 42425 }, { "epoch": 5.518720748829953, "grad_norm": 0.000985422171652317, "learning_rate": 1.9358972624302478e-05, "loss": 5.462504923343658e-05, "step": 42450 }, { "epoch": 5.521970878835154, "grad_norm": 0.0023801906500011683, "learning_rate": 1.9328174280259937e-05, "loss": 5.5497954599559306e-05, "step": 42475 }, { "epoch": 5.5252210088403535, "grad_norm": 0.0014551696367561817, "learning_rate": 1.9297385008558734e-05, "loss": 5.6313322857022287e-05, "step": 42500 }, { "epoch": 5.528471138845553, "grad_norm": 0.00187019188888371, "learning_rate": 1.9266604858447713e-05, "loss": 5.991232581436634e-05, "step": 42525 }, { "epoch": 5.531721268850754, "grad_norm": 0.0019099252531304955, "learning_rate": 1.9235833879161103e-05, "loss": 5.998517386615276e-05, "step": 42550 }, { "epoch": 5.534971398855954, "grad_norm": 0.00036679941695183516, "learning_rate": 1.9205072119918483e-05, "loss": 5.814393982291222e-05, "step": 42575 }, { "epoch": 5.538221528861154, "grad_norm": 0.0006620019557885826, "learning_rate": 1.9174319629924677e-05, "loss": 5.28849707916379e-05, "step": 42600 }, { "epoch": 5.541471658866355, "grad_norm": 0.0005447391886264086, "learning_rate": 1.914357645836967e-05, "loss": 5.236105527728796e-05, "step": 42625 }, { "epoch": 5.544721788871555, "grad_norm": 0.0006025910843163729, "learning_rate": 1.9112842654428564e-05, "loss": 5.910190287977457e-05, "step": 42650 }, { "epoch": 5.547971918876755, "grad_norm": 0.0006120563484728336, "learning_rate": 1.908211826726146e-05, "loss": 6.058319006115198e-05, "step": 42675 }, { "epoch": 5.5512220488819555, "grad_norm": 0.0006649884744547307, "learning_rate": 1.9051403346013406e-05, "loss": 5.306174512952566e-05, "step": 42700 }, { "epoch": 5.554472178887155, "grad_norm": 0.001947683049365878, "learning_rate": 1.9020697939814308e-05, "loss": 5.80581184476614e-05, "step": 42725 }, { "epoch": 5.557722308892355, "grad_norm": 0.0007162385736592114, "learning_rate": 1.8990002097778846e-05, "loss": 5.648276302963495e-05, "step": 42750 }, { "epoch": 5.560972438897556, "grad_norm": 0.0007452594581991434, "learning_rate": 1.8959315869006406e-05, "loss": 5.895831622183323e-05, "step": 42775 }, { "epoch": 5.564222568902756, "grad_norm": 0.0010503396624699235, "learning_rate": 1.8928639302580993e-05, "loss": 6.209584884345532e-05, "step": 42800 }, { "epoch": 5.567472698907956, "grad_norm": 0.0016897665336728096, "learning_rate": 1.8897972447571167e-05, "loss": 6.0595464892685415e-05, "step": 42825 }, { "epoch": 5.570722828913157, "grad_norm": 0.0011591825168579817, "learning_rate": 1.8867315353029935e-05, "loss": 5.761759821325541e-05, "step": 42850 }, { "epoch": 5.573972958918357, "grad_norm": 0.0006514639244414866, "learning_rate": 1.883666806799472e-05, "loss": 6.036429665982723e-05, "step": 42875 }, { "epoch": 5.577223088923557, "grad_norm": 0.0015818012179806828, "learning_rate": 1.880603064148723e-05, "loss": 6.041154731065035e-05, "step": 42900 }, { "epoch": 5.580473218928757, "grad_norm": 0.0007480286876671016, "learning_rate": 1.8775403122513417e-05, "loss": 5.3077372722327706e-05, "step": 42925 }, { "epoch": 5.583723348933957, "grad_norm": 0.0007682368159294128, "learning_rate": 1.874478556006337e-05, "loss": 5.74409170076251e-05, "step": 42950 }, { "epoch": 5.586973478939157, "grad_norm": 0.0002805618569254875, "learning_rate": 1.871417800311128e-05, "loss": 5.8236741460859774e-05, "step": 42975 }, { "epoch": 5.590223608944358, "grad_norm": 0.0010887292446568608, "learning_rate": 1.8683580500615293e-05, "loss": 5.965796299278736e-05, "step": 43000 }, { "epoch": 5.593473738949558, "grad_norm": 0.000911369570530951, "learning_rate": 1.865299310151752e-05, "loss": 5.662684794515371e-05, "step": 43025 }, { "epoch": 5.596723868954758, "grad_norm": 0.0007228704052977264, "learning_rate": 1.862241585474387e-05, "loss": 6.427208427339792e-05, "step": 43050 }, { "epoch": 5.599973998959959, "grad_norm": 0.0008474698988720775, "learning_rate": 1.859184880920403e-05, "loss": 5.8374633081257347e-05, "step": 43075 }, { "epoch": 5.6032241289651585, "grad_norm": 0.001890084007754922, "learning_rate": 1.8561292013791386e-05, "loss": 5.880506709218025e-05, "step": 43100 }, { "epoch": 5.6064742589703584, "grad_norm": 0.000911073642782867, "learning_rate": 1.8530745517382898e-05, "loss": 5.3243809379637244e-05, "step": 43125 }, { "epoch": 5.609724388975559, "grad_norm": 0.0003147880779579282, "learning_rate": 1.8500209368839068e-05, "loss": 5.6440765038132665e-05, "step": 43150 }, { "epoch": 5.612974518980759, "grad_norm": 0.0021293694153428078, "learning_rate": 1.8469683617003844e-05, "loss": 6.4151119440794e-05, "step": 43175 }, { "epoch": 5.616224648985959, "grad_norm": 0.00065466423984617, "learning_rate": 1.8439168310704547e-05, "loss": 6.0292785055935385e-05, "step": 43200 }, { "epoch": 5.61947477899116, "grad_norm": 0.0014012489700689912, "learning_rate": 1.8408663498751787e-05, "loss": 5.5334623903036116e-05, "step": 43225 }, { "epoch": 5.62272490899636, "grad_norm": 0.001345883822068572, "learning_rate": 1.837816922993939e-05, "loss": 5.596188828349114e-05, "step": 43250 }, { "epoch": 5.62597503900156, "grad_norm": 0.000952576519921422, "learning_rate": 1.8347685553044314e-05, "loss": 6.185410544276237e-05, "step": 43275 }, { "epoch": 5.6292251690067605, "grad_norm": 0.0011654671980068088, "learning_rate": 1.8317212516826576e-05, "loss": 5.8170962147414685e-05, "step": 43300 }, { "epoch": 5.63247529901196, "grad_norm": 0.0006497739814221859, "learning_rate": 1.8286750170029175e-05, "loss": 6.200517527759075e-05, "step": 43325 }, { "epoch": 5.63572542901716, "grad_norm": 0.0005279257311485708, "learning_rate": 1.8256298561378006e-05, "loss": 5.059632007032633e-05, "step": 43350 }, { "epoch": 5.638975559022361, "grad_norm": 0.001287080580368638, "learning_rate": 1.8225857739581793e-05, "loss": 6.327224429696798e-05, "step": 43375 }, { "epoch": 5.642225689027561, "grad_norm": 0.0005075703375041485, "learning_rate": 1.8195427753332007e-05, "loss": 6.046473048627377e-05, "step": 43400 }, { "epoch": 5.645475819032761, "grad_norm": 0.001157130696810782, "learning_rate": 1.8165008651302788e-05, "loss": 5.593940615653992e-05, "step": 43425 }, { "epoch": 5.648725949037962, "grad_norm": 0.0009579618345014751, "learning_rate": 1.8134600482150863e-05, "loss": 5.601766984909773e-05, "step": 43450 }, { "epoch": 5.651976079043162, "grad_norm": 0.00118792534340173, "learning_rate": 1.8104203294515463e-05, "loss": 4.821959882974625e-05, "step": 43475 }, { "epoch": 5.655226209048362, "grad_norm": 0.0007555894553661346, "learning_rate": 1.8073817137018275e-05, "loss": 5.662656389176845e-05, "step": 43500 }, { "epoch": 5.658476339053562, "grad_norm": 0.0013229441829025745, "learning_rate": 1.8043442058263333e-05, "loss": 5.855949129909277e-05, "step": 43525 }, { "epoch": 5.661726469058762, "grad_norm": 0.0005543443257920444, "learning_rate": 1.801307810683692e-05, "loss": 6.278359331190586e-05, "step": 43550 }, { "epoch": 5.664976599063962, "grad_norm": 0.0013776642736047506, "learning_rate": 1.798272533130757e-05, "loss": 5.518711637705564e-05, "step": 43575 }, { "epoch": 5.668226729069163, "grad_norm": 0.0009767175652086735, "learning_rate": 1.7952383780225915e-05, "loss": 5.770546849817038e-05, "step": 43600 }, { "epoch": 5.671476859074363, "grad_norm": 0.000513025326654315, "learning_rate": 1.792205350212463e-05, "loss": 6.170390173792839e-05, "step": 43625 }, { "epoch": 5.674726989079563, "grad_norm": 0.0008384613902308047, "learning_rate": 1.789173454551837e-05, "loss": 6.214483641088008e-05, "step": 43650 }, { "epoch": 5.677977119084764, "grad_norm": 0.0011359285563230515, "learning_rate": 1.786142695890367e-05, "loss": 5.717642605304718e-05, "step": 43675 }, { "epoch": 5.681227249089964, "grad_norm": 0.0007647558231838048, "learning_rate": 1.7831130790758882e-05, "loss": 5.201744846999645e-05, "step": 43700 }, { "epoch": 5.6844773790951635, "grad_norm": 0.0006666983827017248, "learning_rate": 1.7800846089544105e-05, "loss": 5.539606790989637e-05, "step": 43725 }, { "epoch": 5.687727509100364, "grad_norm": 0.0014740355545654893, "learning_rate": 1.7770572903701083e-05, "loss": 5.5209877900779246e-05, "step": 43750 }, { "epoch": 5.690977639105564, "grad_norm": 0.0013862771447747946, "learning_rate": 1.774031128165314e-05, "loss": 5.5004595778882504e-05, "step": 43775 }, { "epoch": 5.694227769110764, "grad_norm": 0.0008636791026219726, "learning_rate": 1.7710061271805106e-05, "loss": 5.696599837392569e-05, "step": 43800 }, { "epoch": 5.697477899115965, "grad_norm": 0.007790093310177326, "learning_rate": 1.7679822922543237e-05, "loss": 5.6002470664680004e-05, "step": 43825 }, { "epoch": 5.700728029121165, "grad_norm": 0.001316463458351791, "learning_rate": 1.764959628223515e-05, "loss": 5.814025644212961e-05, "step": 43850 }, { "epoch": 5.703978159126365, "grad_norm": 0.0018464484019204974, "learning_rate": 1.7619381399229702e-05, "loss": 5.792874842882156e-05, "step": 43875 }, { "epoch": 5.7072282891315655, "grad_norm": 0.0005530464695766568, "learning_rate": 1.758917832185698e-05, "loss": 5.812514573335648e-05, "step": 43900 }, { "epoch": 5.7104784191367655, "grad_norm": 0.0020436521153897047, "learning_rate": 1.755898709842816e-05, "loss": 5.4781720973551276e-05, "step": 43925 }, { "epoch": 5.713728549141965, "grad_norm": 0.0012618141481652856, "learning_rate": 1.7528807777235467e-05, "loss": 5.868271458894014e-05, "step": 43950 }, { "epoch": 5.716978679147166, "grad_norm": 0.001740070409141481, "learning_rate": 1.7498640406552093e-05, "loss": 5.9813684783875944e-05, "step": 43975 }, { "epoch": 5.720228809152366, "grad_norm": 0.0014334343140944839, "learning_rate": 1.7468485034632107e-05, "loss": 5.893455818295479e-05, "step": 44000 }, { "epoch": 5.723478939157566, "grad_norm": 0.0011614639079198241, "learning_rate": 1.7438341709710388e-05, "loss": 5.300328135490417e-05, "step": 44025 }, { "epoch": 5.726729069162767, "grad_norm": 0.0004994666669517756, "learning_rate": 1.7408210480002547e-05, "loss": 5.188804119825363e-05, "step": 44050 }, { "epoch": 5.729979199167967, "grad_norm": 0.0005633342661894858, "learning_rate": 1.737809139370484e-05, "loss": 