polyglot-tagger-60L-Experimental / trainer_state.json
DerivedFunction's picture
End of training
5cb2eff verified
{
"best_global_step": 32500,
"best_metric": 0.8929190695762744,
"best_model_checkpoint": "./lang-ner-xlmr/checkpoint-32500",
"epoch": 2.0,
"eval_steps": 2500,
"global_step": 34550,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005788879562360705,
"grad_norm": 2.855613946914673,
"learning_rate": 4.9856729377713464e-05,
"loss": 2.9271701049804686,
"step": 100
},
{
"epoch": 0.01157775912472141,
"grad_norm": 1.3880442380905151,
"learning_rate": 4.9712011577424025e-05,
"loss": 0.34735004425048827,
"step": 200
},
{
"epoch": 0.017366638687082114,
"grad_norm": 2.103525400161743,
"learning_rate": 4.9567293777134585e-05,
"loss": 0.14239531517028808,
"step": 300
},
{
"epoch": 0.02315551824944282,
"grad_norm": 1.3836640119552612,
"learning_rate": 4.942257597684515e-05,
"loss": 0.10217083930969238,
"step": 400
},
{
"epoch": 0.028944397811803524,
"grad_norm": 2.793973445892334,
"learning_rate": 4.927785817655572e-05,
"loss": 0.08668763160705567,
"step": 500
},
{
"epoch": 0.03473327737416423,
"grad_norm": 0.9237315654754639,
"learning_rate": 4.913314037626629e-05,
"loss": 0.07951077461242675,
"step": 600
},
{
"epoch": 0.04052215693652494,
"grad_norm": 1.0332331657409668,
"learning_rate": 4.898842257597685e-05,
"loss": 0.07264325618743897,
"step": 700
},
{
"epoch": 0.04631103649888564,
"grad_norm": 0.7395448088645935,
"learning_rate": 4.884370477568741e-05,
"loss": 0.0672088623046875,
"step": 800
},
{
"epoch": 0.052099916061246344,
"grad_norm": 0.4162349998950958,
"learning_rate": 4.8698986975397976e-05,
"loss": 0.06357911109924316,
"step": 900
},
{
"epoch": 0.05788879562360705,
"grad_norm": 1.134838342666626,
"learning_rate": 4.855426917510854e-05,
"loss": 0.06361278057098389,
"step": 1000
},
{
"epoch": 0.06367767518596776,
"grad_norm": 0.9246254563331604,
"learning_rate": 4.8409551374819104e-05,
"loss": 0.06069922924041748,
"step": 1100
},
{
"epoch": 0.06946655474832845,
"grad_norm": 0.4614603519439697,
"learning_rate": 4.826483357452967e-05,
"loss": 0.0631745719909668,
"step": 1200
},
{
"epoch": 0.07525543431068916,
"grad_norm": 1.585123062133789,
"learning_rate": 4.812011577424023e-05,
"loss": 0.05860543251037598,
"step": 1300
},
{
"epoch": 0.08104431387304988,
"grad_norm": 0.521318793296814,
"learning_rate": 4.79753979739508e-05,
"loss": 0.056866631507873536,
"step": 1400
},
{
"epoch": 0.08683319343541057,
"grad_norm": 0.9092019200325012,
"learning_rate": 4.7830680173661366e-05,
"loss": 0.06285685062408447,
"step": 1500
},
{
"epoch": 0.09262207299777128,
"grad_norm": 0.612201452255249,
"learning_rate": 4.7685962373371927e-05,
"loss": 0.054396772384643556,
"step": 1600
},
{
"epoch": 0.09841095256013199,
"grad_norm": 0.6812730431556702,
"learning_rate": 4.7541244573082494e-05,
"loss": 0.05651024341583252,
"step": 1700
},
{
"epoch": 0.10419983212249269,
"grad_norm": 0.8203144073486328,
"learning_rate": 4.7396526772793054e-05,
"loss": 0.061346669197082516,
"step": 1800
},
{
"epoch": 0.1099887116848534,
"grad_norm": 1.9262521266937256,
"learning_rate": 4.725180897250362e-05,
"loss": 0.05345334053039551,
"step": 1900
},
{
"epoch": 0.1157775912472141,
"grad_norm": 1.366341471672058,
"learning_rate": 4.710709117221418e-05,
"loss": 0.049096508026123045,
"step": 2000
},
{
"epoch": 0.1215664708095748,
"grad_norm": 1.9058470726013184,
"learning_rate": 4.696237337192475e-05,
"loss": 0.04964198589324951,
"step": 2100
},
{
"epoch": 0.12735535037193552,
"grad_norm": 0.20036761462688446,
"learning_rate": 4.681765557163532e-05,
"loss": 0.048866801261901856,
"step": 2200
},
{
"epoch": 0.13314422993429623,
"grad_norm": 0.6949800252914429,
"learning_rate": 4.667293777134588e-05,
"loss": 0.049001736640930174,
"step": 2300
},
{
"epoch": 0.1389331094966569,
"grad_norm": 1.4212485551834106,
"learning_rate": 4.6528219971056445e-05,
"loss": 0.05099475383758545,
"step": 2400
},
{
"epoch": 0.14472198905901762,
"grad_norm": 0.5998656749725342,
"learning_rate": 4.6383502170767005e-05,
"loss": 0.046523327827453616,
"step": 2500
},
{
"epoch": 0.14472198905901762,
"eval_accuracy": 0.9827913999033898,
"eval_f1": 0.8260160577581378,
"eval_loss": 0.08191228657960892,
"eval_precision": 0.794459210305773,
"eval_recall": 0.8601835528362543,
"eval_runtime": 41.7733,
"eval_samples_per_second": 299.234,
"eval_steps_per_second": 8.331,
"step": 2500
},
{
"epoch": 0.15051086862137833,
"grad_norm": 0.26346391439437866,
"learning_rate": 4.623878437047757e-05,
"loss": 0.04394114971160889,
"step": 2600
},
{
"epoch": 0.15629974818373904,
"grad_norm": 0.6683024168014526,
"learning_rate": 4.609406657018814e-05,
"loss": 0.04297324180603027,
"step": 2700
},
{
"epoch": 0.16208862774609975,
"grad_norm": 0.792713463306427,
"learning_rate": 4.59493487698987e-05,
"loss": 0.044585137367248534,
"step": 2800
},
{
"epoch": 0.16787750730846046,
"grad_norm": 0.8176506161689758,
"learning_rate": 4.580463096960926e-05,
"loss": 0.04621150970458984,
"step": 2900
},
{
"epoch": 0.17366638687082114,
"grad_norm": 0.21292151510715485,
"learning_rate": 4.565991316931983e-05,
"loss": 0.04335964679718018,
"step": 3000
},
{
"epoch": 0.17945526643318185,
"grad_norm": 0.5183402299880981,
"learning_rate": 4.5515195369030395e-05,
"loss": 0.045092535018920896,
"step": 3100
},
{
"epoch": 0.18524414599554256,
"grad_norm": 0.8505319356918335,
"learning_rate": 4.537047756874096e-05,
"loss": 0.03996892213821411,
"step": 3200
},
{
"epoch": 0.19103302555790327,
"grad_norm": 2.187335252761841,
"learning_rate": 4.522575976845152e-05,
"loss": 0.048550710678100586,
"step": 3300
},
{
"epoch": 0.19682190512026398,
"grad_norm": 0.5401766896247864,
"learning_rate": 4.5081041968162084e-05,
"loss": 0.03830349683761597,
"step": 3400
},
{
"epoch": 0.20261078468262467,
"grad_norm": 3.9655873775482178,
"learning_rate": 4.493632416787265e-05,
"loss": 0.04094114303588867,
"step": 3500
},
{
"epoch": 0.20839966424498538,
"grad_norm": 2.4231624603271484,
"learning_rate": 4.479160636758322e-05,
"loss": 0.050821685791015626,
"step": 3600
},
{
"epoch": 0.2141885438073461,
"grad_norm": 0.8014847040176392,
"learning_rate": 4.464688856729378e-05,
"loss": 0.04339597225189209,
"step": 3700
},
{
"epoch": 0.2199774233697068,
"grad_norm": 0.6645370125770569,
"learning_rate": 4.450217076700434e-05,
"loss": 0.04568838119506836,
"step": 3800
},
{
"epoch": 0.2257663029320675,
"grad_norm": 0.7347345948219299,
"learning_rate": 4.435745296671491e-05,
"loss": 0.038632638454437256,
"step": 3900
},
{
"epoch": 0.2315551824944282,
"grad_norm": 0.5599935054779053,
"learning_rate": 4.4212735166425474e-05,
"loss": 0.048587980270385744,
"step": 4000
},
{
"epoch": 0.2373440620567889,
"grad_norm": 0.6407144665718079,
"learning_rate": 4.406801736613604e-05,
"loss": 0.04263918876647949,
"step": 4100
},
{
"epoch": 0.2431329416191496,
"grad_norm": 0.6048207879066467,
"learning_rate": 4.39232995658466e-05,
"loss": 0.039798662662506104,
"step": 4200
},
{
"epoch": 0.24892182118151032,
"grad_norm": 1.7978732585906982,
"learning_rate": 4.377858176555716e-05,
"loss": 0.04390395164489746,
"step": 4300
},
{
"epoch": 0.25471070074387103,
