arthrod's picture
Upload folder using huggingface_hub
1f63396 verified
Raw
History Blame Contribute Delete
111 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.794071762870515,
"eval_steps": 3450,
"global_step": 13800,
"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
}
],
"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
}