5.062679294496775e-05, "step": 44075 }, { "epoch": 5.733229329173167, "grad_norm": 0.0009324777056463063, "learning_rate": 1.734798449899412e-05, "loss": 4.902868065983057e-05, "step": 44100 }, { "epoch": 5.736479459178367, "grad_norm": 0.0009728263830766082, "learning_rate": 1.7317889844027707e-05, "loss": 6.319301668554545e-05, "step": 44125 }, { "epoch": 5.739729589183567, "grad_norm": 0.0019865240901708603, "learning_rate": 1.728780747694337e-05, "loss": 6.220892537385225e-05, "step": 44150 }, { "epoch": 5.742979719188767, "grad_norm": 0.0007336774142459035, "learning_rate": 1.7257737445859214e-05, "loss": 5.1782336086034775e-05, "step": 44175 }, { "epoch": 5.746229849193968, "grad_norm": 0.0008690340328030288, "learning_rate": 1.7227679798873612e-05, "loss": 5.682059098035097e-05, "step": 44200 }, { "epoch": 5.749479979199168, "grad_norm": 0.0013132203603163362, "learning_rate": 1.7197634584065117e-05, "loss": 5.47515694051981e-05, "step": 44225 }, { "epoch": 5.752730109204368, "grad_norm": 0.0009918984724208713, "learning_rate": 1.716760184949242e-05, "loss": 5.762970075011253e-05, "step": 44250 }, { "epoch": 5.755980239209569, "grad_norm": 0.0018158400198444724, "learning_rate": 1.7137581643194233e-05, "loss": 5.589201580733061e-05, "step": 44275 }, { "epoch": 5.759230369214769, "grad_norm": 0.0007202354026958346, "learning_rate": 1.7107574013189225e-05, "loss": 5.807615350931883e-05, "step": 44300 }, { "epoch": 5.7624804992199685, "grad_norm": 0.0008584561292082071, "learning_rate": 1.7077579007475967e-05, "loss": 5.944670177996159e-05, "step": 44325 }, { "epoch": 5.765730629225169, "grad_norm": 0.0005054424400441349, "learning_rate": 1.7047596674032812e-05, "loss": 6.018887273967266e-05, "step": 44350 }, { "epoch": 5.768980759230369, "grad_norm": 0.0006955042481422424, "learning_rate": 1.7017627060817865e-05, "loss": 7.0955203846097e-05, "step": 44375 }, { "epoch": 5.772230889235569, "grad_norm": 0.0008705614600330591, "learning_rate": 1.698767021576887e-05, "loss": 5.560650490224361e-05, "step": 44400 }, { "epoch": 5.77548101924077, "grad_norm": 0.0006629931158386171, "learning_rate": 1.695772618680316e-05, "loss": 5.404864437878132e-05, "step": 44425 }, { "epoch": 5.77873114924597, "grad_norm": 0.0006427660118788481, "learning_rate": 1.6927795021817557e-05, "loss": 5.3759533911943436e-05, "step": 44450 }, { "epoch": 5.78198127925117, "grad_norm": 0.0034291213378310204, "learning_rate": 1.6897876768688306e-05, "loss": 5.709392484277487e-05, "step": 44475 }, { "epoch": 5.785231409256371, "grad_norm": 0.00047558051301166415, "learning_rate": 1.6867971475271013e-05, "loss": 5.766252521425486e-05, "step": 44500 }, { "epoch": 5.7884815392615705, "grad_norm": 0.0005283249774947762, "learning_rate": 1.683807918940054e-05, "loss": 4.972586408257484e-05, "step": 44525 }, { "epoch": 5.79173166926677, "grad_norm": 0.0010149440495297313, "learning_rate": 1.6808199958890953e-05, "loss": 4.468717612326145e-05, "step": 44550 }, { "epoch": 5.794981799271971, "grad_norm": 0.000631525821518153, "learning_rate": 1.677833383153542e-05, "loss": 5.736928898841143e-05, "step": 44575 }, { "epoch": 5.798231929277171, "grad_norm": 0.0007197380182333291, "learning_rate": 1.6748480855106173e-05, "loss": 6.000942084938288e-05, "step": 44600 }, { "epoch": 5.801482059282371, "grad_norm": 0.0010328327771276236, "learning_rate": 1.6718641077354384e-05, "loss": 5.3696725517511366e-05, "step": 44625 }, { "epoch": 5.804732189287572, "grad_norm": 0.0008097238605841994, "learning_rate": 1.6688814546010133e-05, "loss": 5.372181534767151e-05, "step": 44650 }, { "epoch": 5.807982319292772, "grad_norm": 0.0007223514840006828, "learning_rate": 1.6659001308782304e-05, "loss": 6.021360866725445e-05, "step": 44675 }, { "epoch": 5.811232449297972, "grad_norm": 0.0024087284691631794, "learning_rate": 1.6629201413358515e-05, "loss": 5.350717343389988e-05, "step": 44700 }, { "epoch": 5.8144825793031725, "grad_norm": 0.0014146625762805343, "learning_rate": 1.6599414907405035e-05, "loss": 5.6938403286039826e-05, "step": 44725 }, { "epoch": 5.817732709308372, "grad_norm": 0.0010600128443911672, "learning_rate": 1.656964183856674e-05, "loss": 5.834721028804779e-05, "step": 44750 }, { "epoch": 5.820982839313572, "grad_norm": 0.001138837425969541, "learning_rate": 1.653988225446698e-05, "loss": 6.050665862858295e-05, "step": 44775 }, { "epoch": 5.824232969318773, "grad_norm": 0.00038540340028703213, "learning_rate": 1.6510136202707576e-05, "loss": 6.285170558840037e-05, "step": 44800 }, { "epoch": 5.827483099323973, "grad_norm": 0.001457010512240231, "learning_rate": 1.6480403730868664e-05, "loss": 6.334346253424882e-05, "step": 44825 }, { "epoch": 5.830733229329173, "grad_norm": 0.0006736749783158302, "learning_rate": 1.6450684886508682e-05, "loss": 5.799752660095692e-05, "step": 44850 }, { "epoch": 5.830733229329173, "eval_loss": 0.00023623552988283336, "eval_runtime": 9.4054, "eval_samples_per_second": 531.61, "eval_steps_per_second": 4.253, "step": 44850 }, { "epoch": 5.830733229329173, "eval_holdout_avg_strict_f1": 0.2014214459588505, "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": 0.6747094306311608, "eval_holdout_nemotron_pii_strict_f1": 0.5927723840345199, "eval_holdout_open_pii_masking_500k_strict_f1": 0.4938954158028104, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.4542586750788643, "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": 5.833983359334374, "grad_norm": 0.0006291124154813588, "learning_rate": 1.6420979717164263e-05, "loss": 5.027389153838158e-05, "step": 44875 }, { "epoch": 5.837233489339574, "grad_norm": 0.0003392710059415549, "learning_rate": 1.639128827035017e-05, "loss": 6.0606077313423156e-05, "step": 44900 }, { "epoch": 5.840483619344774, "grad_norm": 0.0006324895075522363, "learning_rate": 1.6361610593559205e-05, "loss": 4.894746001809835e-05, "step": 44925 }, { "epoch": 5.843733749349974, "grad_norm": 0.0007670517661608756, "learning_rate": 1.6331946734262153e-05, "loss": 4.5631802640855314e-05, "step": 44950 }, { "epoch": 5.846983879355174, "grad_norm": 0.000623277563136071, "learning_rate": 1.630229673990771e-05, "loss": 4.5926272869110107e-05, "step": 44975 }, { "epoch": 5.850234009360374, "grad_norm": 0.0011902826372534037, "learning_rate": 1.627266065792236e-05, "loss": 5.539466626942158e-05, "step": 45000 }, { "epoch": 5.853484139365575, "grad_norm": 0.0013399514136835933, "learning_rate": 1.6243038535710366e-05, "loss": 5.582823883742094e-05, "step": 45025 }, { "epoch": 5.856734269370775, "grad_norm": 0.0009559797472320497, "learning_rate": 1.621343042065365e-05, "loss": 5.07558137178421e-05, "step": 45050 }, { "epoch": 5.859984399375975, "grad_norm": 0.0011914969654753804, "learning_rate": 1.6183836360111732e-05, "loss": 5.756758153438568e-05, "step": 45075 }, { "epoch": 5.863234529381176, "grad_norm": 0.0009328750311397016, "learning_rate": 1.6154256401421638e-05, "loss": 5.6522605009377e-05, "step": 45100 }, { "epoch": 5.8664846593863755, "grad_norm": 0.0028059748001396656, "learning_rate": 1.6124690591897856e-05, "loss": 5.388669203966856e-05, "step": 45125 }, { "epoch": 5.8697347893915754, "grad_norm": 0.0028132221195846796, "learning_rate": 1.6095138978832224e-05, "loss": 6.291760597378015e-05, "step": 45150 }, { "epoch": 5.872984919396776, "grad_norm": 0.0007538492209278047, "learning_rate": 1.6065601609493897e-05, "loss": 5.3359810262918476e-05, "step": 45175 }, { "epoch": 5.876235049401976, "grad_norm": 0.0008285692310892045, "learning_rate": 1.6036078531129218e-05, "loss": 5.511572584509849e-05, "step": 45200 }, { "epoch": 5.879485179407176, "grad_norm": 0.0007537577766925097, "learning_rate": 1.6006569790961686e-05, "loss": 6.129821296781302e-05, "step": 45225 }, { "epoch": 5.882735309412377, "grad_norm": 0.0013270736671984196, "learning_rate": 1.5977075436191866e-05, "loss": 5.301970522850752e-05, "step": 45250 }, { "epoch": 5.885985439417577, "grad_norm": 0.0013897874159738421, "learning_rate": 1.594759551399731e-05, "loss": 5.829334259033203e-05, "step": 45275 }, { "epoch": 5.889235569422777, "grad_norm": 0.0011161805596202612, "learning_rate": 1.5918130071532483e-05, "loss": 5.8640376664698124e-05, "step": 45300 }, { "epoch": 5.8924856994279775, "grad_norm": 0.0006761163240298629, "learning_rate": 1.5888679155928694e-05, "loss": 5.250411108136177e-05, "step": 45325 }, { "epoch": 5.895735829433177, "grad_norm": 0.0010602240217849612, "learning_rate": 1.5859242814294013e-05, "loss": 5.693878047168255e-05, "step": 45350 }, { "epoch": 5.898985959438377, "grad_norm": 0.0006510379607789218, "learning_rate": 1.5829821093713187e-05, "loss": 5.3747231140732767e-05, "step": 45375 }, { "epoch": 5.902236089443578, "grad_norm": 0.0005744985537603498, "learning_rate": 1.58004140412476e-05, "loss": 5.7163042947649954e-05, "step": 45400 }, { "epoch": 5.905486219448778, "grad_norm": 0.0011158339912071824, "learning_rate": 1.5771021703935156e-05, "loss": 5.281668156385422e-05, "step": 45425 }, { "epoch": 5.908736349453978, "grad_norm": 0.0021327738650143147, "learning_rate": 1.5741644128790223e-05, "loss": 6.039546802639961e-05, "step": 45450 }, { "epoch": 5.911986479459179, "grad_norm": 0.001834407332353294, "learning_rate": 1.571228136280356e-05, "loss": 5.143918562680483e-05, "step": 45475 }, { "epoch": 5.915236609464379, "grad_norm": 0.0007935308967716992, "learning_rate": 1.5682933452942238e-05, "loss": 5.64591633155942e-05, "step": 45500 }, { "epoch": 5.918486739469579, "grad_norm": 0.002537026535719633, "learning_rate": 1.5653600446149562e-05, "loss": 5.811158567667007e-05, "step": 45525 }, { "epoch": 5.921736869474779, "grad_norm": 0.0011298012686893344, "learning_rate": 1.5624282389345002e-05, "loss": 6.025033537298441e-05, "step": 45550 }, { "epoch": 5.924986999479979, "grad_norm": 0.0005638355505652726, "learning_rate": 1.5594979329424115e-05, "loss": 5.252854432910681e-05, "step": 45575 }, { "epoch": 5.928237129485179, "grad_norm": 0.001121621928177774, "learning_rate": 1.5565691313258467e-05, "loss": 6.342857610434293e-05, "step": 45600 }, { "epoch": 5.93148725949038, "grad_norm": 0.002177988411858678, "learning_rate": 1.553641838769556e-05, "loss": 6.375594995915889e-05, "step": 45625 }, { "epoch": 5.93473738949558, "grad_norm": 0.000697288487572223, "learning_rate": 1.5507160599558767e-05, "loss": 4.882913548499346e-05, "step": 45650 }, { "epoch": 5.93798751950078, "grad_norm": 0.0006555210566148162, "learning_rate": 1.547791799564724e-05, "loss": 5.582562182098627e-05, "step": 45675 }, { "epoch": 5.941237649505981, "grad_norm": 0.0011105132289230824, "learning_rate": 1.544869062273584e-05, "loss": 6.1004818417131903e-05, "step": 45700 }, { "epoch": 5.944487779511181, "grad_norm": 0.00050974334590137, "learning_rate": 1.5419478527575068e-05, "loss": 4.895668476819992e-05, "step": 45725 }, { "epoch": 5.9477379095163805, "grad_norm": 0.0022341220173984766, "learning_rate": 1.5390281756890995e-05, "loss": 5.823615007102489e-05, "step": 45750 }, { "epoch": 5.950988039521581, "grad_norm": 0.0018339826492592692, "learning_rate": 1.5361100357385174e-05, "loss": 6.302142050117254e-05, "step": 45775 }, { "epoch": 5.954238169526781, "grad_norm": 0.0009803585708141327, "learning_rate": 1.533193437573457e-05, "loss": 5.6852148845791816e-05, "step": 45800 }, { "epoch": 5.957488299531981, "grad_norm": 0.0005284277722239494, "learning_rate": 1.530278385859148e-05, "loss": 5.531609058380127e-05, "step": 45825 }, { "epoch": 5.960738429537182, "grad_norm": 0.0007458928739652038, "learning_rate": 1.5273648852583483e-05, "loss": 5.0207963213324546e-05, "step": 45850 }, { "epoch": 5.963988559542382, "grad_norm": 0.0013245365116745234, "learning_rate": 1.5244529404313334e-05, "loss": 5.4156063124537466e-05, "step": 45875 }, { "epoch": 5.967238689547582, "grad_norm": 0.0012080601882189512, "learning_rate": 1.5215425560358904e-05, "loss": 5.0886315293610095e-05, "step": 45900 }, { "epoch": 5.9704888195527825, "grad_norm": 0.0008415214833803475, "learning_rate": 1.5186337367273105e-05, "loss": 5.4693627171218394e-05, "step": 45925 }, { "epoch": 5.9737389495579825, "grad_norm": 0.0005115243257023394, "learning_rate": 1.5157264871583816e-05, "loss": 5.0804675556719306e-05, "step": 45950 }, { "epoch": 5.976989079563182, "grad_norm": 0.0003763347049243748, "learning_rate": 1.5128208119793805e-05, "loss": 4.892028868198395e-05, "step": 45975 }, { "epoch": 5.980239209568383, "grad_norm": 0.0015862856525927782, "learning_rate": 1.509916715838066e-05, "loss": 5.7299989275634286e-05, "step": 46000 }, { "epoch": 5.983489339573583, "grad_norm": 0.002948810113593936, "learning_rate": 1.5070142033796714e-05, "loss": 5.2129309624433516e-05, "step": 46025 }, { "epoch": 5.986739469578783, "grad_norm": 0.0010450729168951511, "learning_rate": 1.504113279246896e-05, "loss": 5.7538626715540883e-05, "step": 46050 }, { "epoch": 5.989989599583984, "grad_norm": 0.0005764640518464148, "learning_rate": 1.5012139480798987e-05, "loss": 5.119350738823414e-05, "step": 46075 }, { "epoch": 5.993239729589184, "grad_norm": 0.0007520103827118874, "learning_rate": 1.4983162145162911e-05, "loss": 5.104032810777426e-05, "step": 46100 }, { "epoch": 5.996489859594384, "grad_norm": 0.0006807005847804248, "learning_rate": 1.4954200831911286e-05, "loss": 4.5933490619063377e-05, "step": 46125 }, { "epoch": 5.999739989599584, "grad_norm": 0.001581962569616735, "learning_rate": 1.4925255587369035e-05, "loss": 5.1267072558403014e-05, "step": 46150 }, { "epoch": 6.002990119604784, "grad_norm": 0.0012374649522826076, "learning_rate": 1.4896326457835397e-05, "loss": 5.052815657109022e-05, "step": 46175 }, { "epoch": 6.006240249609984, "grad_norm": 0.0009138894383795559, "learning_rate": 1.4867413489583815e-05, "loss": 5.4765683598816396e-05, "step": 46200 }, { "epoch": 6.009490379615184, "grad_norm": 0.001971031306311488, "learning_rate": 1.4838516728861884e-05, "loss": 5.4955333471298215e-05, "step": 46225 }, { "epoch": 6.012740509620385, "grad_norm": 0.0004724987084046006, "learning_rate": 1.480963622189128e-05, "loss": 5.1706158556044104e-05, "step": 46250 }, { "epoch": 6.015990639625585, "grad_norm": 0.0016419119201600552, "learning_rate": 1.4780772014867677e-05, "loss": 4.929132759571076e-05, "step": 46275 }, { "epoch": 6.019240769630785, "grad_norm": 0.0006701303645968437, "learning_rate": 1.475192415396068e-05, "loss": 5.488833412528038e-05, "step": 46300 }, { "epoch": 6.022490899635986, "grad_norm": 0.00042553534149192274, "learning_rate": 1.4723092685313744e-05, "loss": 5.728942342102528e-05, "step": 46325 }, { "epoch": 6.0257410296411855, "grad_norm": 0.0009560334146954119, "learning_rate": 1.4694277655044103e-05, "loss": 6.337665487080812e-05, "step": 46350 }, { "epoch": 6.028991159646385, "grad_norm": 0.0011956730158999562, "learning_rate": 1.4665479109242696e-05, "loss": 5.3428104147315023e-05, "step": 46375 }, { "epoch": 6.032241289651586, "grad_norm": 0.0017137513495981693, "learning_rate": 1.4636697093974108e-05, "loss": 5.2756345830857753e-05, "step": 46400 }, { "epoch": 6.035491419656786, "grad_norm": 0.0012260169023647904, "learning_rate": 1.4607931655276463e-05, "loss": 5.90510293841362e-05, "step": 46425 }, { "epoch": 6.038741549661986, "grad_norm": 0.0008922087145037949, "learning_rate": 1.4579182839161379e-05, "loss": 5.9839952737092975e-05, "step": 46450 }, { "epoch": 6.041991679667187, "grad_norm": 0.0007592141046188772, "learning_rate": 1.4550450691613898e-05, "loss": 5.7964874431490896e-05, "step": 46475 }, { "epoch": 6.045241809672387, "grad_norm": 0.00118032016325742, "learning_rate": 1.4521735258592365e-05, "loss": 5.47326635569334e-05, "step": 46500 }, { "epoch": 6.048491939677587, "grad_norm": 0.0009195404127240181, "learning_rate": 1.4493036586028435e-05, "loss": 5.391910206526518e-05, "step": 46525 }, { "epoch": 6.0517420696827875, "grad_norm": 0.0008804433746263385, "learning_rate": 1.446435471982691e-05, "loss": 5.4110162891447545e-05, "step": 46550 }, { "epoch": 6.054992199687987, "grad_norm": 0.001282447250559926, "learning_rate": 1.4435689705865751e-05, "loss": 4.844974726438522e-05, "step": 46575 }, { "epoch": 6.058242329693187, "grad_norm": 0.0006766556762158871, "learning_rate": 1.4407041589995924e-05, "loss": 5.6384094059467315e-05, "step": 46600 }, { "epoch": 6.061492459698388, "grad_norm": 0.0007930307765491307, "learning_rate": 1.437841041804141e-05, "loss": 4.7800848260521886e-05, "step": 46625 }, { "epoch": 6.064742589703588, "grad_norm": 0.0012145201908424497, "learning_rate": 1.434979623579902e-05, "loss": 4.694397561252117e-05, "step": 46650 }, { "epoch": 6.067992719708788, "grad_norm": 0.0014720909530296922, "learning_rate": 1.4321199089038467e-05, "loss": 5.448969546705484e-05, "step": 46675 }, { "epoch": 6.071242849713989, "grad_norm": 0.000679254939313978, "learning_rate": 1.4292619023502152e-05, "loss": 5.103331059217453e-05, "step": 46700 }, { "epoch": 6.074492979719189, "grad_norm": 0.0013445024378597736, "learning_rate": 1.4264056084905203e-05, "loss": 5.010082852095366e-05, "step": 46725 }, { "epoch": 6.077743109724389, "grad_norm": 0.004307881463319063, "learning_rate": 1.4235510318935311e-05, "loss": 5.093471147119999e-05, "step": 46750 }, { "epoch": 6.080993239729589, "grad_norm": 0.0012630269629880786, "learning_rate": 1.4206981771252726e-05, "loss": 5.346503108739853e-05, "step": 46775 }, { "epoch": 6.084243369734789, "grad_norm": 0.001210701302625239, "learning_rate": 1.417847048749016e-05, "loss": 5.036811344325542e-05, "step": 46800 }, { "epoch": 6.087493499739989, "grad_norm": 0.0005595847615040839, "learning_rate": 1.4149976513252677e-05, "loss": 5.4655736312270166e-05, "step": 46825 }, { "epoch": 6.09074362974519, "grad_norm": 0.000959868892095983, "learning_rate": 1.4121499894117695e-05, "loss": 4.79230796918273e-05, "step": 46850 }, { "epoch": 6.09399375975039, "grad_norm": 0.0008491180487908423, "learning_rate": 1.4093040675634832e-05, "loss": 5.639640148729086e-05, "step": 46875 }, { "epoch": 6.09724388975559, "grad_norm": 0.0016768217319622636, "learning_rate": 1.406459890332592e-05, "loss": 5.8293580077588556e-05, "step": 46900 }, { "epoch": 6.100494019760791, "grad_norm": 0.0016112140147015452, "learning_rate": 1.4036174622684828e-05, "loss": 5.103891715407372e-05, "step": 46925 }, { "epoch": 6.103744149765991, "grad_norm": 0.0009003854938782752, "learning_rate": 1.4007767879177502e-05, "loss": 4.7347662039101125e-05, "step": 46950 }, { "epoch": 6.1069942797711905, "grad_norm": 0.0007181945838965476, "learning_rate": 1.3979378718241793e-05, "loss": 4.894330631941557e-05, "step": 46975 }, { "epoch": 6.110244409776391, "grad_norm": 0.0011972918873652816, "learning_rate": 1.3951007185287458e-05, "loss": 5.4634641855955124e-05, "step": 47000 }, { "epoch": 6.113494539781591, "grad_norm": 0.0005784347304143012, "learning_rate": 1.3922653325696028e-05, "loss": 5.294144619256258e-05, "step": 47025 }, { "epoch": 6.116744669786791, "grad_norm": 0.0008896737126633525, "learning_rate": 1.3894317184820807e-05, "loss": 5.0346250645816326e-05, "step": 47050 }, { "epoch": 6.119994799791992, "grad_norm": 0.0008720190380699933, "learning_rate": 1.3865998807986707e-05, "loss": 5.354752298444509e-05, "step": 47075 }, { "epoch": 6.123244929797192, "grad_norm": 0.000674187031108886, "learning_rate": 1.3837698240490271e-05, "loss": 5.313417874276638e-05, "step": 47100 }, { "epoch": 6.126495059802392, "grad_norm": 0.0009301781537942588, "learning_rate": 1.3809415527599518e-05, "loss": 5.831962451338768e-05, "step": 47125 }, { "epoch": 6.1297451898075925, "grad_norm": 0.0007834744756110013, "learning_rate": 1.3781150714553936e-05, "loss": 5.779194179922342e-05, "step": 47150 }, { "epoch": 6.1329953198127924, "grad_norm": 0.0013891003327444196, "learning_rate": 1.375290384656436e-05, "loss": 5.626036785542965e-05, "step": 47175 }, { "epoch": 6.136245449817992, "grad_norm": 0.0009299811790697277, "learning_rate": 1.3724674968812946e-05, "loss": 6.232800893485546e-05, "step": 47200 }, { "epoch": 6.139495579823193, "grad_norm": 0.0007591965841129422, "learning_rate": 1.3696464126453035e-05, "loss": 5.328999366611242e-05, "step": 47225 }, { "epoch": 6.142745709828393, "grad_norm": 0.0019203375559300184, "learning_rate": 1.3668271364609169e-05, "loss": 5.660127848386765e-05, "step": 47250 }, { "epoch": 6.145995839833593, "grad_norm": 0.0024457117542624474, "learning_rate": 1.3640096728376922e-05, "loss": 