"grad_norm": 0.5556352734565735,
"learning_rate": 4.363386396526773e-05,
"loss": 0.03865460634231568,
"step": 4400
},
{
"epoch": 0.2604995803062317,
"grad_norm": 1.2710750102996826,
"learning_rate": 4.34891461649783e-05,
"loss": 0.041819486618041996,
"step": 4500
},
{
"epoch": 0.26628845986859245,
"grad_norm": 0.5540153384208679,
"learning_rate": 4.334442836468886e-05,
"loss": 0.03990748643875122,
"step": 4600
},
{
"epoch": 0.27207733943095314,
"grad_norm": 0.24696502089500427,
"learning_rate": 4.319971056439942e-05,
"loss": 0.039545681476593014,
"step": 4700
},
{
"epoch": 0.2778662189933138,
"grad_norm": 0.2856484353542328,
"learning_rate": 4.3054992764109985e-05,
"loss": 0.04045855045318603,
"step": 4800
},
{
"epoch": 0.28365509855567456,
"grad_norm": 0.4371595084667206,
"learning_rate": 4.291027496382055e-05,
"loss": 0.04244920253753662,
"step": 4900
},
{
"epoch": 0.28944397811803524,
"grad_norm": 0.42544451355934143,
"learning_rate": 4.276555716353112e-05,
"loss": 0.04395281791687012,
"step": 5000
},
{
"epoch": 0.28944397811803524,
"eval_accuracy": 0.9842557123690646,
"eval_f1": 0.8330216670406662,
"eval_loss": 0.07031189650297165,
"eval_precision": 0.8023149704625138,
"eval_recall": 0.8661723530021778,
"eval_runtime": 32.2916,
"eval_samples_per_second": 387.098,
"eval_steps_per_second": 10.777,
"step": 5000
},
{
"epoch": 0.295232857680396,
"grad_norm": 0.46878165006637573,
"learning_rate": 4.262083936324168e-05,
"loss": 0.041322021484375,
"step": 5100
},
{
"epoch": 0.30102173724275666,
"grad_norm": 0.6579214930534363,
"learning_rate": 4.247612156295224e-05,
"loss": 0.03830409288406372,
"step": 5200
},
{
"epoch": 0.30681061680511734,
"grad_norm": 0.42139366269111633,
"learning_rate": 4.233140376266281e-05,
"loss": 0.03726105690002442,
"step": 5300
},
{
"epoch": 0.3125994963674781,
"grad_norm": 0.2871117889881134,
"learning_rate": 4.2186685962373376e-05,
"loss": 0.04068236351013184,
"step": 5400
},
{
"epoch": 0.31838837592983876,
"grad_norm": 0.5657113790512085,
"learning_rate": 4.2041968162083936e-05,
"loss": 0.041853628158569335,
"step": 5500
},
{
"epoch": 0.3241772554921995,
"grad_norm": 1.3855081796646118,
"learning_rate": 4.1897250361794504e-05,
"loss": 0.039269649982452394,
"step": 5600
},
{
"epoch": 0.3299661350545602,
"grad_norm": 0.8465105295181274,
"learning_rate": 4.1752532561505064e-05,
"loss": 0.03952852487564087,
"step": 5700
},
{
"epoch": 0.3357550146169209,
"grad_norm": 0.3637921214103699,
"learning_rate": 4.160781476121563e-05,
"loss": 0.03640928745269775,
"step": 5800
},
{
"epoch": 0.3415438941792816,
"grad_norm": 1.1824228763580322,
"learning_rate": 4.14630969609262e-05,
"loss": 0.03920279264450073,
"step": 5900
},
{
"epoch": 0.3473327737416423,
"grad_norm": 0.18278339505195618,
"learning_rate": 4.131837916063676e-05,
"loss": 0.03853697776794433,
"step": 6000
},
{
"epoch": 0.353121653304003,
"grad_norm": 0.6014581322669983,
"learning_rate": 4.1173661360347326e-05,
"loss": 0.03705440759658814,
"step": 6100
},
{
"epoch": 0.3589105328663637,
"grad_norm": 0.46531063318252563,
"learning_rate": 4.102894356005789e-05,
"loss": 0.03999743700027466,
"step": 6200
},
{
"epoch": 0.36469941242872445,
"grad_norm": 0.1958639770746231,
"learning_rate": 4.0884225759768454e-05,
"loss": 0.03664716958999634,
"step": 6300
},
{
"epoch": 0.37048829199108513,
"grad_norm": 0.8862726092338562,
"learning_rate": 4.0739507959479015e-05,
"loss": 0.0379261326789856,
"step": 6400
},
{
"epoch": 0.3762771715534458,
"grad_norm": 0.9592189192771912,
"learning_rate": 4.059479015918958e-05,
"loss": 0.03712235450744629,
"step": 6500
},
{
"epoch": 0.38206605111580655,
"grad_norm": 0.6839034557342529,
"learning_rate": 4.045007235890015e-05,
"loss": 0.03996901988983154,
"step": 6600
},
{
"epoch": 0.38785493067816723,
"grad_norm": 0.4922831952571869,
"learning_rate": 4.030535455861071e-05,
"loss": 0.03477381706237793,
"step": 6700
},
{
"epoch": 0.39364381024052797,
"grad_norm": 0.7703688740730286,
"learning_rate": 4.016063675832128e-05,
"loss": 0.03694391012191772,
"step": 6800
},
{
"epoch": 0.39943268980288865,
"grad_norm": 0.9563616514205933,
"learning_rate": 4.001591895803184e-05,
"loss": 0.038102331161499026,
"step": 6900
},
{
"epoch": 0.40522156936524933,
"grad_norm": 0.5397209525108337,
"learning_rate": 3.9871201157742405e-05,
"loss": 0.03435644626617432,
"step": 7000
},
{
"epoch": 0.4110104489276101,
"grad_norm": 0.33264386653900146,
"learning_rate": 3.972648335745297e-05,
"loss": 0.034106507301330566,
"step": 7100
},
{
"epoch": 0.41679932848997076,
"grad_norm": 0.4908270239830017,
"learning_rate": 3.958176555716353e-05,
"loss": 0.03293986797332764,
"step": 7200
},
{
"epoch": 0.4225882080523315,
"grad_norm": 1.4851772785186768,
"learning_rate": 3.9437047756874093e-05,
"loss": 0.041512365341186526,
"step": 7300
},
{
"epoch": 0.4283770876146922,
"grad_norm": 1.109512209892273,
"learning_rate": 3.929232995658466e-05,
"loss": 0.03690081834793091,
"step": 7400
},
{
"epoch": 0.43416596717705286,
"grad_norm": 1.2585190534591675,
"learning_rate": 3.914761215629523e-05,
"loss": 0.035063812732696535,
"step": 7500
},
{
"epoch": 0.43416596717705286,
"eval_accuracy": 0.9860376945037634,
"eval_f1": 0.8609184178154288,
"eval_loss": 0.06113845109939575,
"eval_precision": 0.8426553461929942,
"eval_recall": 0.8799906668049362,
"eval_runtime": 32.811,
"eval_samples_per_second": 380.97,
"eval_steps_per_second": 10.606,
"step": 7500
},
{
"epoch": 0.4399548467394136,
"grad_norm": 0.5866221189498901,
"learning_rate": 3.9002894356005795e-05,
"loss": 0.03833510398864746,
"step": 7600
},
{
"epoch": 0.4457437263017743,
"grad_norm": 0.3515453636646271,
"learning_rate": 3.885817655571635e-05,
"loss": 0.03402453660964966,
"step": 7700
},
{
"epoch": 0.451532605864135,
"grad_norm": 0.5338568687438965,
"learning_rate": 3.8713458755426916e-05,
"loss": 0.03593117237091065,
"step": 7800
},
{
"epoch": 0.4573214854264957,
"grad_norm": 0.42428648471832275,
"learning_rate": 3.8568740955137484e-05,
"loss": 0.036249592304229736,
"step": 7900
},
{
"epoch": 0.4631103649888564,
"grad_norm": 0.5833432078361511,
"learning_rate": 3.842402315484805e-05,
"loss": 0.033896231651306154,
"step": 8000
},
{
"epoch": 0.4688992445512171,
"grad_norm": 0.24067725241184235,
"learning_rate": 3.827930535455861e-05,
"loss": 0.03889668464660644,
"step": 8100
},
{
"epoch": 0.4746881241135778,
"grad_norm": 1.6670092344284058,
"learning_rate": 3.813458755426917e-05,
"loss": 0.036442911624908446,
"step": 8200
},
{
"epoch": 0.48047700367593854,
"grad_norm": 0.6004341244697571,
"learning_rate": 3.798986975397974e-05,
"loss": 0.037013137340545656,
"step": 8300
},
{
"epoch": 0.4862658832382992,
"grad_norm": 0.3944297432899475,
"learning_rate": 3.784515195369031e-05,
"loss": 0.036278882026672364,
"step": 8400
},
{
"epoch": 0.4920547628006599,
"grad_norm": 0.6234197020530701,
"learning_rate": 3.7700434153400874e-05,
"loss": 0.038663127422332765,
"step": 8500
},
{
"epoch": 0.49784364236302064,
"grad_norm": 0.403590589761734,
"learning_rate": 3.7555716353111435e-05,
"loss": 0.037761948108673095,
"step": 8600
},
{
"epoch": 0.5036325219253813,
