arthrod's picture
Upload folder using huggingface_hub
786e4c0 verified
Raw
History Blame Contribute Delete
55.9 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8970358814352574,
"eval_steps": 3450,
"global_step": 6900,
"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
}
],
"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
}