5.0819846801459786e-05, "step": 47275 }, { "epoch": 6.149245969838794, "grad_norm": 0.0008455108618363738, "learning_rate": 1.3611940262822902e-05, "loss": 5.232867319136858e-05, "step": 47300 }, { "epoch": 6.152496099843994, "grad_norm": 0.0007656101370230317, "learning_rate": 1.358380201298467e-05, "loss": 5.268223583698273e-05, "step": 47325 }, { "epoch": 6.155746229849194, "grad_norm": 0.0005016038194298744, "learning_rate": 1.3555682023870592e-05, "loss": 5.126280710101127e-05, "step": 47350 }, { "epoch": 6.158996359854394, "grad_norm": 0.0020711561664938927, "learning_rate": 1.3527580340459888e-05, "loss": 5.504073575139046e-05, "step": 47375 }, { "epoch": 6.162246489859594, "grad_norm": 0.0009334366768598557, "learning_rate": 1.349949700770245e-05, "loss": 5.7264440692961215e-05, "step": 47400 }, { "epoch": 6.165496619864794, "grad_norm": 0.0004539091023616493, "learning_rate": 1.3471432070518853e-05, "loss": 5.8703627437353135e-05, "step": 47425 }, { "epoch": 6.168746749869995, "grad_norm": 0.0007016155286692083, "learning_rate": 1.3443385573800215e-05, "loss": 5.2767740562558174e-05, "step": 47450 }, { "epoch": 6.171996879875195, "grad_norm": 0.0012280548689886928, "learning_rate": 1.341535756240819e-05, "loss": 5.750204436480999e-05, "step": 47475 }, { "epoch": 6.175247009880395, "grad_norm": 0.0006182798533700407, "learning_rate": 1.3387348081174833e-05, "loss": 5.185624118894338e-05, "step": 47500 }, { "epoch": 6.178497139885596, "grad_norm": 0.0005243502091616392, "learning_rate": 1.335935717490259e-05, "loss": 5.0792396068572996e-05, "step": 47525 }, { "epoch": 6.181747269890796, "grad_norm": 0.0016843966441228986, "learning_rate": 1.3331384888364163e-05, "loss": 5.189579911530018e-05, "step": 47550 }, { "epoch": 6.1849973998959955, "grad_norm": 0.00048324925592169166, "learning_rate": 1.3303431266302502e-05, "loss": 5.267609842121601e-05, "step": 47575 }, { "epoch": 6.188247529901196, "grad_norm": 0.0007862239144742489, "learning_rate": 1.3275496353430671e-05, "loss": 4.791575483977795e-05, "step": 47600 }, { "epoch": 6.191497659906396, "grad_norm": 0.0015142271295189857, "learning_rate": 1.3247580194431844e-05, "loss": 5.9403441846370696e-05, "step": 47625 }, { "epoch": 6.194747789911596, "grad_norm": 0.00056993163889274, "learning_rate": 1.321968283395916e-05, "loss": 4.800387192517519e-05, "step": 47650 }, { "epoch": 6.197997919916797, "grad_norm": 0.0010491295251995325, "learning_rate": 1.3191804316635726e-05, "loss": 5.9736697003245355e-05, "step": 47675 }, { "epoch": 6.201248049921997, "grad_norm": 0.0007392332190647721, "learning_rate": 1.3163944687054463e-05, "loss": 4.963223356753588e-05, "step": 47700 }, { "epoch": 6.204498179927197, "grad_norm": 0.001343795913271606, "learning_rate": 1.3136103989778137e-05, "loss": 5.0024427473545074e-05, "step": 47725 }, { "epoch": 6.207748309932398, "grad_norm": 0.0017566962633281946, "learning_rate": 1.3108282269339173e-05, "loss": 5.503607913851738e-05, "step": 47750 }, { "epoch": 6.2109984399375975, "grad_norm": 0.0010497489711269736, "learning_rate": 1.308047957023969e-05, "loss": 5.7456791400909426e-05, "step": 47775 }, { "epoch": 6.214248569942797, "grad_norm": 0.0011104304576292634, "learning_rate": 1.3052695936951342e-05, "loss": 5.048078950494528e-05, "step": 47800 }, { "epoch": 6.217498699947998, "grad_norm": 0.0008966656750999391, "learning_rate": 1.3024931413915317e-05, "loss": 4.594760481268167e-05, "step": 47825 }, { "epoch": 6.220748829953198, "grad_norm": 0.0010476027382537723, "learning_rate": 1.299718604554223e-05, "loss": 5.026077851653099e-05, "step": 47850 }, { "epoch": 6.223998959958398, "grad_norm": 0.001833115704357624, "learning_rate": 1.296945987621203e-05, "loss": 6.138136610388756e-05, "step": 47875 }, { "epoch": 6.227249089963599, "grad_norm": 0.0019242517882958055, "learning_rate": 1.2941752950274003e-05, "loss": 6.104237399995327e-05, "step": 47900 }, { "epoch": 6.230499219968799, "grad_norm": 0.0008576049585826695, "learning_rate": 1.2914065312046602e-05, "loss": 4.5974766835570334e-05, "step": 47925 }, { "epoch": 6.233749349973999, "grad_norm": 0.0006195487221702933, "learning_rate": 1.2886397005817474e-05, "loss": 5.7273879647254944e-05, "step": 47950 }, { "epoch": 6.2369994799791995, "grad_norm": 0.0007689455524086952, "learning_rate": 1.2858748075843307e-05, "loss": 5.02380495890975e-05, "step": 47975 }, { "epoch": 6.240249609984399, "grad_norm": 0.0017887633293867111, "learning_rate": 1.2831118566349834e-05, "loss": 4.9244402907788755e-05, "step": 48000 }, { "epoch": 6.243499739989599, "grad_norm": 0.000808796554338187, "learning_rate": 1.280350852153168e-05, "loss": 4.917326383292675e-05, "step": 48025 }, { "epoch": 6.2467498699948, "grad_norm": 0.00040879345033317804, "learning_rate": 1.277591798555238e-05, "loss": 5.6687667965888975e-05, "step": 48050 }, { "epoch": 6.25, "grad_norm": 0.001766907051205635, "learning_rate": 1.2748347002544219e-05, "loss": 5.940377712249756e-05, "step": 48075 }, { "epoch": 6.2532501300052, "grad_norm": 0.0008571782382205129, "learning_rate": 1.2720795616608256e-05, "loss": 5.4761692881584166e-05, "step": 48100 }, { "epoch": 6.256500260010401, "grad_norm": 0.0006261870730668306, "learning_rate": 1.2693263871814155e-05, "loss": 5.5836727842688563e-05, "step": 48125 }, { "epoch": 6.259750390015601, "grad_norm": 0.002641534199938178, "learning_rate": 1.2665751812200197e-05, "loss": 5.081783048808575e-05, "step": 48150 }, { "epoch": 6.2630005200208005, "grad_norm": 0.0008031228207983077, "learning_rate": 1.2638259481773162e-05, "loss": 4.835553932934999e-05, "step": 48175 }, { "epoch": 6.266250650026001, "grad_norm": 0.0012399654369801283, "learning_rate": 1.261078692450826e-05, "loss": 5.459531210362911e-05, "step": 48200 }, { "epoch": 6.269500780031201, "grad_norm": 0.001342507777735591, "learning_rate": 1.2583334184349111e-05, "loss": 5.181224551051855e-05, "step": 48225 }, { "epoch": 6.272750910036401, "grad_norm": 0.0008894753409549594, "learning_rate": 1.255590130520759e-05, "loss": 4.977792035788298e-05, "step": 48250 }, { "epoch": 6.276001040041602, "grad_norm": 0.0009034202666953206, "learning_rate": 1.2528488330963844e-05, "loss": 5.268285050988197e-05, "step": 48275 }, { "epoch": 6.279251170046802, "grad_norm": 0.0013463840587064624, "learning_rate": 1.2501095305466143e-05, "loss": 5.88150043040514e-05, "step": 48300 }, { "epoch": 6.279251170046802, "eval_loss": 0.00021980605379212648, "eval_runtime": 8.4953, "eval_samples_per_second": 588.563, "eval_steps_per_second": 4.709, "step": 48300 }, { "epoch": 6.279251170046802, "eval_holdout_avg_strict_f1": 0.20306499772820824, "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": 0.6993993993993993, "eval_holdout_nemotron_pii_strict_f1": 0.5678635090399796, "eval_holdout_open_pii_masking_500k_strict_f1": 0.493978641217905, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.47247342535300657, "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": 6.282501300052002, "grad_norm": 0.0009723958210088313, "learning_rate": 1.2473722272530893e-05, "loss": 4.986293148249388e-05, "step": 48325 }, { "epoch": 6.285751430057203, "grad_norm": 0.0008662575855851173, "learning_rate": 1.2446369275942474e-05, "loss": 5.218135192990303e-05, "step": 48350 }, { "epoch": 6.2890015600624025, "grad_norm": 0.0009377783862873912, "learning_rate": 1.2419036359453257e-05, "loss": 6.170285865664482e-05, "step": 48375 }, { "epoch": 6.292251690067602, "grad_norm": 0.0009352407651022077, "learning_rate": 1.2391723566783458e-05, "loss": 4.8859925009310245e-05, "step": 48400 }, { "epoch": 6.295501820072803, "grad_norm": 0.0008908355957828462, "learning_rate": 1.2364430941621142e-05, "loss": 5.229210015386343e-05, "step": 48425 }, { "epoch": 6.298751950078003, "grad_norm": 0.0011844635009765625, "learning_rate": 1.2337158527622072e-05, "loss": 5.3475331515073774e-05, "step": 48450 }, { "epoch": 6.302002080083203, "grad_norm": 0.0003706692368723452, "learning_rate": 1.2309906368409732e-05, "loss": 4.749213345348835e-05, "step": 48475 }, { "epoch": 6.305252210088404, "grad_norm": 0.0009108723024837673, "learning_rate": 1.2282674507575157e-05, "loss": 5.9289149940013884e-05, "step": 48500 }, { "epoch": 6.308502340093604, "grad_norm": 0.000819518172647804, "learning_rate": 1.2255462988676959e-05, "loss": 5.131556652486324e-05, "step": 48525 }, { "epoch": 6.311752470098804, "grad_norm": 0.001111007877625525, "learning_rate": 1.222827185524117e-05, "loss": 5.3537050262093545e-05, "step": 48550 }, { "epoch": 6.3150026001040045, "grad_norm": 0.0008592934464104474, "learning_rate": 1.2201101150761257e-05, "loss": 5.600704345852137e-05, "step": 48575 }, { "epoch": 6.318252730109204, "grad_norm": 0.0016190868336707354, "learning_rate": 1.2173950918697968e-05, "loss": 5.317042116075754e-05, "step": 48600 }, { "epoch": 6.321502860114404, "grad_norm": 0.0005172528908587992, "learning_rate": 1.2146821202479348e-05, "loss": 5.593968089669943e-05, "step": 48625 }, { "epoch": 6.324752990119605, "grad_norm": 0.0007290459470823407, "learning_rate": 1.211971204550058e-05, "loss": 5.2886949852108956e-05, "step": 48650 }, { "epoch": 6.328003120124805, "grad_norm": 0.001188524765893817, "learning_rate": 1.2092623491123994e-05, "loss": 5.6732012890279296e-05, "step": 48675 }, { "epoch": 6.331253250130005, "grad_norm": 0.0006830750498920679, "learning_rate": 1.2065555582678969e-05, "loss": 5.768478848040104e-05, "step": 48700 }, { "epoch": 6.334503380135206, "grad_norm": 0.001155124045908451, "learning_rate": 1.2038508363461826e-05, "loss": 5.4220580495893954e-05, "step": 48725 }, { "epoch": 6.337753510140406, "grad_norm": 0.0012975187273696065, "learning_rate": 1.2011481876735831e-05, "loss": 5.0848005339503286e-05, "step": 48750 }, { "epoch": 6.341003640145606, "grad_norm": 0.0008511929190717638, "learning_rate": 1.198447616573105e-05, "loss": 5.065632052719593e-05, "step": 48775 }, { "epoch": 6.344253770150806, "grad_norm": 0.0005204291082918644, "learning_rate": 1.1957491273644362e-05, "loss": 5.1365350373089314e-05, "step": 48800 }, { "epoch": 6.347503900156006, "grad_norm": 0.000926018925383687, "learning_rate": 1.1930527243639294e-05, "loss": 