"grad_norm": 0.44773924350738525,
"learning_rate": 3.7410998552821995e-05,
"loss": 0.03594711542129517,
"step": 8700
},
{
"epoch": 0.5094214014877421,
"grad_norm": 0.8247023820877075,
"learning_rate": 3.726628075253256e-05,
"loss": 0.03601913452148438,
"step": 8800
},
{
"epoch": 0.5152102810501028,
"grad_norm": 1.1590162515640259,
"learning_rate": 3.712156295224313e-05,
"loss": 0.03685137271881103,
"step": 8900
},
{
"epoch": 0.5209991606124634,
"grad_norm": 0.6263375878334045,
"learning_rate": 3.697684515195369e-05,
"loss": 0.036658039093017576,
"step": 9000
},
{
"epoch": 0.5267880401748242,
"grad_norm": 0.5682932138442993,
"learning_rate": 3.683212735166426e-05,
"loss": 0.03221390724182129,
"step": 9100
},
{
"epoch": 0.5325769197371849,
"grad_norm": 0.4283082187175751,
"learning_rate": 3.668740955137482e-05,
"loss": 0.03447196245193482,
"step": 9200
},
{
"epoch": 0.5383657992995455,
"grad_norm": 0.513534426689148,
"learning_rate": 3.6542691751085385e-05,
"loss": 0.03253072500228882,
"step": 9300
},
{
"epoch": 0.5441546788619063,
"grad_norm": 0.1790156066417694,
"learning_rate": 3.639797395079595e-05,
"loss": 0.03559961318969727,
"step": 9400
},
{
"epoch": 0.549943558424267,
"grad_norm": 1.3116710186004639,
"learning_rate": 3.625325615050651e-05,
"loss": 0.0339055609703064,
"step": 9500
},
{
"epoch": 0.5557324379866276,
"grad_norm": 0.7609701752662659,
"learning_rate": 3.610853835021708e-05,
"loss": 0.033302297592163084,
"step": 9600
},
{
"epoch": 0.5615213175489884,
"grad_norm": 0.6684858798980713,
"learning_rate": 3.596382054992764e-05,
"loss": 0.03894152641296387,
"step": 9700
},
{
"epoch": 0.5673101971113491,
"grad_norm": 0.25678926706314087,
"learning_rate": 3.581910274963821e-05,
"loss": 0.033086774349212644,
"step": 9800
},
{
"epoch": 0.5730990766737099,
"grad_norm": 1.2110711336135864,
"learning_rate": 3.567438494934877e-05,
"loss": 0.037588162422180174,
"step": 9900
},
{
"epoch": 0.5788879562360705,
"grad_norm": 0.7344034910202026,
"learning_rate": 3.5529667149059336e-05,
"loss": 0.03140888452529907,
"step": 10000
},
{
"epoch": 0.5788879562360705,
"eval_accuracy": 0.9871526392423338,
"eval_f1": 0.8693991367126322,
"eval_loss": 0.0593421570956707,
"eval_precision": 0.8542474665332166,
"eval_recall": 0.8850979985481696,
"eval_runtime": 32.4321,
"eval_samples_per_second": 385.42,
"eval_steps_per_second": 10.73,
"step": 10000
},
{
"epoch": 0.5846768357984312,
"grad_norm": 1.8443788290023804,
"learning_rate": 3.5384949348769903e-05,
"loss": 0.034446282386779783,
"step": 10100
},
{
"epoch": 0.590465715360792,
"grad_norm": 3.829798698425293,
"learning_rate": 3.5240231548480464e-05,
"loss": 0.031233868598937987,
"step": 10200
},
{
"epoch": 0.5962545949231526,
"grad_norm": 0.22466252744197845,
"learning_rate": 3.5095513748191025e-05,
"loss": 0.03304744958877563,
"step": 10300
},
{
"epoch": 0.6020434744855133,
"grad_norm": 0.2421451061964035,
"learning_rate": 3.495079594790159e-05,
"loss": 0.032493886947631834,
"step": 10400
},
{
"epoch": 0.6078323540478741,
"grad_norm": 6.648340225219727,
"learning_rate": 3.480607814761216e-05,
"loss": 0.034116878509521484,
"step": 10500
},
{
"epoch": 0.6136212336102347,
"grad_norm": 0.5613166093826294,
"learning_rate": 3.4661360347322726e-05,
"loss": 0.03445070266723633,
"step": 10600
},
{
"epoch": 0.6194101131725954,
"grad_norm": 0.24381904304027557,
"learning_rate": 3.451664254703329e-05,
"loss": 0.03339603900909424,
"step": 10700
},
{
"epoch": 0.6251989927349562,
"grad_norm": 0.5657049417495728,
"learning_rate": 3.437192474674385e-05,
"loss": 0.03580770492553711,
"step": 10800
},
{
"epoch": 0.6309878722973169,
"grad_norm": 0.16176201403141022,
"learning_rate": 3.4227206946454415e-05,
"loss": 0.03211415767669678,
"step": 10900
},
{
"epoch": 0.6367767518596775,
"grad_norm": 0.9659017324447632,
"learning_rate": 3.408248914616498e-05,
"loss": 0.032091012001037596,
"step": 11000
},
{
"epoch": 0.6425656314220383,
"grad_norm": 0.37151074409484863,
"learning_rate": 3.393777134587555e-05,
"loss": 0.030981764793395997,
"step": 11100
},
{
"epoch": 0.648354510984399,
"grad_norm": 0.24677230417728424,
"learning_rate": 3.37930535455861e-05,
"loss": 0.031599972248077396,
"step": 11200
},
{
"epoch": 0.6541433905467596,
"grad_norm": 0.5559372901916504,
"learning_rate": 3.364833574529667e-05,
"loss": 0.030684573650360106,
"step": 11300
},
{
"epoch": 0.6599322701091204,
"grad_norm": 0.309211790561676,
"learning_rate": 3.350361794500724e-05,
"loss": 0.03191032409667969,
"step": 11400
},
{
"epoch": 0.6657211496714811,
"grad_norm": 0.1990319788455963,
"learning_rate": 3.3358900144717805e-05,
"loss": 0.030000259876251222,
"step": 11500
},
{
"epoch": 0.6715100292338418,
"grad_norm": 0.6448608636856079,
"learning_rate": 3.3214182344428366e-05,
"loss": 0.03020137071609497,
"step": 11600
},
{
"epoch": 0.6772989087962025,
"grad_norm": 0.4042809009552002,
"learning_rate": 3.3069464544138926e-05,
"loss": 0.0288107705116272,
"step": 11700
},
{
"epoch": 0.6830877883585632,
"grad_norm": 0.48739156126976013,
"learning_rate": 3.2924746743849493e-05,
"loss": 0.02975822925567627,
"step": 11800
},
{
"epoch": 0.688876667920924,
"grad_norm": 0.3511544466018677,
"learning_rate": 3.278002894356006e-05,
"loss": 0.030011208057403566,
"step": 11900
},
{
"epoch": 0.6946655474832846,
"grad_norm": 0.20981945097446442,
"learning_rate": 3.263531114327063e-05,
"loss": 0.030392658710479737,
"step": 12000
},
{
"epoch": 0.7004544270456453,
"grad_norm": 1.725892186164856,
"learning_rate": 3.249059334298119e-05,
"loss": 0.0313503360748291,
"step": 12100
},
{
"epoch": 0.706243306608006,
"grad_norm": 0.16606950759887695,
"learning_rate": 3.234587554269175e-05,
"loss": 0.03735621213912964,
"step": 12200
},
{
"epoch": 0.7120321861703667,
"grad_norm": 0.4616575539112091,
"learning_rate": 3.2201157742402316e-05,
"loss": 0.03038395643234253,
"step": 12300
},
{
"epoch": 0.7178210657327274,
"grad_norm": 0.40673601627349854,
"learning_rate": 3.2056439942112884e-05,
"loss": 0.035007147789001464,
"step": 12400
},
{
"epoch": 0.7236099452950882,
"grad_norm": 0.27561140060424805,
"learning_rate": 3.1911722141823444e-05,
"loss": 0.032888281345367434,
"step": 12500
},
{
"epoch": 0.7236099452950882,
"eval_accuracy": 0.9868453058965968,
"eval_f1": 0.8583013393139975,
"eval_loss": 0.056312501430511475,
"eval_precision": 0.8394012243178269,
"eval_recall": 0.8780721767084932,
"eval_runtime": 32.461,
"eval_samples_per_second": 385.078,
"eval_steps_per_second": 10.721,
"step": 12500
},
{
"epoch": 0.7293988248574489,
"grad_norm": 0.7054789662361145,
"learning_rate": 3.176700434153401e-05,
"loss": 0.031692807674407956,
"step": 12600
},
{
"epoch": 0.7351877044198095,
"grad_norm": 0.31711819767951965,
"learning_rate": 3.162228654124457e-05,
"loss": 0.03108912706375122,
"step": 12700
},
{
"epoch": 0.7409765839821703,
"grad_norm": 0.24462510645389557,
"learning_rate": 3.147756874095514e-05,
"loss": 0.03314091444015503,
"step": 12800
},
{
"epoch": 0.746765463544531,
"grad_norm": 0.37591752409935,
"learning_rate": 3.133285094066571e-05,
"loss": 0.031636784076690676,
"step": 12900
},
{
"epoch": 0.7525543431068916,
"grad_norm": 0.16671085357666016,