5.231708288192749e-05, "step": 48825 }, { "epoch": 6.350754030161206, "grad_norm": 0.000474592816317454, "learning_rate": 1.1903584118846053e-05, "loss": 4.792127292603254e-05, "step": 48850 }, { "epoch": 6.354004160166407, "grad_norm": 0.0008394842152483761, "learning_rate": 1.1876661942361363e-05, "loss": 5.290365312248468e-05, "step": 48875 }, { "epoch": 6.357254290171607, "grad_norm": 0.0010855448199436069, "learning_rate": 1.1849760757248482e-05, "loss": 4.7449623234570023e-05, "step": 48900 }, { "epoch": 6.360504420176807, "grad_norm": 0.0008439780212938786, "learning_rate": 1.1822880606537051e-05, "loss": 5.104629322886467e-05, "step": 48925 }, { "epoch": 6.363754550182008, "grad_norm": 0.0009840527782216668, "learning_rate": 1.1796021533223101e-05, "loss": 5.209230352193117e-05, "step": 48950 }, { "epoch": 6.3670046801872076, "grad_norm": 0.0006465347833000124, "learning_rate": 1.1769183580268917e-05, "loss": 5.163868423551321e-05, "step": 48975 }, { "epoch": 6.3702548101924075, "grad_norm": 0.0005550122004933655, "learning_rate": 1.1742366790603033e-05, "loss": 4.52796695753932e-05, "step": 49000 }, { "epoch": 6.373504940197608, "grad_norm": 0.0007293246453627944, "learning_rate": 1.1715571207120097e-05, "loss": 5.652129650115967e-05, "step": 49025 }, { "epoch": 6.376755070202808, "grad_norm": 0.0006662892992608249, "learning_rate": 1.1688796872680874e-05, "loss": 5.634432658553124e-05, "step": 49050 }, { "epoch": 6.380005200208008, "grad_norm": 0.0005172014934942126, "learning_rate": 1.16620438301121e-05, "loss": 5.780817475169897e-05, "step": 49075 }, { "epoch": 6.383255330213209, "grad_norm": 0.0008618307183496654, "learning_rate": 1.1635312122206496e-05, "loss": 6.105607841163873e-05, "step": 49100 }, { "epoch": 6.386505460218409, "grad_norm": 0.00380233908072114, "learning_rate": 1.1608601791722614e-05, "loss": 5.726946517825127e-05, "step": 49125 }, { "epoch": 6.389755590223609, "grad_norm": 0.000504620373249054, "learning_rate": 1.158191288138486e-05, "loss": 5.196085199713707e-05, "step": 49150 }, { "epoch": 6.3930057202288095, "grad_norm": 0.0009074567351490259, "learning_rate": 1.1555245433883322e-05, "loss": 5.9245391748845575e-05, "step": 49175 }, { "epoch": 6.396255850234009, "grad_norm": 0.0006184721132740378, "learning_rate": 1.1528599491873812e-05, "loss": 4.4547030702233316e-05, "step": 49200 }, { "epoch": 6.399505980239209, "grad_norm": 0.0014585874741896987, "learning_rate": 1.1501975097977696e-05, "loss": 4.7586807049810886e-05, "step": 49225 }, { "epoch": 6.40275611024441, "grad_norm": 0.000947857741266489, "learning_rate": 1.1475372294781905e-05, "loss": 4.761990625411272e-05, "step": 49250 }, { "epoch": 6.40600624024961, "grad_norm": 0.0007337559945881367, "learning_rate": 1.1448791124838834e-05, "loss": 5.466753151267767e-05, "step": 49275 }, { "epoch": 6.40925637025481, "grad_norm": 0.0009100241004489362, "learning_rate": 1.1422231630666243e-05, "loss": 4.865573719143867e-05, "step": 49300 }, { "epoch": 6.412506500260011, "grad_norm": 0.0010067097609862685, "learning_rate": 1.1395693854747263e-05, "loss": 4.9660182558000084e-05, "step": 49325 }, { "epoch": 6.415756630265211, "grad_norm": 0.0006972657283768058, "learning_rate": 1.1369177839530248e-05, "loss": 5.0599314272403716e-05, "step": 49350 }, { "epoch": 6.419006760270411, "grad_norm": 0.0004099777725059539, "learning_rate": 1.1342683627428777e-05, "loss": 5.1275333389639856e-05, "step": 49375 }, { "epoch": 6.422256890275611, "grad_norm": 0.0011731521226465702, "learning_rate": 1.131621126082152e-05, "loss": 5.212320014834404e-05, "step": 49400 }, { "epoch": 6.425507020280811, "grad_norm": 0.0004537368076853454, "learning_rate": 1.1289760782052241e-05, "loss": 5.102592520415783e-05, "step": 49425 }, { "epoch": 6.428757150286011, "grad_norm": 0.000945354753639549, "learning_rate": 1.126333223342966e-05, "loss": 5.2614114247262477e-05, "step": 49450 }, { "epoch": 6.432007280291212, "grad_norm": 0.0009774493519216776, "learning_rate": 1.123692565722745e-05, "loss": 5.589960142970085e-05, "step": 49475 }, { "epoch": 6.435257410296412, "grad_norm": 0.0007189423777163029, "learning_rate": 1.1210541095684104e-05, "loss": 4.661910235881805e-05, "step": 49500 }, { "epoch": 6.438507540301612, "grad_norm": 0.0012313470942899585, "learning_rate": 1.1184178591002936e-05, "loss": 5.0068972632288934e-05, "step": 49525 }, { "epoch": 6.441757670306813, "grad_norm": 0.0006813606014475226, "learning_rate": 1.1157838185351948e-05, "loss": 5.321679636836052e-05, "step": 49550 }, { "epoch": 6.445007800312013, "grad_norm": 0.0004522796079982072, "learning_rate": 1.1131519920863826e-05, "loss": 5.187105853110552e-05, "step": 49575 }, { "epoch": 6.4482579303172125, "grad_norm": 0.0007867637323215604, "learning_rate": 1.1105223839635801e-05, "loss": 5.514636170119047e-05, "step": 49600 }, { "epoch": 6.451508060322413, "grad_norm": 0.0010232602944597602, "learning_rate": 1.1078949983729661e-05, "loss": 4.953653551638126e-05, "step": 49625 }, { "epoch": 6.454758190327613, "grad_norm": 0.0009344135178253055, "learning_rate": 1.105269839517161e-05, "loss": 6.110776215791703e-05, "step": 49650 }, { "epoch": 6.458008320332813, "grad_norm": 0.0005648386431857944, "learning_rate": 1.1026469115952265e-05, "loss": 5.287195090204477e-05, "step": 49675 }, { "epoch": 6.461258450338014, "grad_norm": 0.0013120878720656037, "learning_rate": 1.1000262188026525e-05, "loss": 5.4909246973693374e-05, "step": 49700 }, { "epoch": 6.464508580343214, "grad_norm": 0.0008301194757223129, "learning_rate": 1.0974077653313572e-05, "loss": 4.911462310701609e-05, "step": 49725 }, { "epoch": 6.467758710348414, "grad_norm": 0.0013627648586407304, "learning_rate": 1.0947915553696742e-05, "loss": 5.175200756639242e-05, "step": 49750 }, { "epoch": 6.471008840353614, "grad_norm": 0.0014881057431921363, "learning_rate": 1.092177593102349e-05, "loss": 4.9665956757962705e-05, "step": 49775 }, { "epoch": 6.4742589703588145, "grad_norm": 0.0006165856029838324, "learning_rate": 1.0895658827105335e-05, "loss": 4.70941374078393e-05, "step": 49800 }, { "epoch": 6.477509100364014, "grad_norm": 0.0009103734046220779, "learning_rate": 1.0869564283717748e-05, "loss": 5.3128520958125593e-05, "step": 49825 }, { "epoch": 6.480759230369214, "grad_norm": 0.001776489894837141, "learning_rate": 1.0843492342600148e-05, "loss": 5.466731730848551e-05, "step": 49850 }, { "epoch": 6.484009360374415, "grad_norm": 0.0008382052183151245, "learning_rate": 1.0817443045455766e-05, "loss": 4.983595106750727e-05, "step": 49875 }, { "epoch": 6.487259490379615, "grad_norm": 0.0002927955356426537, "learning_rate": 1.0791416433951642e-05, "loss": 4.307393915951252e-05, "step": 49900 }, { "epoch": 6.490509620384815, "grad_norm": 0.0006147593376226723, "learning_rate": 1.0765412549718506e-05, "loss": 4.8834788613021375e-05, "step": 49925 }, { "epoch": 6.493759750390016, "grad_norm": 0.0012819243129342794, "learning_rate": 1.0739431434350756e-05, "loss": 5.180512089282274e-05, "step": 49950 }, { "epoch": 6.497009880395216, "grad_norm": 0.0011393764289095998, "learning_rate": 1.0713473129406342e-05, "loss": 5.038310773670673e-05, "step": 49975 }, { "epoch": 6.500260010400416, "grad_norm": 0.000777397130150348, "learning_rate": 1.0687537676406768e-05, "loss": 5.257781129330397e-05, "step": 50000 }, { "epoch": 6.503510140405616, "grad_norm": 0.00054601498413831, "learning_rate": 1.0661625116836938e-05, "loss": 5.108096171170473e-05, "step": 50025 }, { "epoch": 6.506760270410816, "grad_norm": 0.00037357318797148764, "learning_rate": 1.0635735492145171e-05, "loss": 4.8436527140438554e-05, "step": 50050 }, { "epoch": 6.510010400416016, "grad_norm": 0.00044461688958108425, "learning_rate": 1.0609868843743104e-05, "loss": 4.606904927641153e-05, "step": 50075 }, { "epoch": 6.513260530421217, "grad_norm": 0.0010972999734804034, "learning_rate": 1.0584025213005588e-05, "loss": 5.220580846071243e-05, "step": 50100 }, { "epoch": 6.516510660426417, "grad_norm": 0.000971423287410289, "learning_rate": 1.0558204641270697e-05, "loss": 5.218916106969118e-05, "step": 50125 }, { "epoch": 6.519760790431617, "grad_norm": 0.0011062498670071363, "learning_rate": 1.0532407169839581e-05, "loss": 5.5080661550164226e-05, "step": 50150 }, { "epoch": 6.523010920436818, "grad_norm": 0.001248106244020164, "learning_rate": 1.050663283997648e-05, "loss": 5.207579582929611e-05, "step": 50175 }, { "epoch": 6.5262610504420175, "grad_norm": 0.0008872096659615636, "learning_rate": 1.0480881692908582e-05, "loss": 5.191338248550892e-05, "step": 50200 }, { "epoch": 6.5295111804472175, "grad_norm": 0.0005655499990098178, "learning_rate": 1.045515376982602e-05, "loss": 4.5283748768270016e-05, "step": 50225 }, { "epoch": 6.532761310452418, "grad_norm": 0.0009184451773762703, "learning_rate": 1.0429449111881761e-05, "loss": 5.5114086717367175e-05, "step": 50250 }, { "epoch": 6.536011440457618, "grad_norm": 0.0006520917522720993, "learning_rate": 1.0403767760191579e-05, "loss": 4.5382659882307055e-05, "step": 50275 }, { "epoch": 6.539261570462818, "grad_norm": 0.0008992376970127225, "learning_rate": 1.0378109755833938e-05, "loss": 5.191691685467958e-05, "step": 50300 }, { "epoch": 6.542511700468019, "grad_norm": 0.0011201618472114205, "learning_rate": 1.0352475139849993e-05, "loss": 5.629440769553185e-05, "step": 50325 }, { "epoch": 6.545761830473219, "grad_norm": 0.0004670462221838534, "learning_rate": 1.0326863953243448e-05, "loss": 5.4356176406145096e-05, "step": 50350 }, { "epoch": 6.549011960478419, "grad_norm": 0.0016588082071393728, "learning_rate": 1.0301276236980578e-05, "loss": 5.4260496981441974e-05, "step": 50375 }, { "epoch": 6.5522620904836195, "grad_norm": 0.0011788501869887114, "learning_rate": 1.0275712031990068e-05, "loss": 5.5396570824086664e-05, "step": 50400 }, { "epoch": 6.555512220488819, "grad_norm": 0.0003991807752754539, "learning_rate": 1.0250171379163035e-05, "loss": 5.2642743103206154e-05, "step": 50425 }, { "epoch": 6.558762350494019, "grad_norm": 0.000275289494311437, "learning_rate": 1.0224654319352888e-05, "loss": 4.832143429666758e-05, "step": 50450 }, { "epoch": 6.56201248049922, "grad_norm": 0.001332565094344318, "learning_rate": 1.0199160893375339e-05, "loss": 5.5184760130941866e-05, "step": 50475 }, { "epoch": 6.56526261050442, "grad_norm": 0.0006848552147857845, "learning_rate": 1.0173691142008254e-05, "loss": 5.620783194899559e-05, "step": 50500 }, { "epoch": 6.56851274050962, "grad_norm": 0.0011175863910466433, "learning_rate": 1.0148245105991666e-05, "loss": 5.078235641121864e-05, "step": 50525 }, { "epoch": 6.571762870514821, "grad_norm": 0.0016618550289422274, "learning_rate": 1.0122822826027644e-05, "loss": 4.93824016302824e-05, "step": 50550 }, { "epoch": 6.575013000520021, "grad_norm": 0.0007669252809137106, "learning_rate": 1.0097424342780288e-05, "loss": 5.086067598313093e-05, "step": 50575 }, { "epoch": 6.578263130525221, "grad_norm": 0.0006938986480236053, "learning_rate": 1.0072049696875602e-05, "loss": 4.979620222002268e-05, "step": 50600 }, { "epoch": 6.581513260530421, "grad_norm": 0.0006569888792000711, "learning_rate": 1.0046698928901488e-05, "loss": 5.524772685021162e-05, "step": 50625 }, { "epoch": 6.584763390535621, "grad_norm": 0.0007797977887094021, "learning_rate": 1.002137207940765e-05, "loss": 4.758282098919153e-05, "step": 50650 }, { "epoch": 6.588013520540821, "grad_norm": 0.0013503392692655325, "learning_rate": 9.996069188905512e-06, "loss": 4.8612328246235844e-05, "step": 50675 }, { "epoch": 6.591263650546022, "grad_norm": 0.0005067220772616565, "learning_rate": 9.970790297868206e-06, "loss": 4.199960269033909e-05, "step": 50700 }, { "epoch": 6.594513780551222, "grad_norm": 0.0011761673958972096, "learning_rate": 9.945535446730447e-06, "loss": 4.403208382427692e-05, "step": 50725 }, { "epoch": 6.597763910556422, "grad_norm": 0.0008753379806876183, "learning_rate": 9.92030467588852e-06, "loss": 4.6119438484311106e-05, "step": 50750 }, { "epoch": 6.601014040561623, "grad_norm": 0.0007041359203867614, "learning_rate": 9.89509802570017e-06, "loss": 5.357351154088974e-05, "step": 50775 }, { "epoch": 6.604264170566823, "grad_norm": 0.0009907010244205594, "learning_rate": 9.869915536484586e-06, "loss": 5.310242995619774e-05, "step": 50800 }, { "epoch": 6.6075143005720225, "grad_norm": 0.0009675812325440347, "learning_rate": 9.844757248522279e-06, "loss": 5.300640128552914e-05, "step": 50825 }, { "epoch": 6.610764430577223, "grad_norm": 0.0014275657013058662, "learning_rate": 9.81962320205509e-06, "loss": 5.8087925426661966e-05, "step": 50850 }, { "epoch": 6.614014560582423, "grad_norm": 0.0012523540062829852, "learning_rate": 9.794513437286037e-06, "loss": 5.714151076972485e-05, "step": 50875 }, { "epoch": 6.617264690587623, "grad_norm": 0.0011984722223132849, "learning_rate": 9.769427994379343e-06, "loss": 5.3068120032548904e-05, "step": 50900 }, { "epoch": 6.620514820592824, "grad_norm": 0.0009554311400279403, "learning_rate": 9.74436691346029e-06, "loss": 5.476878955960274e-05, "step": 50925 }, { "epoch": 6.623764950598024, "grad_norm": 0.0007628744933754206, "learning_rate": 9.719330234615227e-06, "loss": 5.1487311720848085e-05, "step": 50950 }, { "epoch": 6.627015080603224, "grad_norm": 0.0005077653913758695, "learning_rate": 9.694317997891427e-06, "loss": 5.384529009461403e-05, "step": 50975 }, { "epoch": 6.6302652106084246, "grad_norm": 0.0009919082513079047, "learning_rate": 9.66933024329712e-06, "loss": 5.3829210810363295e-05, "step": 51000 }, { "epoch": 6.6335153406136245, "grad_norm": 0.0020310399122536182, "learning_rate": 9.644367010801325e-06, "loss": 5.0482768565416335e-05, "step": 51025 }, { "epoch": 6.636765470618824, "grad_norm": 0.0007473555160686374, "learning_rate": 9.619428340333875e-06, "loss": 5.156612489372492e-05, "step": 51050 }, { "epoch": 6.640015600624025, "grad_norm": 0.0021099038422107697, "learning_rate": 9.594514271785288e-06, "loss": 5.590208806097508e-05, "step": 51075 }, { "epoch": 6.643265730629225, "grad_norm": 0.0018917652778327465, "learning_rate": 9.569624845006753e-06, "loss": 4.5162332244217394e-05, "step": 51100 }, { "epoch": 6.646515860634425, "grad_norm": 0.0007686164462938905, "learning_rate": 9.544760099810018e-06, "loss": 5.0472081638872624e-05, "step": 51125 }, { "epoch": 6.649765990639626, "grad_norm": 0.0004505772376433015, "learning_rate": 9.519920075967376e-06, "loss": 5.4867747239768503e-05, "step": 51150 }, { "epoch": 6.653016120644826, "grad_norm": 0.0008554458618164062, "learning_rate": 9.49510481321157e-06, "loss": 4.993608687072992e-05, "step": 51175 }, { "epoch": 6.656266250650026, "grad_norm": 0.0005862816469743848, "learning_rate": 9.47031435123572e-06, "loss": 4.572540055960417e-05, "step": 51200 }, { "epoch": 6.659516380655226, "grad_norm": 0.0006738247466273606, "learning_rate": 9.445548729693306e-06, "loss": 4.8767803236842154e-05, "step": 51225 }, { "epoch": 6.662766510660426, "grad_norm": 0.0005253670387901366, "learning_rate": 9.42080798819804e-06, "loss": 4.815364722162485e-05, "step": 51250 }, { "epoch": 6.666016640665626, "grad_norm": 0.0011463460978120565, "learning_rate": 9.396092166323884e-06, "loss": 5.130481906235218e-05, "step": 51275 }, { "epoch": 6.669266770670827, "grad_norm": 0.0005145824397914112, "learning_rate": 9.371401303604871e-06, "loss": 5.162282381206751e-05, "step": 51300 }, { "epoch": 6.672516900676027, "grad_norm": 0.000858815386891365, "learning_rate": 9.346735439535182e-06, "loss": 5.7454938068985936e-05, "step": 51325 }, { "epoch": 6.675767030681227, "grad_norm": 0.0004837331944145262, "learning_rate": 9.322094613568958e-06, "loss": 4.7916513867676255e-05, "step": 51350 }, { "epoch": 6.679017160686428, "grad_norm": 0.0006912416429258883, "learning_rate": 9.297478865120335e-06, "loss": 4.536592401564121e-05, "step": 51375 }, { "epoch": 6.682267290691628, "grad_norm": 0.000967474072240293, "learning_rate": 9.272888233563292e-06, "loss": 4.8160371370613575e-05, "step": 51400 }, { "epoch": 6.6855174206968275, "grad_norm": 0.0008392477175220847, "learning_rate": 9.248322758231678e-06, "loss": 4.7136936336755754e-05, "step": 51425 }, { "epoch": 6.688767550702028, "grad_norm": 0.0003954404091928154, "learning_rate": 9.223782478419061e-06, "loss": 5.024930462241173e-05, "step": 51450 }, { "epoch": 6.692017680707228, "grad_norm": 0.001348863705061376, "learning_rate": 9.199267433378727e-06, "loss": 5.338989663869142e-05, "step": 51475 }, { "epoch": 6.695267810712428, "grad_norm": 0.0008867901051416993, "learning_rate": 9.17477766232362e-06, "loss": 5.0528296269476415e-05, "step": 51500 }, { "epoch": 6.698517940717629, "grad_norm": 0.0008472822955809534, "learning_rate": 9.150313204426206e-06, "loss": 4.966225940734148e-05, "step": 51525 }, { "epoch": 6.701768070722829, "grad_norm": 0.0004032078431919217, "learning_rate": 9.125874098818513e-06, "loss": 3.678184002637863e-05, "step": 51550 }, { "epoch": 6.705018200728029, "grad_norm": 0.0014030481688678265, "learning_rate": 9.101460384591972e-06, "loss": 5.0221350975334644e-05, "step": 51575 }, { "epoch": 6.70826833073323, "grad_norm": 0.0006258166395127773, "learning_rate": 9.077072100797446e-06, "loss": 5.020291544497013e-05, "step": 51600 }, { "epoch": 6.7115184607384295, "grad_norm": 0.0018765149870887399, "learning_rate": 9.05270928644507e-06, "loss": 5.554258357733488e-05, "step": 51625 }, { "epoch": 6.714768590743629, "grad_norm": 0.0012404171284288168, "learning_rate": 9.028371980504291e-06, "loss": 5.0092870369553564e-05, "step": 51650 }, { "epoch": 6.71801872074883, "grad_norm": 0.0014120676787570119, "learning_rate": 9.004060221903707e-06, "loss": 4.679827019572258e-05, "step": 51675 }, { "epoch": 6.72126885075403, "grad_norm": 0.0007829887908883393, "learning_rate": 8.979774049531092e-06, "loss": 5.45542361214757e-05, "step": 51700 }, { "epoch": 6.72451898075923, "grad_norm": 0.0006810849299654365, "learning_rate": 8.95551350223326e-06, "loss": 5.085187498480082e-05, "step": 51725 }, { "epoch": 6.727769110764431, "grad_norm": 0.001711326534859836, "learning_rate": 8.931278618816064e-06, "loss": 6.025351583957672e-05, "step": 51750 }, { "epoch": 6.727769110764431, "eval_loss": 0.0002206969220424071, "eval_runtime": 8.5121, "eval_samples_per_second": 587.401, "eval_steps_per_second": 4.699, "step": 51750 }, { "epoch": 6.727769110764431, "eval_holdout_avg_strict_f1": 0.2006446245263545, "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": 0.6312238564296315, "eval_holdout_nemotron_pii_strict_f1": 0.6189332051898125, "eval_holdout_open_pii_masking_500k_strict_f1": 0.4917959091930771, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.4651378989773784, "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": 6.731019240769631, "grad_norm": 0.0010405771899968386, "learning_rate": 8.907069438044283e-06, "loss": 5.527334753423929e-05, "step": 51775 }, { "epoch": 6.734269370774831, "grad_norm": 0.0007932729204185307, "learning_rate": 8.882885998641607e-06, "loss": 5.495774559676647e-05, "step": 51800 }, { "epoch": 6.7375195007800315, "grad_norm": 0.0005779250641353428, "learning_rate": 8.858728339290526e-06, "loss": 5.047453567385674e-05, "step": 51825 }, { "epoch": 6.740769630785231, "grad_norm": 0.0008217446738854051, "learning_rate": 8.834596498632322e-06, "loss": 5.141938105225563e-05, "step": 51850 }, { "epoch": 6.744019760790431, "grad_norm": 0.0009164359071291983, "learning_rate": 8.810490515266948e-06, "loss": 5.273064132779837e-05, "step": 51875 }, { "epoch": 6.747269890795632, "grad_norm": 0.001297359587624669, "learning_rate": 8.786410427753028e-06, "loss": 4.6013118699193e-05, "step": 51900 }, { "epoch": 6.750520020800832, "grad_norm": 0.00047881552018225193, "learning_rate": 8.762356274607733e-06, "loss": 5.003579892218113e-05, "step": 51925 }, { "epoch": 6.753770150806032, "grad_norm": 0.000765210366807878, "learning_rate": 8.738328094306785e-06, "loss": 5.394895095378161e-05, "step": 51950 }, { "epoch": 6.757020280811233, "grad_norm": 0.0006065898342058063, "learning_rate": 8.714325925284325e-06, "loss": 5.555019713938236e-05, "step": 51975 }, { "epoch": 6.760270410816433, "grad_norm": 0.0016391038661822677, "learning_rate": 8.690349805932918e-06, "loss": 5.818097852170467e-05, "step": 52000 }, { "epoch": 6.763520540821633, "grad_norm": 0.0003327186277601868, "learning_rate": 8.666399774603454e-06, "loss": 4.9596908502280713e-05, "step": 