"learning_rate": 3.118813314037627e-05,
"loss": 0.027464551925659178,
"step": 13000
},
{
"epoch": 0.7583432226692524,
"grad_norm": 1.5406149625778198,
"learning_rate": 3.1043415340086835e-05,
"loss": 0.03511166572570801,
"step": 13100
},
{
"epoch": 0.7641321022316131,
"grad_norm": 0.1813717931509018,
"learning_rate": 3.0898697539797395e-05,
"loss": 0.0282421875,
"step": 13200
},
{
"epoch": 0.7699209817939737,
"grad_norm": 0.25257691740989685,
"learning_rate": 3.075397973950796e-05,
"loss": 0.029794423580169677,
"step": 13300
},
{
"epoch": 0.7757098613563345,
"grad_norm": 0.534304141998291,
"learning_rate": 3.060926193921852e-05,
"loss": 0.030250344276428223,
"step": 13400
},
{
"epoch": 0.7814987409186952,
"grad_norm": 0.8739162087440491,
"learning_rate": 3.046454413892909e-05,
"loss": 0.031027588844299316,
"step": 13500
},
{
"epoch": 0.7872876204810559,
"grad_norm": 0.540971577167511,
"learning_rate": 3.0319826338639658e-05,
"loss": 0.03038400173187256,
"step": 13600
},
{
"epoch": 0.7930765000434166,
"grad_norm": 0.7075596451759338,
"learning_rate": 3.0175108538350215e-05,
"loss": 0.03126862049102783,
"step": 13700
},
{
"epoch": 0.7988653796057773,
"grad_norm": 0.22685867547988892,
"learning_rate": 3.0030390738060782e-05,
"loss": 0.03233437061309814,
"step": 13800
},
{
"epoch": 0.804654259168138,
"grad_norm": 3.8470654487609863,
"learning_rate": 2.9885672937771346e-05,
"loss": 0.03189040184020996,
"step": 13900
},
{
"epoch": 0.8104431387304987,
"grad_norm": 0.16255338490009308,
"learning_rate": 2.9740955137481913e-05,
"loss": 0.030559961795806886,
"step": 14000
},
{
"epoch": 0.8162320182928594,
"grad_norm": 0.4145297110080719,
"learning_rate": 2.9596237337192477e-05,
"loss": 0.027420687675476074,
"step": 14100
},
{
"epoch": 0.8220208978552201,
"grad_norm": 0.23214294016361237,
"learning_rate": 2.9451519536903038e-05,
"loss": 0.02794215202331543,
"step": 14200
},
{
"epoch": 0.8278097774175808,
"grad_norm": 0.18062900006771088,
"learning_rate": 2.9306801736613605e-05,
"loss": 0.028336293697357177,
"step": 14300
},
{
"epoch": 0.8335986569799415,
"grad_norm": 0.7959395051002502,
"learning_rate": 2.916208393632417e-05,
"loss": 0.028267955780029295,
"step": 14400
},
{
"epoch": 0.8393875365423022,
"grad_norm": 0.5956525802612305,
"learning_rate": 2.9017366136034736e-05,
"loss": 0.028834567070007325,
"step": 14500
},
{
"epoch": 0.845176416104663,
"grad_norm": 0.3449164628982544,
"learning_rate": 2.88726483357453e-05,
"loss": 0.03145886182785034,
"step": 14600
},
{
"epoch": 0.8509652956670236,
"grad_norm": 0.16741275787353516,
"learning_rate": 2.872793053545586e-05,
"loss": 0.026835625171661378,
"step": 14700
},
{
"epoch": 0.8567541752293844,
"grad_norm": 0.46983611583709717,
"learning_rate": 2.8583212735166425e-05,
"loss": 0.03117095708847046,
"step": 14800
},
{
"epoch": 0.8625430547917451,
"grad_norm": 0.22663377225399017,
"learning_rate": 2.8438494934876992e-05,
"loss": 0.028009552955627442,
"step": 14900
},
{
"epoch": 0.8683319343541057,
"grad_norm": 0.23122131824493408,
"learning_rate": 2.8293777134587556e-05,
"loss": 0.028059725761413575,
"step": 15000
},
{
"epoch": 0.8683319343541057,
"eval_accuracy": 0.9886279771195148,
"eval_f1": 0.8722127148731833,
"eval_loss": 0.04878264293074608,
"eval_precision": 0.8595016360432922,
"eval_recall": 0.8853054028829203,
"eval_runtime": 32.7448,
"eval_samples_per_second": 381.74,
"eval_steps_per_second": 10.628,
"step": 15000
},
{
"epoch": 0.8741208139164665,
"grad_norm": 0.6293914318084717,
"learning_rate": 2.8149059334298123e-05,
"loss": 0.030007996559143067,
"step": 15100
},
{
"epoch": 0.8799096934788272,
"grad_norm": 0.9233108758926392,
"learning_rate": 2.8004341534008684e-05,
"loss": 0.030494704246520996,
"step": 15200
},
{
"epoch": 0.8856985730411879,
"grad_norm": 0.28081145882606506,
"learning_rate": 2.7859623733719247e-05,
"loss": 0.026717009544372557,
"step": 15300
},
{
"epoch": 0.8914874526035486,
"grad_norm": 0.6658106446266174,
"learning_rate": 2.7714905933429815e-05,
"loss": 0.031118297576904298,
"step": 15400
},
{
"epoch": 0.8972763321659093,
"grad_norm": 0.940838098526001,
"learning_rate": 2.757018813314038e-05,
"loss": 0.03049607515335083,
"step": 15500
},
{
"epoch": 0.90306521172827,
"grad_norm": 0.12419965863227844,
"learning_rate": 2.7425470332850946e-05,
"loss": 0.026502671241760253,
"step": 15600
},
{
"epoch": 0.9088540912906307,
"grad_norm": 1.1096726655960083,
"learning_rate": 2.7280752532561503e-05,
"loss": 0.02529672861099243,
"step": 15700
},
{
"epoch": 0.9146429708529914,
"grad_norm": 0.3621964752674103,
"learning_rate": 2.713603473227207e-05,
"loss": 0.02636525869369507,
"step": 15800
},
{
"epoch": 0.9204318504153521,
"grad_norm": 0.21582575142383575,
"learning_rate": 2.6991316931982634e-05,
"loss": 0.03223026037216187,
"step": 15900
},
{
"epoch": 0.9262207299777128,
"grad_norm": 0.25821372866630554,
"learning_rate": 2.68465991316932e-05,
"loss": 0.026826431751251222,
"step": 16000
},
{
"epoch": 0.9320096095400735,
"grad_norm": 0.399935245513916,
"learning_rate": 2.6701881331403766e-05,
"loss": 0.028431081771850587,
"step": 16100
},
{
"epoch": 0.9377984891024342,
"grad_norm": 0.5942548513412476,
"learning_rate": 2.6557163531114326e-05,
"loss": 0.027340149879455565,
"step": 16200
},
{
"epoch": 0.943587368664795,
"grad_norm": 0.3555188775062561,
"learning_rate": 2.6412445730824893e-05,
"loss": 0.02627647399902344,
"step": 16300
},
{
"epoch": 0.9493762482271556,
"grad_norm": 0.14022284746170044,
"learning_rate": 2.6267727930535457e-05,
"loss": 0.027896411418914795,
"step": 16400
},
{
"epoch": 0.9551651277895163,
"grad_norm": 0.5751340389251709,
"learning_rate": 2.612301013024602e-05,
"loss": 0.02570687770843506,
"step": 16500
},
{
"epoch": 0.9609540073518771,
"grad_norm": 0.44881781935691833,
"learning_rate": 2.597829232995659e-05,
"loss": 0.030154764652252197,
"step": 16600
},
{
"epoch": 0.9667428869142377,
"grad_norm": 0.1963057667016983,
"learning_rate": 2.583357452966715e-05,
"loss": 0.031277601718902585,
"step": 16700
},
{
"epoch": 0.9725317664765984,
"grad_norm": 0.4031456410884857,
"learning_rate": 2.5688856729377713e-05,
"loss": 0.030245101451873778,
"step": 16800
},
{
"epoch": 0.9783206460389592,
"grad_norm": 0.29256272315979004,
"learning_rate": 2.554413892908828e-05,
"loss": 0.031824679374694825,
"step": 16900
},
{
"epoch": 0.9841095256013198,
"grad_norm": 0.42400193214416504,
"learning_rate": 2.5399421128798844e-05,
"loss": 0.028290491104125976,
"step": 17000
},
{
"epoch": 0.9898984051636806,
"grad_norm": 1.173027753829956,
"learning_rate": 2.525470332850941e-05,
"loss": 0.02786562204360962,
"step": 17100
},
{
"epoch": 0.9956872847260413,
"grad_norm": 0.13319961726665497,
"learning_rate": 2.510998552821997e-05,
"loss": 0.030247974395751952,
"step": 17200
},
{
"epoch": 1.0014472198905902,
"grad_norm": 0.8692908883094788,
"learning_rate": 2.4965267727930536e-05,
"loss": 0.029876837730407713,
"step": 17300
},
{
"epoch": 1.0072360994529508,
"grad_norm": 0.132135272026062,
"learning_rate": 2.48205499276411e-05,
"loss": 0.028613386154174806,
"step": 17400
},
{
"epoch": 1.0130249790153116,
"grad_norm": 0.43961101770401,
"learning_rate": 2.4675832127351664e-05,
"loss": 0.02742033004760742,
"step": 17500
},
{
"epoch": 1.0130249790153116,
"eval_accuracy": 0.9893659906022149,
"eval_f1": 0.8761479591836735,
"eval_loss": 0.04772739112377167,
"eval_precision": 0.8623330320377623,
"eval_recall": 0.8904127346261537,
"eval_runtime": 32.383,
"eval_samples_per_second": 386.005,
"eval_steps_per_second": 10.746,
"step": 17500
},
{
"epoch": 1.0188138585776723,
"grad_norm": 1.3907451629638672,
"learning_rate": 2.453111432706223e-05,
"loss": 0.026595606803894042,
"step": 17600
},
{
"epoch": 1.0246027381400329,
"grad_norm": 0.15164747834205627,
"learning_rate": 2.4386396526772795e-05,
"loss": 0.024490804672241212,
"step": 17700
},
{
"epoch": 1.0303916177023937,
"grad_norm": 0.44126424193382263,
"learning_rate": 2.424167872648336e-05,
"loss": 0.023133702278137207,
"step": 17800
},
{
"epoch": 1.0361804972647544,
"grad_norm": 0.14820177853107452,
"learning_rate": 2.4096960926193923e-05,
"loss": 0.02218240737915039,
"step": 17900
},
{
"epoch": 1.0419693768271152,
"grad_norm": 0.5905808210372925,
"learning_rate": 2.3952243125904487e-05,
"loss": 0.020209569931030274,
"step": 18000
},
{
"epoch": 1.0477582563894758,
"grad_norm": 0.17811790108680725,
"learning_rate": 2.380752532561505e-05,
"loss": 0.023463377952575682,
"step": 18100
},
{
"epoch": 1.0535471359518365,
"grad_norm": 0.18444955348968506,
"learning_rate": 2.3662807525325618e-05,
"loss": 0.02178111791610718,
"step": 18200
},
{
"epoch": 1.0593360155141973,
"grad_norm": 0.3301508128643036,
"learning_rate": 2.351808972503618e-05,
"loss": 0.02543956518173218,
"step": 18300
},
{
"epoch": 1.065124895076558,
"grad_norm": 0.1861371099948883,
"learning_rate": 2.3373371924746746e-05,
"loss": 0.024148540496826174,
"step": 18400
},
{
"epoch": 1.0709137746389186,
"grad_norm": 0.3149067163467407,
"learning_rate": 2.3228654124457306e-05,
"loss": 0.023476483821868895,
"step": 18500
},
{
"epoch": 1.0767026542012794,
"grad_norm": 0.17988641560077667,
"learning_rate": 2.3083936324167874e-05,
"loss": 0.02149003028869629,
"step": 18600
},
{
"epoch": 1.08249153376364,
"grad_norm": 0.1312856823205948,
"learning_rate": 2.2939218523878438e-05,
"loss": 0.023462765216827393,
"step": 18700
},
{
"epoch": 1.0882804133260007,
"grad_norm": 0.20052380859851837,
"learning_rate": 2.2794500723589e-05,
"loss": 0.025409071445465087,
"step": 18800
},
{
"epoch": 1.0940692928883615,
"grad_norm": 0.2507052421569824,
"learning_rate": 2.264978292329957e-05,
"loss": 0.026879096031188966,
"step": 18900
},
{
"epoch": 1.0998581724507221,
"grad_norm": 0.15323978662490845,
"learning_rate": 2.250506512301013e-05,
"loss": 0.023210296630859373,
"step": 19000
},
{
"epoch": 1.1056470520130828,
"grad_norm": 0.1345296949148178,
"learning_rate": 2.2360347322720697e-05,
"loss": 0.020816826820373537,
"step": 19100
},
{
"epoch": 1.1114359315754436,
"grad_norm": 0.2258956879377365,
"learning_rate": 2.221562952243126e-05,
"loss": 0.023039839267730712,
"step": 19200
},
{
"epoch": 1.1172248111378043,
"grad_norm": 0.17817442119121552,
"learning_rate": 2.2070911722141824e-05,
"loss": 0.02491870164871216,
"step": 19300
},
{
"epoch": 1.1230136907001649,
"grad_norm": 0.23916760087013245,
"learning_rate": 2.192619392185239e-05,
"loss": 0.02417280673980713,
"step": 19400
},
{
"epoch": 1.1288025702625257,
"grad_norm": 0.5979987978935242,
"learning_rate": 2.1781476121562952e-05,
"loss": 0.025201258659362794,
"step": 19500
},
{
"epoch": 1.1345914498248864,
"grad_norm": 0.7608785033226013,
"learning_rate": 2.1636758321273516e-05,
"loss": 0.02450251579284668,
"step": 19600
},
{
"epoch": 1.1403803293872472,
"grad_norm": 1.2524911165237427,
"learning_rate": 2.1492040520984084e-05,
"loss": 0.02275413990020752,
"step": 19700
},
{
"epoch": 1.1461692089496078,
"grad_norm": 0.4412006139755249,
"learning_rate": 2.1347322720694647e-05,
"loss": 0.023493762016296386,
"step": 19800
},
{
"epoch": 1.1519580885119685,
"grad_norm": 0.1437130719423294,
"learning_rate": 2.120260492040521e-05,
"loss": 0.024696297645568847,
"step": 19900
},
{
"epoch": 1.1577469680743293,
"grad_norm": 0.6046096086502075,
"learning_rate": 2.1057887120115775e-05,
"loss": 0.023616561889648436,
"step": 20000
},
{
"epoch": 1.1577469680743293,
"eval_accuracy": 0.9893949323074188,
"eval_f1": 0.8802002835647409,
"eval_loss": 0.04831967130303383,
"eval_precision": 0.8675126520129919,
"eval_recall": 0.8932645442289744,
"eval_runtime": 32.3669,
"eval_samples_per_second": 386.197,
"eval_steps_per_second": 10.752,
"step": 20000
},
{
"epoch": 1.16353584763669,
"grad_norm": 0.3236995339393616,
"learning_rate": 2.091316931982634e-05,
"loss": 0.024802815914154053,
"step": 20100
},
{
"epoch": 1.1693247271990506,
"grad_norm": 1.4749183654785156,
"learning_rate": 2.0768451519536907e-05,
"loss": 0.0224468994140625,
"step": 20200
},
{
"epoch": 1.1751136067614114,
"grad_norm": 0.7911006212234497,
"learning_rate": 2.0623733719247467e-05,
"loss": 0.021509246826171877,
"step": 20300
},
{
"epoch": 1.180902486323772,
"grad_norm": 0.23929397761821747,
"learning_rate": 2.0479015918958034e-05,
"loss": 0.02354356527328491,
"step": 20400
},
{
"epoch": 1.1866913658861327,
"grad_norm": 0.28904756903648376,
"learning_rate": 2.0334298118668595e-05,
"loss": 0.021830506324768066,
"step": 20500
},
{
"epoch": 1.1924802454484935,
"grad_norm": 0.24184764921665192,
"learning_rate": 2.0189580318379162e-05,
"loss": 0.022603347301483154,
"step": 20600
},
{
"epoch": 1.1982691250108541,
"grad_norm": 0.9602212905883789,
"learning_rate": 2.0044862518089726e-05,
"loss": 0.024089906215667724,
"step": 20700
},
{
"epoch": 1.2040580045732148,
"grad_norm": 0.18168984353542328,
"learning_rate": 1.990014471780029e-05,
"loss": 0.02312016725540161,
"step": 20800
},
{
"epoch": 1.2098468841355756,
"grad_norm": 0.5313889384269714,
"learning_rate": 1.9755426917510854e-05,
"loss": 0.022191174030303955,
"step": 20900
},
{
"epoch": 1.2156357636979362,
"grad_norm": 1.4984052181243896,
"learning_rate": 1.9610709117221418e-05,
"loss": 0.020048980712890626,
"step": 21000
},
{
"epoch": 1.2214246432602969,
"grad_norm": 0.9525922536849976,
"learning_rate": 1.9465991316931985e-05,
"loss": 0.023054752349853515,
"step": 21100
},
{
"epoch": 1.2272135228226577,
"grad_norm": 0.20787988603115082,
"learning_rate": 1.932127351664255e-05,
"loss": 0.02273550271987915,
"step": 21200
},
{
"epoch": 1.2330024023850183,
"grad_norm": 0.19591836631298065,
"learning_rate": 1.9176555716353113e-05,
"loss": 0.02390467405319214,
"step": 21300
},
{
"epoch": 1.2387912819473792,
"grad_norm": 0.1931363046169281,
"learning_rate": 1.9031837916063677e-05,
"loss": 0.023615493774414062,
"step": 21400
},
{
"epoch": 1.2445801615097398,
"grad_norm": 0.16858945786952972,
"learning_rate": 1.888712011577424e-05,
"loss": 0.02515049457550049,
"step": 21500
},
{
"epoch": 1.2503690410721005,
"grad_norm": 0.1835613250732422,
"learning_rate": 1.8742402315484805e-05,
"loss": 0.02049088478088379,
"step": 21600
},
{
"epoch": 1.256157920634461,
"grad_norm": 1.2275546789169312,
"learning_rate": 1.8597684515195372e-05,
"loss": 0.022141406536102293,
"step": 21700
},
{
"epoch": 1.261946800196822,
"grad_norm": 1.089022159576416,
"learning_rate": 1.8452966714905933e-05,
"loss": 0.022219130992889403,
"step": 21800
},
{
"epoch": 1.2677356797591826,
"grad_norm": 0.32157450914382935,
"learning_rate": 1.83082489146165e-05,
"loss": 0.025665369033813477,
"step": 21900
},
{
"epoch": 1.2735245593215434,
"grad_norm": 0.28916555643081665,
"learning_rate": 1.816353111432706e-05,
"loss": 0.022141153812408446,
"step": 22000
},
{
"epoch": 1.279313438883904,
"grad_norm": 0.4547838866710663,
"learning_rate": 1.8018813314037628e-05,
"loss": 0.02140897512435913,
"step": 22100
},
{
"epoch": 1.2851023184462647,
"grad_norm": 0.2740997076034546,
"learning_rate": 1.787409551374819e-05,
"loss": 0.01996962308883667,
"step": 22200
},
{
"epoch": 1.2908911980086255,
"grad_norm": 0.17777739465236664,
"learning_rate": 1.7729377713458756e-05,
"loss": 0.020210413932800292,
"step": 22300
},
{
"epoch": 1.2966800775709861,
"grad_norm": 0.2631765604019165,
"learning_rate": 1.7584659913169323e-05,
"loss": 0.02249443531036377,
"step": 22400
},
{
"epoch": 1.3024689571333468,
"grad_norm": 2.136570453643799,
"learning_rate": 1.7439942112879883e-05,
"loss": 0.02353119134902954,
"step": 22500
},
{
"epoch": 1.3024689571333468,
"eval_accuracy": 0.9900812641736834,
"eval_f1": 0.8825427722569409,
"eval_loss": 0.046070199459791183,
"eval_precision": 0.8720012146978439,
"eval_recall": 0.8933423208545058,
"eval_runtime": 32.9824,
"eval_samples_per_second": 378.99,
"eval_steps_per_second": 10.551,
"step": 22500
},
{
"epoch": 1.3082578366957076,
"grad_norm": 0.16276246309280396,
"learning_rate": 1.729522431259045e-05,
"loss": 0.021528096199035646,
"step": 22600
},
{
"epoch": 1.3140467162580682,
"grad_norm": 0.1779128611087799,
"learning_rate": 1.7150506512301015e-05,
"loss": 0.021381580829620363,
"step": 22700
},
{
"epoch": 1.3198355958204289,
"grad_norm": 0.12842315435409546,
"learning_rate": 1.700578871201158e-05,
"loss": 0.022963883876800536,
"step": 22800
},
{
"epoch": 1.3256244753827897,
"grad_norm": 0.38589125871658325,
"learning_rate": 1.6861070911722142e-05,
"loss": 0.025010223388671874,
"step": 22900
},
{
"epoch": 1.3314133549451503,
"grad_norm": 0.17700180411338806,
"learning_rate": 1.6716353111432706e-05,
"loss": 0.025014562606811522,
"step": 23000
},
{
"epoch": 1.3372022345075112,
"grad_norm": 0.1977829933166504,
"learning_rate": 1.657163531114327e-05,
"loss": 0.019888348579406738,
"step": 23100
},
{
"epoch": 1.3429911140698718,
"grad_norm": 0.21066619455814362,
"learning_rate": 1.6426917510853838e-05,
"loss": 0.021409926414489747,
"step": 23200
},
{
"epoch": 1.3487799936322324,
"grad_norm": 0.1378607600927353,
"learning_rate": 1.6282199710564398e-05,
"loss": 0.02372417688369751,
"step": 23300
},
{
"epoch": 1.354568873194593,
"grad_norm": 0.3123644292354584,
"learning_rate": 1.6137481910274965e-05,
"loss": 0.021678264141082763,
"step": 23400
},
{
"epoch": 1.360357752756954,
"grad_norm": 0.19485028088092804,
"learning_rate": 1.599276410998553e-05,
"loss": 0.024895586967468263,
"step": 23500
},
{
"epoch": 1.3661466323193145,
"grad_norm": 0.2177608162164688,
"learning_rate": 1.5848046309696093e-05,
"loss": 0.020630009174346924,
"step": 23600
},
{
"epoch": 1.3719355118816754,
"grad_norm": 1.222109317779541,
"learning_rate": 1.570332850940666e-05,
"loss": 0.022696774005889892,
"step": 23700
},
{
"epoch": 1.377724391444036,
"grad_norm": 0.5391749143600464,
"learning_rate": 1.555861070911722e-05,
"loss": 0.019349946975708007,
"step": 23800
},
{
"epoch": 1.3835132710063966,
"grad_norm": 0.8667725920677185,
"learning_rate": 1.541389290882779e-05,
"loss": 0.021944737434387206,
"step": 23900
},
{
"epoch": 1.3893021505687575,
"grad_norm": 0.2695491909980774,
"learning_rate": 1.526917510853835e-05,
"loss": 0.023090031147003174,
"step": 24000
},
{
"epoch": 1.3950910301311181,
"grad_norm": 0.470904678106308,
"learning_rate": 1.5124457308248916e-05,
"loss": 0.023335537910461425,
"step": 24100
},
{
"epoch": 1.4008799096934788,
"grad_norm": 0.12368060648441315,
"learning_rate": 1.4979739507959482e-05,
"loss": 0.020203118324279786,
"step": 24200
},
{
"epoch": 1.4066687892558396,
"grad_norm": 0.8601803779602051,
"learning_rate": 1.4835021707670044e-05,
"loss": 0.024733288288116453,
"step": 24300
},
{
"epoch": 1.4124576688182002,
"grad_norm": 0.12211176753044128,
"learning_rate": 1.469030390738061e-05,
"loss": 0.0239523983001709,
"step": 24400
},
{
"epoch": 1.4182465483805609,
"grad_norm": 0.15338654816150665,
"learning_rate": 1.4545586107091172e-05,
"loss": 0.02348433494567871,
"step": 24500
},
{
"epoch": 1.4240354279429217,
"grad_norm": 0.14509518444538116,
"learning_rate": 1.4400868306801738e-05,
"loss": 0.024761919975280763,
"step": 24600
},
{
"epoch": 1.4298243075052823,
"grad_norm": 0.3267483115196228,
"learning_rate": 1.4256150506512303e-05,
"loss": 0.02035109281539917,
"step": 24700
},
{
"epoch": 1.4356131870676432,
"grad_norm": 0.7865790128707886,
"learning_rate": 1.4111432706222865e-05,
"loss": 0.020213403701782227,
"step": 24800
},
{
"epoch": 1.4414020666300038,
"grad_norm": 0.6819100975990295,
"learning_rate": 1.3966714905933431e-05,
"loss": 0.02440610408782959,
"step": 24900
},
{
"epoch": 1.4471909461923644,
"grad_norm": 0.22851134836673737,
"learning_rate": 1.3821997105643993e-05,
"loss": 0.019472746849060057,
"step": 25000
},
{
"epoch": 1.4471909461923644,
"eval_accuracy": 0.9902693852575088,
"eval_f1": 0.8853341536568484,
"eval_loss": 0.04390441253781319,
"eval_precision": 0.8755260355929625,
"eval_recall": 0.8953645131183242,
"eval_runtime": 32.2884,
"eval_samples_per_second": 387.136,
"eval_steps_per_second": 10.778,
"step": 25000
},
{
"epoch": 1.452979825754725,
"grad_norm": 0.3433781564235687,
"learning_rate": 1.3677279305354559e-05,
"loss": 0.021682107448577882,
"step": 25100
},
{
"epoch": 1.458768705317086,
"grad_norm": 0.2263897955417633,
"learning_rate": 1.3532561505065124e-05,
"loss": 0.020724060535430907,
"step": 25200
},
{
"epoch": 1.4645575848794465,
"grad_norm": 0.5709189772605896,
"learning_rate": 1.3387843704775688e-05,
"loss": 0.023897509574890136,
"step": 25300
},
{
"epoch": 1.4703464644418074,
"grad_norm": 0.13530676066875458,
"learning_rate": 1.3243125904486254e-05,
"loss": 0.022753942012786865,
"step": 25400
},
{
"epoch": 1.476135344004168,
"grad_norm": 0.42096275091171265,
"learning_rate": 1.3098408104196816e-05,
"loss": 0.021938772201538087,
"step": 25500
},
{
"epoch": 1.4819242235665286,
"grad_norm": 2.0374867916107178,
"learning_rate": 1.2953690303907382e-05,
"loss": 0.023144633769989015,
"step": 25600
},
{
"epoch": 1.4877131031288893,
"grad_norm": 0.22001959383487701,
"learning_rate": 1.2808972503617947e-05,
"loss": 0.021838405132293702,
"step": 25700
},
{
"epoch": 1.4935019826912501,
"grad_norm": 0.2641585171222687,
"learning_rate": 1.266425470332851e-05,
"loss": 0.021520249843597412,
"step": 25800
},
{
"epoch": 1.4992908622536107,
"grad_norm": 0.191110759973526,
"learning_rate": 1.2519536903039075e-05,
"loss": 0.01960566997528076,
"step": 25900
},
{
"epoch": 1.5050797418159716,
"grad_norm": 1.1695928573608398,
"learning_rate": 1.2374819102749639e-05,
"loss": 0.022222683429718018,
"step": 26000
},
{
"epoch": 1.5108686213783322,
"grad_norm": 0.19455936551094055,
"learning_rate": 1.2230101302460203e-05,
"loss": 0.020654516220092775,
"step": 26100
},
{
"epoch": 1.5166575009406928,
"grad_norm": 0.15471012890338898,
"learning_rate": 1.2085383502170767e-05,
"loss": 0.022886896133422853,
"step": 26200
},
{
"epoch": 1.5224463805030535,
"grad_norm": 1.4628580808639526,
"learning_rate": 1.1940665701881331e-05,
"loss": 0.02138796329498291,
"step": 26300
},
{
"epoch": 1.5282352600654143,
"grad_norm": 0.49336832761764526,
"learning_rate": 1.1795947901591896e-05,
"loss": 0.021676077842712402,
"step": 26400
},
{
"epoch": 1.5340241396277752,
"grad_norm": 0.18711985647678375,
"learning_rate": 1.1651230101302462e-05,
"loss": 0.022171633243560793,
"step": 26500
},
{
"epoch": 1.5398130191901358,
"grad_norm": 0.197096049785614,
"learning_rate": 1.1506512301013026e-05,
"loss": 0.021774094104766845,
"step": 26600
},
{
"epoch": 1.5456018987524964,
"grad_norm": 0.17335055768489838,
"learning_rate": 1.136179450072359e-05,
"loss": 0.019333064556121826,
"step": 26700
},
{
"epoch": 1.551390778314857,
"grad_norm": 0.9639333486557007,
"learning_rate": 1.1217076700434154e-05,
"loss": 0.021504545211791994,
"step": 26800
},
{
"epoch": 1.557179657877218,
"grad_norm": 0.7893505692481995,
"learning_rate": 1.1072358900144718e-05,
"loss": 0.01952719211578369,
"step": 26900
},
{
"epoch": 1.5629685374395785,
"grad_norm": 0.11000892519950867,
"learning_rate": 1.0927641099855283e-05,
"loss": 0.023864905834197998,
"step": 27000
},
{
"epoch": 1.5687574170019394,
"grad_norm": 1.0035220384597778,
"learning_rate": 1.0782923299565847e-05,
"loss": 0.022396252155303956,
"step": 27100
},
{
"epoch": 1.5745462965643,
"grad_norm": 0.18122516572475433,
"learning_rate": 1.0638205499276411e-05,
"loss": 0.02149169921875,
"step": 27200
},
{
"epoch": 1.5803351761266606,
"grad_norm": 0.4648451805114746,
"learning_rate": 1.0493487698986975e-05,
"loss": 0.02050316572189331,
"step": 27300
},
{
"epoch": 1.5861240556890213,
"grad_norm": 0.7127793431282043,
"learning_rate": 1.0348769898697539e-05,
"loss": 0.021997590065002442,
"step": 27400
},
{
"epoch": 1.591912935251382,
"grad_norm": 0.41411492228507996,
"learning_rate": 1.0204052098408105e-05,
"loss": 0.02217501640319824,
"step": 27500
},
{
"epoch": 1.591912935251382,
"eval_accuracy": 0.9900791969090259,
"eval_f1": 0.886322562452736,
"eval_loss": 0.04419637843966484,
"eval_precision": 0.8764925089360408,
"eval_recall": 0.8963756092502333,
"eval_runtime": 32.2485,
"eval_samples_per_second": 387.615,
"eval_steps_per_second": 10.791,
"step": 27500
},
{
"epoch": 1.597701814813743,
"grad_norm": 0.7603561878204346,
"learning_rate": 1.005933429811867e-05,
"loss": 0.019264650344848634,
"step": 27600
},
{
"epoch": 1.6034906943761036,
"grad_norm": 0.44727957248687744,
"learning_rate": 9.914616497829234e-06,
"loss": 0.024952189922332765,
"step": 27700
},
{
"epoch": 1.6092795739384642,
"grad_norm": 0.3509667217731476,
"learning_rate": 9.769898697539798e-06,
"loss": 0.02343012571334839,
"step": 27800
},
{
"epoch": 1.6150684535008248,
"grad_norm": 0.1554228961467743,
"learning_rate": 9.625180897250362e-06,
"loss": 0.022485718727111817,
"step": 27900
},
{
"epoch": 1.6208573330631855,
"grad_norm": 0.48960787057876587,
"learning_rate": 9.480463096960928e-06,
"loss": 0.022733292579650878,
"step": 28000
},
{
"epoch": 1.6266462126255463,
"grad_norm": 0.4882723093032837,
"learning_rate": 9.335745296671492e-06,
"loss": 0.02101508617401123,
"step": 28100
},
{
"epoch": 1.6324350921879072,
"grad_norm": 0.3346649408340454,
"learning_rate": 9.191027496382055e-06,
"loss": 0.02136120557785034,
"step": 28200
},
{
"epoch": 1.6382239717502678,
"grad_norm": 0.43525007367134094,
"learning_rate": 9.04630969609262e-06,
"loss": 0.019716554880142213,
"step": 28300
},
{
"epoch": 1.6440128513126284,
"grad_norm": 1.4369014501571655,
"learning_rate": 8.901591895803183e-06,
"loss": 0.021362924575805665,
"step": 28400
},
{
"epoch": 1.649801730874989,
"grad_norm": 0.36247485876083374,
"learning_rate": 8.756874095513747e-06,
"loss": 0.022539958953857422,
"step": 28500
},
{
"epoch": 1.65559061043735,
"grad_norm": 0.1396828442811966,
"learning_rate": 8.612156295224313e-06,
"loss": 0.01977320432662964,
"step": 28600
},
{
"epoch": 1.6613794899997105,
"grad_norm": 0.09776929765939713,
"learning_rate": 8.467438494934877e-06,
"loss": 0.017783541679382325,
"step": 28700
},
{
"epoch": 1.6671683695620714,
"grad_norm": 0.20341573655605316,
"learning_rate": 8.322720694645442e-06,
"loss": 0.01956522822380066,
"step": 28800
},
{
"epoch": 1.672957249124432,
"grad_norm": 0.24861733615398407,
"learning_rate": 8.178002894356006e-06,
"loss": 0.02077195405960083,
"step": 28900
},
{
"epoch": 1.6787461286867926,
"grad_norm": 0.14596840739250183,
"learning_rate": 8.03328509406657e-06,
"loss": 0.019236416816711427,
"step": 29000
},
{
"epoch": 1.6845350082491533,
"grad_norm": 0.1839938908815384,
"learning_rate": 7.888567293777136e-06,
"loss": 0.023349857330322264,
"step": 29100
},
{
"epoch": 1.690323887811514,
"grad_norm": 0.5248807668685913,
"learning_rate": 7.7438494934877e-06,
"loss": 0.020743234157562254,
"step": 29200
},
{
"epoch": 1.696112767373875,
"grad_norm": 0.23738259077072144,
"learning_rate": 7.599131693198264e-06,
"loss": 0.02022059917449951,
"step": 29300
},
{
"epoch": 1.7019016469362356,
"grad_norm": 0.6698647737503052,
"learning_rate": 7.4544138929088275e-06,
"loss": 0.01865126848220825,
"step": 29400
},
{
"epoch": 1.7076905264985962,
"grad_norm": 1.6622151136398315,
"learning_rate": 7.309696092619392e-06,
"loss": 0.020002634525299073,
"step": 29500
},
{
"epoch": 1.7134794060609568,
"grad_norm": 0.3179205358028412,
"learning_rate": 7.164978292329957e-06,
"loss": 0.021126785278320313,
"step": 29600
},
{
"epoch": 1.7192682856233175,
"grad_norm": 0.10927774757146835,
"learning_rate": 7.020260492040522e-06,
"loss": 0.018858327865600585,
"step": 29700
},
{
"epoch": 1.7250571651856783,
"grad_norm": 0.186599463224411,
"learning_rate": 6.875542691751086e-06,
"loss": 0.01988905429840088,
"step": 29800
},
{
"epoch": 1.7308460447480392,
"grad_norm": 0.22831496596336365,
"learning_rate": 6.73082489146165e-06,
"loss": 0.020202479362487792,
"step": 29900
},
{
"epoch": 1.7366349243103998,
"grad_norm": 0.3853333294391632,
"learning_rate": 6.586107091172214e-06,
"loss": 0.01944092631340027,
"step": 30000
},
{
"epoch": 1.7366349243103998,
"eval_accuracy": 0.9902431999051815,
"eval_f1": 0.8897238929427909,
"eval_loss": 0.043809473514556885,
"eval_precision": 0.8803197563760944,
"eval_recall": 0.8993311210204293,
"eval_runtime": 32.3718,
"eval_samples_per_second": 386.139,
"eval_steps_per_second": 10.75,
"step": 30000
},
{
"epoch": 1.7424238038727604,
"grad_norm": 0.5895107984542847,
"learning_rate": 6.441389290882779e-06,
"loss": 0.020335075855255128,
"step": 30100
},
{
"epoch": 1.748212683435121,
"grad_norm": 0.10662174969911575,
"learning_rate": 6.296671490593344e-06,
"loss": 0.020258052349090575,
"step": 30200
},
{
"epoch": 1.7540015629974819,
"grad_norm": 3.988093376159668,
"learning_rate": 6.151953690303908e-06,
"loss": 0.0205714750289917,
"step": 30300
},
{
"epoch": 1.7597904425598425,
"grad_norm": 0.5093377828598022,
"learning_rate": 6.007235890014472e-06,
"loss": 0.020437090396881102,
"step": 30400
},
{
"epoch": 1.7655793221222034,
"grad_norm": 0.29351383447647095,
"learning_rate": 5.8625180897250366e-06,
"loss": 0.01850534439086914,
"step": 30500
},
{
"epoch": 1.771368201684564,
"grad_norm": 0.199212908744812,
"learning_rate": 5.7178002894356005e-06,
"loss": 0.02155954599380493,
"step": 30600
},
{
"epoch": 1.7771570812469246,
"grad_norm": 0.346227765083313,
"learning_rate": 5.573082489146165e-06,
"loss": 0.019093557596206664,
"step": 30700
},
{
"epoch": 1.7829459608092852,
"grad_norm": 0.28586652874946594,
"learning_rate": 5.42836468885673e-06,
"loss": 0.022267727851867675,
"step": 30800
},
{
"epoch": 1.788734840371646,
"grad_norm": 0.16195492446422577,
"learning_rate": 5.283646888567294e-06,
"loss": 0.019566291570663454,
"step": 30900
},
{
"epoch": 1.7945237199340067,
"grad_norm": 0.2971166968345642,
"learning_rate": 5.138929088277859e-06,
"loss": 0.01942929744720459,
"step": 31000
},
{
"epoch": 1.8003125994963676,
"grad_norm": 0.17818105220794678,
"learning_rate": 4.994211287988423e-06,
"loss": 0.02038184642791748,
"step": 31100
},
{
"epoch": 1.8061014790587282,
"grad_norm": 0.29902341961860657,
"learning_rate": 4.849493487698987e-06,
"loss": 0.019359084367752074,
"step": 31200
},
{
"epoch": 1.8118903586210888,
"grad_norm": 0.25175297260284424,
"learning_rate": 4.704775687409551e-06,
"loss": 0.02133084535598755,
"step": 31300
},
{
"epoch": 1.8176792381834495,
"grad_norm": 0.37808459997177124,
"learning_rate": 4.560057887120116e-06,
"loss": 0.01949509859085083,
"step": 31400
},
{
"epoch": 1.8234681177458103,
"grad_norm": 0.6678466200828552,
"learning_rate": 4.415340086830681e-06,
"loss": 0.018650727272033693,
"step": 31500
},
{
"epoch": 1.8292569973081712,
"grad_norm": 0.5661903619766235,
"learning_rate": 4.270622286541245e-06,
"loss": 0.020224461555480956,
"step": 31600
},
{
"epoch": 1.8350458768705318,
"grad_norm": 0.295162558555603,
"learning_rate": 4.125904486251809e-06,
"loss": 0.0190382981300354,
"step": 31700
},
{
"epoch": 1.8408347564328924,
"grad_norm": 0.5357158184051514,
"learning_rate": 3.981186685962373e-06,
"loss": 0.02294764518737793,
"step": 31800
},
{
"epoch": 1.846623635995253,
"grad_norm": 0.2613368630409241,
"learning_rate": 3.836468885672938e-06,
"loss": 0.019658113718032836,
"step": 31900
},
{
"epoch": 1.8524125155576137,
"grad_norm": 0.3176723122596741,
"learning_rate": 3.6917510853835025e-06,
"loss": 0.01859914779663086,
"step": 32000
},
{
"epoch": 1.8582013951199745,
"grad_norm": 0.1181308925151825,
"learning_rate": 3.547033285094067e-06,
"loss": 0.02106498718261719,
"step": 32100
},
{
"epoch": 1.8639902746823354,
"grad_norm": 0.6285836100578308,
"learning_rate": 3.4023154848046308e-06,
"loss": 0.019543524980545044,
"step": 32200
},
{
"epoch": 1.869779154244696,
"grad_norm": 0.221060112118721,
"learning_rate": 3.2575976845151955e-06,
"loss": 0.019698797464370726,
"step": 32300
},
{
"epoch": 1.8755680338070566,
"grad_norm": 0.46701422333717346,
"learning_rate": 3.11287988422576e-06,
"loss": 0.02131035327911377,
"step": 32400
},
{
"epoch": 1.8813569133694172,
"grad_norm": 0.8717579245567322,
"learning_rate": 2.968162083936324e-06,
"loss": 0.0199610698223114,
"step": 32500
},
{
"epoch": 1.8813569133694172,
"eval_accuracy": 0.9909171281835014,
"eval_f1": 0.8929190695762744,
"eval_loss": 0.04036634415388107,
"eval_precision": 0.8848160875652284,
"eval_recall": 0.9011718344913409,
"eval_runtime": 32.8086,
"eval_samples_per_second": 380.998,
"eval_steps_per_second": 10.607,
"step": 32500
},
{
"epoch": 1.887145792931778,
"grad_norm": 0.42211058735847473,
"learning_rate": 2.8234442836468885e-06,
"loss": 0.01953967571258545,
"step": 32600
},
{
"epoch": 1.8929346724941387,
"grad_norm": 0.14807343482971191,
"learning_rate": 2.6787264833574533e-06,
"loss": 0.02133486270904541,
"step": 32700
},
{
"epoch": 1.8987235520564996,
"grad_norm": 0.2488560974597931,
"learning_rate": 2.5340086830680177e-06,
"loss": 0.02061129570007324,
"step": 32800
},
{
"epoch": 1.9045124316188602,
"grad_norm": 0.12760600447654724,
"learning_rate": 2.3892908827785816e-06,
"loss": 0.018405574560165405,
"step": 32900
},
{
"epoch": 1.9103013111812208,
"grad_norm": 0.14860856533050537,
"learning_rate": 2.2445730824891463e-06,
"loss": 0.018643089532852174,
"step": 33000
},
{
"epoch": 1.9160901907435814,
"grad_norm": 0.21985752880573273,
"learning_rate": 2.0998552821997107e-06,
"loss": 0.01826516628265381,
"step": 33100
},
{
"epoch": 1.9218790703059423,
"grad_norm": 0.12793774902820587,
"learning_rate": 1.955137481910275e-06,
"loss": 0.018108237981796265,
"step": 33200
},
{
"epoch": 1.9276679498683031,
"grad_norm": 0.6992884278297424,
"learning_rate": 1.8104196816208394e-06,
"loss": 0.018568735122680664,
"step": 33300
},
{
"epoch": 1.9334568294306638,
"grad_norm": 0.16569721698760986,
"learning_rate": 1.6657018813314037e-06,
"loss": 0.020773212909698486,
"step": 33400
},
{
"epoch": 1.9392457089930244,
"grad_norm": 0.2137010395526886,
"learning_rate": 1.5209840810419682e-06,
"loss": 0.020217933654785157,
"step": 33500
},
{
"epoch": 1.945034588555385,
"grad_norm": 0.2512764036655426,
"learning_rate": 1.3762662807525328e-06,
"loss": 0.021186413764953612,
"step": 33600
},
{
"epoch": 1.9508234681177457,
"grad_norm": 1.0330688953399658,
"learning_rate": 1.231548480463097e-06,
"loss": 0.02138917684555054,
"step": 33700
},
{
"epoch": 1.9566123476801065,
"grad_norm": 0.3796994090080261,
"learning_rate": 1.0868306801736615e-06,
"loss": 0.017367198467254638,
"step": 33800
},
{
"epoch": 1.9624012272424673,
"grad_norm": 0.35818561911582947,
"learning_rate": 9.421128798842257e-07,
"loss": 0.019348199367523192,
"step": 33900
},
{
"epoch": 1.968190106804828,
"grad_norm": 0.4799649715423584,
"learning_rate": 7.973950795947903e-07,
"loss": 0.022617738246917724,
"step": 34000
},
{
"epoch": 1.9739789863671886,
"grad_norm": 0.8583610653877258,
"learning_rate": 6.526772793053546e-07,
"loss": 0.019666857719421386,
"step": 34100
},
{
"epoch": 1.9797678659295492,
"grad_norm": 0.6525281667709351,
"learning_rate": 5.079594790159189e-07,
"loss": 0.020464680194854735,
"step": 34200
},
{
"epoch": 1.98555674549191,
"grad_norm": 1.2383188009262085,
"learning_rate": 3.632416787264834e-07,
"loss": 0.018764994144439696,
"step": 34300
},
{
"epoch": 1.9913456250542707,
"grad_norm": 0.19601252675056458,
"learning_rate": 2.1852387843704776e-07,
"loss": 0.018834112882614135,
"step": 34400
},
{
"epoch": 1.9971345046166316,
"grad_norm": 0.25431913137435913,
"learning_rate": 7.380607814761216e-08,
"loss": 0.018961663246154784,
"step": 34500
},
{
"epoch": 2.0,
"step": 34550,
"total_flos": 1.1376036548759528e+18,
"train_loss": 0.03949730815487212,
"train_runtime": 14944.1573,
"train_samples_per_second": 332.906,
"train_steps_per_second": 2.312
}
],
"logging_steps": 100,
"max_steps": 34550,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 2500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.1376036548759528e+18,
"train_batch_size": 72,
"trial_name": null,
"trial_params": null
}