52025 }, { "epoch": 6.766770670826833, "grad_norm": 0.0014722575433552265, "learning_rate": 8.642475869605073e-06, "loss": 5.353460554033518e-05, "step": 52050 }, { "epoch": 6.770020800832033, "grad_norm": 0.00056368054356426, "learning_rate": 8.61857812920516e-06, "loss": 4.6281730756163595e-05, "step": 52075 }, { "epoch": 6.773270930837233, "grad_norm": 0.0010737371630966663, "learning_rate": 8.594706591629214e-06, "loss": 4.599243402481079e-05, "step": 52100 }, { "epoch": 6.776521060842434, "grad_norm": 0.0010878229513764381, "learning_rate": 8.57086129506085e-06, "loss": 5.210103932768107e-05, "step": 52125 }, { "epoch": 6.779771190847634, "grad_norm": 0.0007141023525036871, "learning_rate": 8.547042277641684e-06, "loss": 5.315389018505812e-05, "step": 52150 }, { "epoch": 6.783021320852834, "grad_norm": 0.0008300422341562808, "learning_rate": 8.523249577471323e-06, "loss": 4.998899064958095e-05, "step": 52175 }, { "epoch": 6.786271450858035, "grad_norm": 0.0010613205377012491, "learning_rate": 8.499483232607252e-06, "loss": 5.1546748727560045e-05, "step": 52200 }, { "epoch": 6.7895215808632345, "grad_norm": 0.0006798469694331288, "learning_rate": 8.475743281064829e-06, "loss": 5.163074005395174e-05, "step": 52225 }, { "epoch": 6.7927717108684345, "grad_norm": 0.0008713764837011695, "learning_rate": 8.452029760817159e-06, "loss": 5.739269312471151e-05, "step": 52250 }, { "epoch": 6.796021840873635, "grad_norm": 0.0008321488276124001, "learning_rate": 8.428342709795106e-06, "loss": 5.659094080328941e-05, "step": 52275 }, { "epoch": 6.799271970878835, "grad_norm": 0.0005524233565665781, "learning_rate": 8.404682165887164e-06, "loss": 4.614042583853006e-05, "step": 52300 }, { "epoch": 6.802522100884035, "grad_norm": 0.0004876101156696677, "learning_rate": 8.381048166939453e-06, "loss": 4.8319674097001556e-05, "step": 52325 }, { "epoch": 6.805772230889236, "grad_norm": 0.0004951855516992509, "learning_rate": 8.35744075075561e-06, "loss": 4.282206762582064e-05, "step": 52350 }, { "epoch": 6.809022360894436, "grad_norm": 0.001494159339927137, "learning_rate": 8.333859955096777e-06, "loss": 4.841357003897429e-05, "step": 52375 }, { "epoch": 6.812272490899636, "grad_norm": 0.0007534989272244275, "learning_rate": 8.310305817681485e-06, "loss": 5.463674664497376e-05, "step": 52400 }, { "epoch": 6.8155226209048365, "grad_norm": 0.0010975521290674806, "learning_rate": 8.286778376185658e-06, "loss": 5.0716139376163483e-05, "step": 52425 }, { "epoch": 6.818772750910036, "grad_norm": 0.0005439089727587998, "learning_rate": 8.263277668242481e-06, "loss": 4.8129563219845294e-05, "step": 52450 }, { "epoch": 6.822022880915236, "grad_norm": 0.0008417941862717271, "learning_rate": 8.23980373144242e-06, "loss": 5.230387672781944e-05, "step": 52475 }, { "epoch": 6.825273010920437, "grad_norm": 0.0007711275247856975, "learning_rate": 8.216356603333072e-06, "loss": 5.512117873877287e-05, "step": 52500 }, { "epoch": 6.828523140925637, "grad_norm": 0.0011338484473526478, "learning_rate": 8.192936321419196e-06, "loss": 4.692848771810532e-05, "step": 52525 }, { "epoch": 6.831773270930837, "grad_norm": 0.0009286447893828154, "learning_rate": 8.16954292316259e-06, "loss": 4.941383376717567e-05, "step": 52550 }, { "epoch": 6.835023400936038, "grad_norm": 0.0009268737048842013, "learning_rate": 8.146176445982036e-06, "loss": 4.800440743565559e-05, "step": 52575 }, { "epoch": 6.838273530941238, "grad_norm": 0.0008393432945013046, "learning_rate": 8.122836927253291e-06, "loss": 5.1881340332329274e-05, "step": 52600 }, { "epoch": 6.841523660946438, "grad_norm": 0.0012311184545978904, "learning_rate": 8.099524404308948e-06, "loss": 4.8548951745033265e-05, "step": 52625 }, { "epoch": 6.844773790951638, "grad_norm": 0.0012347905430942774, "learning_rate": 8.076238914438458e-06, "loss": 5.407582502812147e-05, "step": 52650 }, { "epoch": 6.848023920956838, "grad_norm": 0.0010317692067474127, "learning_rate": 8.052980494887996e-06, "loss": 4.8312731087207796e-05, "step": 52675 }, { "epoch": 6.851274050962038, "grad_norm": 0.0016376200364902616, "learning_rate": 8.029749182860469e-06, "loss": 5.7094213552773e-05, "step": 52700 }, { "epoch": 6.854524180967239, "grad_norm": 0.0005895663634873927, "learning_rate": 8.006545015515399e-06, "loss": 5.222155712544918e-05, "step": 52725 }, { "epoch": 6.857774310972439, "grad_norm": 0.0011555579258129, "learning_rate": 7.98336802996891e-06, "loss": 4.738041199743748e-05, "step": 52750 }, { "epoch": 6.861024440977639, "grad_norm": 0.0007772531826049089, "learning_rate": 7.960218263293623e-06, "loss": 5.1794997416436674e-05, "step": 52775 }, { "epoch": 6.86427457098284, "grad_norm": 0.0007658052491024137, "learning_rate": 7.93709575251865e-06, "loss": 5.417586769908666e-05, "step": 52800 }, { "epoch": 6.86752470098804, "grad_norm": 0.001209406997077167, "learning_rate": 7.914000534629487e-06, "loss": 4.9452553503215314e-05, "step": 52825 }, { "epoch": 6.8707748309932395, "grad_norm": 0.0006852225051261485, "learning_rate": 7.890932646567964e-06, "loss": 5.298822652548552e-05, "step": 52850 }, { "epoch": 6.87402496099844, "grad_norm": 0.0011455058120191097, "learning_rate": 7.867892125232228e-06, "loss": 4.9591846764087674e-05, "step": 52875 }, { "epoch": 6.87727509100364, "grad_norm": 0.0014650620287284255, "learning_rate": 7.844879007476622e-06, "loss": 5.317158531397581e-05, "step": 52900 }, { "epoch": 6.88052522100884, "grad_norm": 0.0018496518023312092, "learning_rate": 7.821893330111677e-06, "loss": 5.311891436576843e-05, "step": 52925 }, { "epoch": 6.883775351014041, "grad_norm": 0.0011846880661323667, "learning_rate": 7.798935129904005e-06, "loss": 5.487258080393076e-05, "step": 52950 }, { "epoch": 6.887025481019241, "grad_norm": 0.001011090469546616, "learning_rate": 7.776004443576307e-06, "loss": 5.233734380453825e-05, "step": 52975 }, { "epoch": 6.890275611024441, "grad_norm": 0.0010121514787897468, "learning_rate": 7.753101307807228e-06, "loss": 4.857252817600966e-05, "step": 53000 }, { "epoch": 6.8935257410296416, "grad_norm": 0.0008325328817591071, "learning_rate": 7.730225759231388e-06, "loss": 5.2748131565749645e-05, "step": 53025 }, { "epoch": 6.8967758710348415, "grad_norm": 0.0006486069760285318, "learning_rate": 7.707377834439242e-06, "loss": 4.982855170965195e-05, "step": 53050 }, { "epoch": 6.900026001040041, "grad_norm": 0.0012384431902319193, "learning_rate": 7.684557569977095e-06, "loss": 5.292921792715788e-05, "step": 53075 }, { "epoch": 6.903276131045242, "grad_norm": 0.0011134188389405608, "learning_rate": 7.661765002346968e-06, "loss": 5.096660926938057e-05, "step": 53100 }, { "epoch": 6.906526261050442, "grad_norm": 0.000859664985910058, "learning_rate": 7.63900016800663e-06, "loss": 4.099327605217695e-05, "step": 53125 }, { "epoch": 6.909776391055642, "grad_norm": 0.0005962133873254061, "learning_rate": 7.616263103369433e-06, "loss": 5.0519397482275964e-05, "step": 53150 }, { "epoch": 6.913026521060843, "grad_norm": 0.0008024764247238636, "learning_rate": 7.593553844804366e-06, "loss": 4.9463426694273946e-05, "step": 53175 }, { "epoch": 6.916276651066043, "grad_norm": 0.0007951881270855665, "learning_rate": 7.570872428635889e-06, "loss": 5.0922851078212264e-05, "step": 53200 }, { "epoch": 6.919526781071243, "grad_norm": 0.0005446816794574261, "learning_rate": 7.548218891143971e-06, "loss": 4.4768759980797764e-05, "step": 53225 }, { "epoch": 6.922776911076443, "grad_norm": 0.0008028848096728325, "learning_rate": 7.525593268563949e-06, "loss": 6.023123860359192e-05, "step": 53250 }, { "epoch": 6.926027041081643, "grad_norm": 0.0006392176146619022, "learning_rate": 7.502995597086548e-06, "loss": 4.748048260807991e-05, "step": 53275 }, { "epoch": 6.929277171086843, "grad_norm": 0.0008827222045511007, "learning_rate": 7.480425912857747e-06, "loss": 4.8407982103526595e-05, "step": 53300 }, { "epoch": 6.932527301092044, "grad_norm": 0.0007863828795962036, "learning_rate": 7.457884251978791e-06, "loss": 4.145367536693811e-05, "step": 53325 }, { "epoch": 6.935777431097244, "grad_norm": 0.0005377721390686929, "learning_rate": 7.435370650506066e-06, "loss": 4.480060189962387e-05, "step": 53350 }, { "epoch": 6.939027561102444, "grad_norm": 0.0034648189321160316, "learning_rate": 7.412885144451104e-06, "loss": 5.828516092151403e-05, "step": 53375 }, { "epoch": 6.942277691107645, "grad_norm": 0.0015442428411915898, "learning_rate": 7.3904277697804975e-06, "loss": 6.504377815872431e-05, "step": 53400 }, { "epoch": 6.945527821112845, "grad_norm": 0.00044657569378614426, "learning_rate": 7.367998562415809e-06, "loss": 5.576859693974256e-05, "step": 53425 }, { "epoch": 6.9487779511180445, "grad_norm": 0.001207768335007131, "learning_rate": 7.345597558233591e-06, "loss": 5.0385710783302786e-05, "step": 53450 }, { "epoch": 6.952028081123245, "grad_norm": 0.001414680969901383, "learning_rate": 7.323224793065242e-06, "loss": 4.636392462998629e-05, "step": 53475 }, { "epoch": 6.955278211128445, "grad_norm": 0.001146330265328288, "learning_rate": 7.300880302697027e-06, "loss": 5.4394868202507494e-05, "step": 53500 }, { "epoch": 6.958528341133645, "grad_norm": 0.0008196947746910155, "learning_rate": 7.278564122869949e-06, "loss": 5.888473708182573e-05, "step": 53525 }, { "epoch": 6.961778471138846, "grad_norm": 0.0009597166790626943, "learning_rate": 7.256276289279765e-06, "loss": 5.785546265542507e-05, "step": 53550 }, { "epoch": 6.965028601144046, "grad_norm": 0.0013037995668128133, "learning_rate": 7.2340168375768545e-06, "loss": 5.072474479675293e-05, "step": 53575 }, { "epoch": 6.968278731149246, "grad_norm": 0.0008072399068623781, "learning_rate": 7.21178580336623e-06, "loss": 5.00065553933382e-05, "step": 53600 }, { "epoch": 6.971528861154447, "grad_norm": 0.0005964972078800201, "learning_rate": 7.189583222207419e-06, "loss": 5.658399313688278e-05, "step": 53625 }, { "epoch": 6.9747789911596465, "grad_norm": 0.001554907881654799, "learning_rate": 7.167409129614466e-06, "loss": 6.0585495084524155e-05, "step": 53650 }, { "epoch": 6.978029121164846, "grad_norm": 0.0016246375162154436, "learning_rate": 7.145263561055823e-06, "loss": 5.182713270187378e-05, "step": 53675 }, { "epoch": 6.981279251170047, "grad_norm": 0.0006740947719663382, "learning_rate": 7.123146551954341e-06, "loss": 4.622492473572493e-05, "step": 53700 }, { "epoch": 6.984529381175247, "grad_norm": 0.0004746394115500152, "learning_rate": 7.101058137687155e-06, "loss": 4.261214286088944e-05, "step": 53725 }, { "epoch": 6.987779511180447, "grad_norm": 0.0004588518640957773, "learning_rate": 7.078998353585703e-06, "loss": 4.601514898240566e-05, "step": 53750 }, { "epoch": 6.991029641185648, "grad_norm": 0.0011199535802006721, "learning_rate": 7.0569672349355825e-06, "loss": 5.743246525526047e-05, "step": 53775 }, { "epoch": 6.994279771190848, "grad_norm": 0.0011512077180668712, "learning_rate": 7.034964816976586e-06, "loss": 4.604494664818049e-05, "step": 53800 }, { "epoch": 6.997529901196048, "grad_norm": 0.0009061109740287066, "learning_rate": 7.012991134902552e-06, "loss": 5.5342670530080793e-05, "step": 53825 }, { "epoch": 7.0007800312012485, "grad_norm": 0.0018279379000887275, "learning_rate": 6.9910462238614e-06, "loss": 4.9349549226462844e-05, "step": 53850 }, { "epoch": 7.004030161206448, "grad_norm": 0.00040082563646137714, "learning_rate": 6.969130118954983e-06, "loss": 4.935707431286573e-05, "step": 53875 }, { "epoch": 7.007280291211648, "grad_norm": 0.0017619575373828411, "learning_rate": 6.947242855239122e-06, "loss": 5.107253324240446e-05, "step": 53900 }, { "epoch": 7.010530421216849, "grad_norm": 0.0012135545257478952, "learning_rate": 6.925384467723464e-06, "loss": 4.494341090321541e-05, "step": 53925 }, { "epoch": 7.013780551222049, "grad_norm": 0.0012025287142023444, "learning_rate": 6.903554991371497e-06, "loss": 4.8352917656302455e-05, "step": 53950 }, { "epoch": 7.017030681227249, "grad_norm": 0.0008079640101641417, "learning_rate": 6.881754461100462e-06, "loss": 5.0309794023633006e-05, "step": 53975 }, { "epoch": 7.02028081123245, "grad_norm": 0.00039088018820621073, "learning_rate": 6.8599829117812735e-06, "loss": 4.703182261437178e-05, "step": 54000 }, { "epoch": 7.02353094123765, "grad_norm": 0.0016736063407734036, "learning_rate": 6.838240378238528e-06, "loss": 4.911641590297222e-05, "step": 54025 }, { "epoch": 7.02678107124285, "grad_norm": 0.0005099365371279418, "learning_rate": 6.8165268952503666e-06, "loss": 5.332368426024914e-05, "step": 54050 }, { "epoch": 7.03003120124805, "grad_norm": 0.0011166695039719343, "learning_rate": 6.794842497548509e-06, "loss": 5.042523145675659e-05, "step": 54075 }, { "epoch": 7.03328133125325, "grad_norm": 0.0007455600425601006, "learning_rate": 6.773187219818109e-06, "loss": 5.463405512273312e-05, "step": 54100 }, { "epoch": 7.03653146125845, "grad_norm": 0.0011111466446891427, "learning_rate": 6.751561096697778e-06, "loss": 5.359428934752941e-05, "step": 54125 }, { "epoch": 7.03978159126365, "grad_norm": 0.0012657580664381385, "learning_rate": 6.729964162779459e-06, "loss": 4.909716546535492e-05, "step": 54150 }, { "epoch": 7.043031721268851, "grad_norm": 0.0010687831090763211, "learning_rate": 6.70839645260844e-06, "loss": 5.411746446043253e-05, "step": 54175 }, { "epoch": 7.046281851274051, "grad_norm": 0.0023428178392350674, "learning_rate": 6.6868580006832324e-06, "loss": 5.514922551810741e-05, "step": 54200 }, { "epoch": 7.049531981279251, "grad_norm": 0.000826533418148756, "learning_rate": 6.665348841455577e-06, "loss": 5.2245315164327624e-05, "step": 54225 }, { "epoch": 7.0527821112844515, "grad_norm": 0.0022648393642157316, "learning_rate": 6.643869009330331e-06, "loss": 4.1761137545108795e-05, "step": 54250 }, { "epoch": 7.0560322412896515, "grad_norm": 0.0009918881114572287, "learning_rate": 6.622418538665468e-06, "loss": 5.912513006478548e-05, "step": 54275 }, { "epoch": 7.059282371294851, "grad_norm": 0.0007629656465724111, "learning_rate": 6.600997463771974e-06, "loss": 5.025489255785942e-05, "step": 54300 }, { "epoch": 7.062532501300052, "grad_norm": 0.0017949574394151568, "learning_rate": 6.579605818913837e-06, "loss": 4.755200818181038e-05, "step": 54325 }, { "epoch": 7.065782631305252, "grad_norm": 0.000804223760496825, "learning_rate": 6.5582436383079425e-06, "loss": 5.0910022109746934e-05, "step": 54350 }, { "epoch": 7.069032761310452, "grad_norm": 0.002393157687038183, "learning_rate": 6.536910956124084e-06, "loss": 5.6609432213008405e-05, "step": 54375 }, { "epoch": 7.072282891315653, "grad_norm": 0.0008571452926844358, "learning_rate": 6.515607806484839e-06, "loss": 4.404073115438223e-05, "step": 54400 }, { "epoch": 7.075533021320853, "grad_norm": 0.0005910605541430414, "learning_rate": 6.494334223465545e-06, "loss": 4.796207882463932e-05, "step": 54425 }, { "epoch": 7.078783151326053, "grad_norm": 0.0008327445830218494, "learning_rate": 6.473090241094282e-06, "loss": 4.873095545917749e-05, "step": 54450 }, { "epoch": 7.082033281331253, "grad_norm": 0.001740416744723916, "learning_rate": 6.451875893351741e-06, "loss": 4.6618185006082055e-05, "step": 54475 }, { "epoch": 7.085283411336453, "grad_norm": 0.0008153008529916406, "learning_rate": 6.430691214171242e-06, "loss": 4.7560790553689005e-05, "step": 54500 }, { "epoch": 7.088533541341653, "grad_norm": 0.0019672950729727745, "learning_rate": 6.409536237438621e-06, "loss": 4.65179979801178e-05, "step": 54525 }, { "epoch": 7.091783671346854, "grad_norm": 0.0008286567754112184, "learning_rate": 6.388410996992237e-06, "loss": 4.920311737805605e-05, "step": 54550 }, { "epoch": 7.095033801352054, "grad_norm": 0.0006958983722142875, "learning_rate": 6.367315526622849e-06, "loss": 4.60731890052557e-05, "step": 54575 }, { "epoch": 7.098283931357254, "grad_norm": 0.00045660612522624433, "learning_rate": 6.346249860073628e-06, "loss": 4.782402887940407e-05, "step": 54600 }, { "epoch": 7.101534061362455, "grad_norm": 0.000926536915358156, "learning_rate": 6.325214031040044e-06, "loss": 4.6464838087558744e-05, "step": 54625 }, { "epoch": 7.104784191367655, "grad_norm": 0.0007123056566342711, "learning_rate": 6.304208073169873e-06, "loss": 5.618495400995016e-05, "step": 54650 }, { "epoch": 7.1080343213728545, "grad_norm": 0.0013994867913424969, "learning_rate": 6.283232020063079e-06, "loss": 4.93527902290225e-05, "step": 54675 }, { "epoch": 7.111284451378055, "grad_norm": 0.0006716115749441087, "learning_rate": 6.262285905271814e-06, "loss": 5.061638541519642e-05, "step": 54700 }, { "epoch": 7.114534581383255, "grad_norm": 0.001829572138376534, "learning_rate": 6.2413697623003285e-06, "loss": 4.6400041319429875e-05, "step": 54725 }, { "epoch": 7.117784711388455, "grad_norm": 0.001954107079654932, "learning_rate": 6.220483624604945e-06, "loss": 4.650086630135775e-05, "step": 54750 }, { "epoch": 7.121034841393656, "grad_norm": 0.0006563881761394441, "learning_rate": 6.199627525593973e-06, "loss": 4.709349013864994e-05, "step": 54775 }, { "epoch": 7.124284971398856, "grad_norm": 0.0005796256591565907, "learning_rate": 6.178801498627692e-06, "loss": 5.0751930102705957e-05, "step": 54800 }, { "epoch": 7.127535101404056, "grad_norm": 0.0008404129184782505, "learning_rate": 6.15800557701828e-06, "loss": 4.9090790562331676e-05, "step": 54825 }, { "epoch": 7.130785231409257, "grad_norm": 0.0005137972766533494, "learning_rate": 6.137239794029736e-06, "loss": 5.3911814466118815e-05, "step": 54850 }, { "epoch": 7.1340353614144565, "grad_norm": 0.001054225373081863, "learning_rate": 6.116504182877883e-06, "loss": 4.838683642446995e-05, "step": 54875 }, { "epoch": 7.137285491419656, "grad_norm": 0.0007935213507153094, "learning_rate": 6.0957987767302525e-06, "loss": 4.9587199464440344e-05, "step": 54900 }, { "epoch": 7.140535621424857, "grad_norm": 0.0010193277848884463, "learning_rate": 6.075123608706093e-06, "loss": 5.4644527845084665e-05, "step": 54925 }, { "epoch": 7.143785751430057, "grad_norm": 0.0004261209105607122, "learning_rate": 6.054478711876252e-06, "loss": 5.3432630375027655e-05, "step": 54950 }, { "epoch": 7.147035881435257, "grad_norm": 0.0011106330202892423, "learning_rate": 6.033864119263191e-06, "loss": 5.703236442059279e-05, "step": 54975 }, { "epoch": 7.150286011440458, "grad_norm": 0.0007685767486691475, "learning_rate": 6.013279863840867e-06, "loss": 4.141377285122871e-05, "step": 55000 }, { "epoch": 7.153536141445658, "grad_norm": 0.0005855047493241727, "learning_rate": 5.992725978534738e-06, "loss": 4.959492478519678e-05, "step": 55025 }, { "epoch": 7.156786271450858, "grad_norm": 0.0017621064325794578, "learning_rate": 5.9722024962216625e-06, "loss": 4.753164481371641e-05, "step": 55050 }, { "epoch": 7.1600364014560585, "grad_norm": 0.0013969808351248503, "learning_rate": 5.951709449729884e-06, "loss": 4.794710781425238e-05, "step": 55075 }, { "epoch": 7.163286531461258, "grad_norm": 0.00037920192698948085, "learning_rate": 5.931246871838947e-06, "loss": 4.69488836824894e-05, "step": 55100 }, { "epoch": 7.166536661466458, "grad_norm": 0.0010887382086366415, "learning_rate": 5.910814795279684e-06, "loss": 5.250110290944576e-05, "step": 55125 }, { "epoch": 7.169786791471659, "grad_norm": 0.0008431277819909155, "learning_rate": 5.890413252734103e-06, "loss": 5.024921149015427e-05, "step": 55150 }, { "epoch": 7.173036921476859, "grad_norm": 0.0007794437115080655, "learning_rate": 5.8700422768354135e-06, "loss": 4.801631439477205e-05, "step": 55175 }, { "epoch": 7.176287051482059, "grad_norm": 0.0014055962674319744, "learning_rate": 5.849701900167895e-06, "loss": 5.1826867274940017e-05, "step": 55200 }, { "epoch": 7.176287051482059, "eval_loss": 0.00021625339286401868, "eval_runtime": 8.6836, "eval_samples_per_second": 575.799, "eval_steps_per_second": 4.606, "step": 55200 }, { "epoch": 7.176287051482059, "eval_holdout_avg_strict_f1": 0.20084014314158366, "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": 0.6658231407282441, "eval_holdout_nemotron_pii_strict_f1": 0.5638881956575992, "eval_holdout_open_pii_masking_500k_strict_f1": 0.5012763982362497, "eval_holdout_phishing_darkknight_strict_f1": 0.0, "eval_holdout_phishing_zefang_strict_f1": 0.0, "eval_holdout_pii_masking_400k_strict_f1": 0.47825383993532744, "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 } ], "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": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }