Bo-Multilayer-Detection / training /trainer_state.json
karma689's picture
Upload mmbert_base_v1.2
d190c88 verified
Raw History Blame Contribute Delete
136 kB
{
"best_global_step": 10832,
"best_metric": 0.09284739816799845,
"best_model_checkpoint": "/root/layer_detection_model_train/experiments/mmbert_base_v1.2/outputs/checkpoint-10832",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 13540,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.014776505356483192,
"grad_norm": 701.1569213867188,
"learning_rate": 7.016248153618908e-08,
"loss": 22.79461669921875,
"step": 20
},
{
"epoch": 0.029553010712966385,
"grad_norm": 662.001708984375,
"learning_rate": 1.4401772525849335e-07,
"loss": 21.17723846435547,
"step": 40
},
{
"epoch": 0.04432951606944958,
"grad_norm": 609.3135375976562,
"learning_rate": 2.1787296898079766e-07,
"loss": 18.12454833984375,
"step": 60
},
{
"epoch": 0.05910602142593277,
"grad_norm": 594.9791870117188,
"learning_rate": 2.9172821270310194e-07,
"loss": 13.425947570800782,
"step": 80
},
{
"epoch": 0.07388252678241596,
"grad_norm": 327.8644104003906,
"learning_rate": 3.655834564254062e-07,
"loss": 6.798075866699219,
"step": 100
},
{
"epoch": 0.08865903213889915,
"grad_norm": 43.477909088134766,
"learning_rate": 4.394387001477105e-07,
"loss": 1.6769073486328125,
"step": 120
},
{
"epoch": 0.10343553749538234,
"grad_norm": 19.129718780517578,
"learning_rate": 5.132939438700148e-07,
"loss": 0.6704708576202393,
"step": 140
},
{
"epoch": 0.11821204285186554,
"grad_norm": 41.66476058959961,
"learning_rate": 5.871491875923191e-07,
"loss": 0.5174216270446778,
"step": 160
},
{
"epoch": 0.13298854820834874,
"grad_norm": 7.395859718322754,
"learning_rate": 6.610044313146234e-07,
"loss": 0.5036676406860352,
"step": 180
},
{
"epoch": 0.1477650535648319,
"grad_norm": 5.110939025878906,
"learning_rate": 7.348596750369278e-07,
"loss": 0.4235406398773193,
"step": 200
},
{
"epoch": 0.1625415589213151,
"grad_norm": 10.699678421020508,
"learning_rate": 8.087149187592319e-07,
"loss": 0.49722752571105955,
"step": 220
},
{
"epoch": 0.1773180642777983,
"grad_norm": 12.544513702392578,
"learning_rate": 8.825701624815362e-07,
"loss": 0.36336729526519773,
"step": 240
},
{
"epoch": 0.19209456963428148,
"grad_norm": 10.595778465270996,
"learning_rate": 9.564254062038405e-07,
"loss": 0.4079566955566406,
"step": 260
},
{
"epoch": 0.20687107499076468,
"grad_norm": 3.1899571418762207,
"learning_rate": 1.0302806499261449e-06,
"loss": 0.35996232032775877,
"step": 280
},
{
"epoch": 0.22164758034724788,
"grad_norm": 9.337206840515137,
"learning_rate": 1.1041358936484493e-06,
"loss": 0.3835803270339966,
"step": 300
},
{
"epoch": 0.23642408570373108,
"grad_norm": 8.738773345947266,
"learning_rate": 1.1779911373707534e-06,
"loss": 0.4507084846496582,
"step": 320
},
{
"epoch": 0.25120059106021425,
"grad_norm": 16.647048950195312,
"learning_rate": 1.2518463810930578e-06,
"loss": 0.3412694692611694,
"step": 340
},
{
"epoch": 0.2659770964166975,
"grad_norm": 11.143296241760254,
"learning_rate": 1.325701624815362e-06,
"loss": 0.3433049440383911,
"step": 360
},
{
"epoch": 0.28075360177318065,
"grad_norm": 37.5615234375,
"learning_rate": 1.3995568685376662e-06,
"loss": 0.5304166316986084,
"step": 380
},
{
"epoch": 0.2955301071296638,
"grad_norm": 11.18875789642334,
"learning_rate": 1.4734121122599708e-06,
"loss": 0.30967762470245364,
"step": 400
},
{
"epoch": 0.31030661248614705,
"grad_norm": 5.1344451904296875,
"learning_rate": 1.547267355982275e-06,
"loss": 0.32960081100463867,
"step": 420
},
{
"epoch": 0.3250831178426302,
"grad_norm": 2.6115169525146484,
"learning_rate": 1.6211225997045791e-06,
"loss": 0.27993030548095704,
"step": 440
},
{
"epoch": 0.3398596231991134,
"grad_norm": 5.217758655548096,
"learning_rate": 1.6949778434268835e-06,
"loss": 0.31906490325927733,
"step": 460
},
{
"epoch": 0.3546361285555966,
"grad_norm": 11.346961975097656,
"learning_rate": 1.7688330871491877e-06,
"loss": 0.2474289655685425,
"step": 480
},
{
"epoch": 0.3694126339120798,
"grad_norm": 10.116162300109863,
"learning_rate": 1.842688330871492e-06,
"loss": 0.23720188140869142,
"step": 500
},
{
"epoch": 0.38418913926856296,
"grad_norm": 2.5597643852233887,
"learning_rate": 1.9165435745937964e-06,
"loss": 0.35997202396392824,
"step": 520
},
{
"epoch": 0.3989656446250462,
"grad_norm": 9.458195686340332,
"learning_rate": 1.9903988183161006e-06,
"loss": 0.2479008913040161,
"step": 540
},
{
"epoch": 0.41374214998152936,
"grad_norm": 7.1438422203063965,
"learning_rate": 2.0642540620384048e-06,
"loss": 0.29055349826812743,
"step": 560
},
{
"epoch": 0.42851865533801253,
"grad_norm": 26.124317169189453,
"learning_rate": 2.138109305760709e-06,
"loss": 0.23474643230438233,
"step": 580
},
{
"epoch": 0.44329516069449576,
"grad_norm": 12.375730514526367,
"learning_rate": 2.2119645494830135e-06,
"loss": 0.24732532501220703,
"step": 600
},
{
"epoch": 0.45807166605097893,
"grad_norm": 8.825639724731445,
"learning_rate": 2.2858197932053177e-06,
"loss": 0.21216919422149658,
"step": 620
},
{
"epoch": 0.47284817140746216,
"grad_norm": 15.930329322814941,
"learning_rate": 2.359675036927622e-06,
"loss": 0.24057672023773194,
"step": 640
},
{
"epoch": 0.48762467676394533,
"grad_norm": 1.648369550704956,
"learning_rate": 2.4335302806499265e-06,
"loss": 0.22210261821746827,
"step": 660
},
{
"epoch": 0.5024011821204285,
"grad_norm": 22.25632667541504,
"learning_rate": 2.5073855243722307e-06,
"loss": 0.2805967092514038,
"step": 680
},
{
"epoch": 0.5171776874769117,
"grad_norm": 7.98917293548584,
"learning_rate": 2.5812407680945353e-06,
"loss": 0.23512835502624513,
"step": 700
},
{
"epoch": 0.531954192833395,
"grad_norm": 2.8459553718566895,
"learning_rate": 2.655096011816839e-06,
"loss": 0.24262547492980957,
"step": 720
},
{
"epoch": 0.5467306981898781,
"grad_norm": 16.777976989746094,
"learning_rate": 2.7289512555391436e-06,
"loss": 0.18053247928619384,
"step": 740
},
{
"epoch": 0.5615072035463613,
"grad_norm": 5.54146146774292,
"learning_rate": 2.8028064992614478e-06,
"loss": 0.288055419921875,
"step": 760
},
{
"epoch": 0.5762837089028445,
"grad_norm": 8.700989723205566,
"learning_rate": 2.8766617429837524e-06,
"loss": 0.22562708854675292,
"step": 780
},
{
"epoch": 0.5910602142593276,
"grad_norm": 8.646881103515625,
"learning_rate": 2.950516986706056e-06,
"loss": 0.20924983024597169,
"step": 800
},
{
"epoch": 0.6058367196158109,
"grad_norm": 12.20388412475586,
"learning_rate": 3.0243722304283607e-06,
"loss": 0.2840768098831177,
"step": 820
},
{
"epoch": 0.6206132249722941,
"grad_norm": 23.990116119384766,
"learning_rate": 3.0982274741506653e-06,
"loss": 0.2565877676010132,
"step": 840
},
{
"epoch": 0.6353897303287772,
"grad_norm": 3.284641981124878,
"learning_rate": 3.172082717872969e-06,
"loss": 0.25729591846466066,
"step": 860
},
{
"epoch": 0.6501662356852604,
"grad_norm": 14.040314674377441,
"learning_rate": 3.2459379615952737e-06,
"loss": 0.15883971452713014,
"step": 880
},
{
"epoch": 0.6649427410417437,
"grad_norm": 11.8453950881958,
"learning_rate": 3.319793205317578e-06,
"loss": 0.265518045425415,
"step": 900
},
{
"epoch": 0.6797192463982268,
"grad_norm": 5.4114990234375,
"learning_rate": 3.393648449039882e-06,
"loss": 0.21104788780212402,
"step": 920
},
{
"epoch": 0.69449575175471,
"grad_norm": 5.626718044281006,
"learning_rate": 3.467503692762186e-06,
"loss": 0.21398870944976806,
"step": 940
},
{
"epoch": 0.7092722571111932,
"grad_norm": 8.157901763916016,
"learning_rate": 3.5413589364844908e-06,
"loss": 0.19511226415634156,
"step": 960
},
{
"epoch": 0.7240487624676764,
"grad_norm": 7.630816459655762,
"learning_rate": 3.6152141802067945e-06,
"loss": 0.19391764402389527,
"step": 980
},
{
"epoch": 0.7388252678241596,
"grad_norm": 13.34969425201416,
"learning_rate": 3.689069423929099e-06,
"loss": 0.20496578216552735,
"step": 1000
},
{
"epoch": 0.7536017731806428,
"grad_norm": 5.1071882247924805,
"learning_rate": 3.7629246676514037e-06,
"loss": 0.1636316657066345,
"step": 1020
},
{
"epoch": 0.7683782785371259,
"grad_norm": 11.474555015563965,
"learning_rate": 3.836779911373708e-06,
"loss": 0.23842833042144776,
"step": 1040
},
{
"epoch": 0.7831547838936092,
"grad_norm": 3.2344448566436768,
"learning_rate": 3.910635155096012e-06,
"loss": 0.2313016414642334,
"step": 1060
},
{
"epoch": 0.7979312892500924,
"grad_norm": 22.325469970703125,
"learning_rate": 3.984490398818317e-06,
"loss": 0.15265929698944092,
"step": 1080
},
{
"epoch": 0.8127077946065755,
"grad_norm": 9.243146896362305,
"learning_rate": 4.058345642540621e-06,
"loss": 0.208359694480896,
"step": 1100
},
{
"epoch": 0.8274842999630587,
"grad_norm": 14.041821479797363,
"learning_rate": 4.132200886262925e-06,
"loss": 0.15783677101135254,
"step": 1120
},
{
"epoch": 0.842260805319542,
"grad_norm": 2.4594452381134033,
"learning_rate": 4.20605612998523e-06,
"loss": 0.18288125991821289,
"step": 1140
},
{
"epoch": 0.8570373106760251,
"grad_norm": 7.3095173835754395,
"learning_rate": 4.279911373707533e-06,
"loss": 0.16955589056015014,
"step": 1160
},
{
"epoch": 0.8718138160325083,
"grad_norm": 7.790829181671143,
"learning_rate": 4.353766617429838e-06,
"loss": 0.2293524980545044,
"step": 1180
},
{
"epoch": 0.8865903213889915,
"grad_norm": 4.43232536315918,
"learning_rate": 4.427621861152142e-06,
"loss": 0.1554766058921814,
"step": 1200
},
{
"epoch": 0.9013668267454747,
"grad_norm": 1.7960660457611084,
"learning_rate": 4.501477104874446e-06,
"loss": 0.20159010887145995,
"step": 1220
},
{
"epoch": 0.9161433321019579,
"grad_norm": 3.6872801780700684,
"learning_rate": 4.575332348596751e-06,
"loss": 0.17704389095306397,
"step": 1240
},
{
"epoch": 0.9309198374584411,
"grad_norm": 4.9652628898620605,
"learning_rate": 4.649187592319055e-06,
"loss": 0.3138521432876587,
"step": 1260
},
{
"epoch": 0.9456963428149243,
"grad_norm": 6.686302661895752,
"learning_rate": 4.723042836041359e-06,
"loss": 0.186820387840271,
"step": 1280
},
{
"epoch": 0.9604728481714074,
"grad_norm": 5.3840861320495605,
"learning_rate": 4.796898079763664e-06,
"loss": 0.2030576229095459,
"step": 1300
},
{
"epoch": 0.9752493535278907,
"grad_norm": 4.923296928405762,
"learning_rate": 4.870753323485968e-06,
"loss": 0.20385916233062745,
"step": 1320
},
{
"epoch": 0.9900258588843739,
"grad_norm": 3.530714511871338,
"learning_rate": 4.944608567208272e-06,
"loss": 0.14498186111450195,
"step": 1340
},
{
"epoch": 1.0,
"eval_f1": 0.009949110869689519,
"eval_f1_author": 0.5121951219512195,
"eval_f1_chapter": 0.1423948220064725,
"eval_f1_quote": 0.0,
"eval_f1_sabche": 0.0,
"eval_f1_tsawa": 0.0,
"eval_f1_yigchung": 0.0,
"eval_loss": 0.06369028240442276,
"eval_precision": 0.008021390374331552,
"eval_recall": 0.013096492548547342,
"eval_runtime": 164.2027,
"eval_samples_per_second": 8.623,
"eval_soft_f1_tol0": 0.009949110869689519,
"eval_soft_f1_tol1": 0.01360855394819601,
"eval_soft_precision_tol0": 0.008021390374331552,
"eval_soft_precision_tol1": 0.0109717868338558,
"eval_soft_recall_tol0": 0.013096492548547342,
"eval_soft_recall_tol1": 0.01791359325605901,
"eval_steps_per_second": 4.312,
"step": 1354
},
{
"epoch": 1.004432951606945,
"grad_norm": 22.993642807006836,
"learning_rate": 5.018463810930576e-06,
"loss": 0.24112749099731445,
"step": 1360
},
{
"epoch": 1.0192094569634282,
"grad_norm": 4.486099720001221,
"learning_rate": 5.092319054652881e-06,
"loss": 0.15621832609176636,
"step": 1380
},
{
"epoch": 1.0339859623199112,
"grad_norm": 3.427312135696411,
"learning_rate": 5.166174298375185e-06,
"loss": 0.17396997213363646,
"step": 1400
},
{
"epoch": 1.0487624676763945,
"grad_norm": 2.6286463737487793,
"learning_rate": 5.240029542097489e-06,
"loss": 0.1869495153427124,
"step": 1420
},
{
"epoch": 1.0635389730328777,
"grad_norm": 1.9385275840759277,
"learning_rate": 5.313884785819794e-06,
"loss": 0.17648940086364745,
"step": 1440
},
{
"epoch": 1.078315478389361,
"grad_norm": 4.6867170333862305,
"learning_rate": 5.387740029542098e-06,
"loss": 0.16221047639846803,
"step": 1460
},
{
"epoch": 1.0930919837458442,
"grad_norm": 3.5766005516052246,
"learning_rate": 5.461595273264402e-06,
"loss": 0.23842155933380127,
"step": 1480
},
{
"epoch": 1.1078684891023274,
"grad_norm": 4.315107345581055,
"learning_rate": 5.535450516986706e-06,
"loss": 0.22699246406555176,
"step": 1500
},
{
"epoch": 1.1226449944588106,
"grad_norm": 10.020737648010254,
"learning_rate": 5.609305760709011e-06,
"loss": 0.1604781150817871,
"step": 1520
},
{
"epoch": 1.1374214998152936,
"grad_norm": 3.6754698753356934,
"learning_rate": 5.683161004431315e-06,
"loss": 0.1675458073616028,
"step": 1540
},
{
"epoch": 1.1521980051717768,
"grad_norm": 5.651054382324219,
"learning_rate": 5.757016248153619e-06,
"loss": 0.22861068248748778,
"step": 1560
},
{
"epoch": 1.16697451052826,
"grad_norm": 3.7823054790496826,
"learning_rate": 5.830871491875923e-06,
"loss": 0.1893235921859741,
"step": 1580
},
{
"epoch": 1.1817510158847433,
"grad_norm": 14.77681827545166,
"learning_rate": 5.9047267355982285e-06,
"loss": 0.21120743751525878,
"step": 1600
},
{
"epoch": 1.1965275212412265,
"grad_norm": 2.803490161895752,
"learning_rate": 5.978581979320532e-06,
"loss": 0.16600286960601807,
"step": 1620
},
{
"epoch": 1.2113040265977095,
"grad_norm": 8.804646492004395,
"learning_rate": 6.052437223042836e-06,
"loss": 0.2870540380477905,
"step": 1640
},
{
"epoch": 1.2260805319541928,
"grad_norm": 2.9540953636169434,
"learning_rate": 6.1262924667651415e-06,
"loss": 0.26361379623413084,
"step": 1660
},
{
"epoch": 1.240857037310676,
"grad_norm": 0.9787257313728333,
"learning_rate": 6.200147710487445e-06,
"loss": 0.14785664081573485,
"step": 1680
},
{
"epoch": 1.2556335426671592,
"grad_norm": 2.158139705657959,
"learning_rate": 6.274002954209749e-06,
"loss": 0.1276564598083496,
"step": 1700
},
{
"epoch": 1.2704100480236424,
"grad_norm": 3.3782198429107666,
"learning_rate": 6.347858197932054e-06,
"loss": 0.16768869161605834,
"step": 1720
},
{
"epoch": 1.2851865533801257,
"grad_norm": 10.091465950012207,
"learning_rate": 6.421713441654358e-06,
"loss": 0.14950265884399414,
"step": 1740
},
{
"epoch": 1.299963058736609,
"grad_norm": 0.8304731249809265,
"learning_rate": 6.495568685376662e-06,
"loss": 0.12830007076263428,
"step": 1760
},
{
"epoch": 1.3147395640930921,
"grad_norm": 1.4774373769760132,
"learning_rate": 6.569423929098967e-06,
"loss": 0.19609222412109376,
"step": 1780
},
{
"epoch": 1.3295160694495751,
"grad_norm": 5.649841785430908,
"learning_rate": 6.643279172821271e-06,
"loss": 0.18831112384796142,
"step": 1800
},
{
"epoch": 1.3442925748060583,
"grad_norm": 2.347738027572632,
"learning_rate": 6.717134416543575e-06,
"loss": 0.1261088252067566,
"step": 1820
},
{
"epoch": 1.3590690801625416,
"grad_norm": 1.7928117513656616,
"learning_rate": 6.7909896602658795e-06,
"loss": 0.21077876091003417,
"step": 1840
},
{
"epoch": 1.3738455855190248,
"grad_norm": 1.0126829147338867,
"learning_rate": 6.864844903988184e-06,
"loss": 0.19636497497558594,
"step": 1860
},
{
"epoch": 1.3886220908755078,
"grad_norm": 2.74788236618042,
"learning_rate": 6.938700147710488e-06,
"loss": 0.274681544303894,
"step": 1880
},
{
"epoch": 1.403398596231991,
"grad_norm": 25.7138671875,
"learning_rate": 7.012555391432792e-06,
"loss": 0.1625685453414917,
"step": 1900
},
{
"epoch": 1.4181751015884743,
"grad_norm": 15.7152099609375,
"learning_rate": 7.086410635155096e-06,
"loss": 0.15979108810424805,
"step": 1920
},
{
"epoch": 1.4329516069449575,
"grad_norm": 3.495296001434326,
"learning_rate": 7.160265878877401e-06,
"loss": 0.18342748880386353,
"step": 1940
},
{
"epoch": 1.4477281123014407,
"grad_norm": 8.088497161865234,
"learning_rate": 7.234121122599705e-06,
"loss": 0.1316815972328186,
"step": 1960
},
{
"epoch": 1.462504617657924,
"grad_norm": 8.329476356506348,
"learning_rate": 7.307976366322009e-06,
"loss": 0.15820931196212767,
"step": 1980
},
{
"epoch": 1.4772811230144072,
"grad_norm": 2.184511661529541,
"learning_rate": 7.381831610044313e-06,
"loss": 0.13878380060195922,
"step": 2000
},
{
"epoch": 1.4920576283708904,
"grad_norm": 1.5241365432739258,
"learning_rate": 7.455686853766618e-06,
"loss": 0.13428878784179688,
"step": 2020
},
{
"epoch": 1.5068341337273736,
"grad_norm": 1.7516717910766602,
"learning_rate": 7.529542097488922e-06,
"loss": 0.27027249336242676,
"step": 2040
},
{
"epoch": 1.5216106390838566,
"grad_norm": 4.67120885848999,
"learning_rate": 7.603397341211226e-06,
"loss": 0.13954565525054932,
"step": 2060
},
{
"epoch": 1.5363871444403399,
"grad_norm": 1.9583845138549805,
"learning_rate": 7.67725258493353e-06,
"loss": 0.10507760047912598,
"step": 2080
},
{
"epoch": 1.551163649796823,
"grad_norm": 11.665268898010254,
"learning_rate": 7.751107828655836e-06,
"loss": 0.2288591146469116,
"step": 2100
},
{
"epoch": 1.565940155153306,
"grad_norm": 1.4983267784118652,
"learning_rate": 7.82496307237814e-06,
"loss": 0.24975781440734862,
"step": 2120
},
{
"epoch": 1.5807166605097893,
"grad_norm": 2.566443920135498,
"learning_rate": 7.898818316100443e-06,
"loss": 0.14886268377304077,
"step": 2140
},
{
"epoch": 1.5954931658662725,
"grad_norm": 1.01904296875,
"learning_rate": 7.972673559822747e-06,
"loss": 0.18681776523590088,
"step": 2160
},
{
"epoch": 1.6102696712227558,
"grad_norm": 28.88139533996582,
"learning_rate": 8.046528803545053e-06,
"loss": 0.2081953763961792,
"step": 2180
},
{
"epoch": 1.625046176579239,
"grad_norm": 1.6941733360290527,
"learning_rate": 8.120384047267356e-06,
"loss": 0.16717640161514283,
"step": 2200
},
{
"epoch": 1.6398226819357222,
"grad_norm": 1.5981415510177612,
"learning_rate": 8.19423929098966e-06,
"loss": 0.17540180683135986,
"step": 2220
},
{
"epoch": 1.6545991872922055,
"grad_norm": 3.086256504058838,
"learning_rate": 8.268094534711965e-06,
"loss": 0.13089959621429442,
"step": 2240
},
{
"epoch": 1.6693756926486887,
"grad_norm": 0.6488693952560425,
"learning_rate": 8.34194977843427e-06,
"loss": 0.13536157608032226,
"step": 2260
},
{
"epoch": 1.684152198005172,
"grad_norm": 6.18025541305542,
"learning_rate": 8.415805022156573e-06,
"loss": 0.1749156594276428,
"step": 2280
},
{
"epoch": 1.6989287033616551,
"grad_norm": 5.755612373352051,
"learning_rate": 8.489660265878878e-06,
"loss": 0.14930845499038697,
"step": 2300
},
{
"epoch": 1.7137052087181381,
"grad_norm": 6.043393135070801,
"learning_rate": 8.563515509601182e-06,
"loss": 0.12663286924362183,
"step": 2320
},
{
"epoch": 1.7284817140746214,
"grad_norm": 16.692073822021484,
"learning_rate": 8.637370753323486e-06,
"loss": 0.11381006240844727,
"step": 2340
},
{
"epoch": 1.7432582194311046,
"grad_norm": 1.3630712032318115,
"learning_rate": 8.711225997045791e-06,
"loss": 0.15171061754226683,
"step": 2360
},
{
"epoch": 1.7580347247875876,
"grad_norm": 2.843424081802368,
"learning_rate": 8.785081240768095e-06,
"loss": 0.16213523149490355,
"step": 2380
},
{
"epoch": 1.7728112301440708,
"grad_norm": 2.321843385696411,
"learning_rate": 8.858936484490399e-06,
"loss": 0.14741232395172119,
"step": 2400
},
{
"epoch": 1.787587735500554,
"grad_norm": 1.8364756107330322,
"learning_rate": 8.932791728212704e-06,
"loss": 0.16911053657531738,
"step": 2420
},
{
"epoch": 1.8023642408570373,
"grad_norm": 3.014976739883423,
"learning_rate": 9.006646971935008e-06,
"loss": 0.19249134063720702,
"step": 2440
},
{
"epoch": 1.8171407462135205,
"grad_norm": 3.4525327682495117,
"learning_rate": 9.080502215657312e-06,
"loss": 0.11934747695922851,
"step": 2460
},
{
"epoch": 1.8319172515700037,
"grad_norm": 3.275035858154297,
"learning_rate": 9.154357459379617e-06,
"loss": 0.13772256374359132,
"step": 2480
},
{
"epoch": 1.846693756926487,
"grad_norm": 2.3896384239196777,
"learning_rate": 9.228212703101921e-06,
"loss": 0.19579302072525023,
"step": 2500
},
{
"epoch": 1.8614702622829702,
"grad_norm": 4.905596733093262,
"learning_rate": 9.302067946824225e-06,
"loss": 0.1773526430130005,
"step": 2520
},
{
"epoch": 1.8762467676394534,
"grad_norm": 2.4194257259368896,
"learning_rate": 9.37592319054653e-06,
"loss": 0.14882658720016478,
"step": 2540
},
{
"epoch": 1.8910232729959364,
"grad_norm": 9.767522811889648,
"learning_rate": 9.449778434268834e-06,
"loss": 0.15800939798355101,
"step": 2560
},
{
"epoch": 1.9057997783524196,
"grad_norm": 2.7122888565063477,
"learning_rate": 9.52363367799114e-06,
"loss": 0.16415667533874512,
"step": 2580
},
{
"epoch": 1.9205762837089029,
"grad_norm": 23.18901824951172,
"learning_rate": 9.597488921713443e-06,
"loss": 0.22136979103088378,
"step": 2600
},
{
"epoch": 1.9353527890653859,
"grad_norm": 2.244004964828491,
"learning_rate": 9.671344165435747e-06,
"loss": 0.14884871244430542,
"step": 2620
},
{
"epoch": 1.950129294421869,
"grad_norm": 0.982561469078064,
"learning_rate": 9.745199409158052e-06,
"loss": 0.1401953101158142,
"step": 2640
},
{
"epoch": 1.9649057997783523,
"grad_norm": 2.9314169883728027,
"learning_rate": 9.819054652880356e-06,
"loss": 0.13230215311050414,
"step": 2660
},
{
"epoch": 1.9796823051348356,
"grad_norm": 2.732909917831421,
"learning_rate": 9.89290989660266e-06,
"loss": 0.158538293838501,
"step": 2680
},
{
"epoch": 1.9944588104913188,
"grad_norm": 3.2355642318725586,
"learning_rate": 9.966765140324964e-06,
"loss": 0.22675518989562987,
"step": 2700
},
{
"epoch": 2.0,
"eval_f1": 0.013625434143734972,
"eval_f1_author": 0.5154639175257731,
"eval_f1_chapter": 0.337984496124031,
"eval_f1_quote": 0.0,
"eval_f1_sabche": 0.0032967032967032967,
"eval_f1_tsawa": 0.0007150518412584913,
"eval_f1_yigchung": 0.004184100418410042,
"eval_loss": 0.07157671451568604,
"eval_precision": 0.009674359785014228,
"eval_recall": 0.023031762757790154,
"eval_runtime": 164.3103,
"eval_samples_per_second": 8.618,
"eval_soft_f1_tol0": 0.013625434143734972,
"eval_soft_f1_tol1": 0.02324338765695966,
"eval_soft_precision_tol0": 0.009674359785014228,
"eval_soft_precision_tol1": 0.016503319633259565,
"eval_soft_recall_tol0": 0.023031762757790154,
"eval_soft_recall_tol1": 0.03928947764564203,
"eval_steps_per_second": 4.309,
"step": 2708
},
{
"epoch": 2.00886590321389,
"grad_norm": 0.7488579154014587,
"learning_rate": 9.989844903988184e-06,
"loss": 0.17037104368209838,
"step": 2720
},
{
"epoch": 2.0236424085703733,
"grad_norm": 3.121425151824951,
"learning_rate": 9.971381093057608e-06,
"loss": 0.13356295824050904,
"step": 2740
},
{
"epoch": 2.0384189139268565,
"grad_norm": 10.25585651397705,
"learning_rate": 9.952917282127031e-06,
"loss": 0.14996374845504762,
"step": 2760
},
{
"epoch": 2.0531954192833397,
"grad_norm": 2.897705078125,
"learning_rate": 9.934453471196456e-06,
"loss": 0.13153868913650513,
"step": 2780
},
{
"epoch": 2.0679719246398225,
"grad_norm": 1.3952618837356567,
"learning_rate": 9.91598966026588e-06,
"loss": 0.11466294527053833,
"step": 2800
},
{
"epoch": 2.0827484299963057,
"grad_norm": 1.9680219888687134,
"learning_rate": 9.897525849335303e-06,
"loss": 0.10174458026885987,
"step": 2820
},
{
"epoch": 2.097524935352789,
"grad_norm": 3.1025257110595703,
"learning_rate": 9.879062038404727e-06,
"loss": 0.12117102146148681,
"step": 2840
},
{
"epoch": 2.112301440709272,
"grad_norm": 3.454657554626465,
"learning_rate": 9.860598227474152e-06,
"loss": 0.14881492853164674,
"step": 2860
},
{
"epoch": 2.1270779460657554,
"grad_norm": 1.3067108392715454,
"learning_rate": 9.842134416543575e-06,
"loss": 0.09414324760437012,
"step": 2880
},
{
"epoch": 2.1418544514222386,
"grad_norm": 22.44338035583496,
"learning_rate": 9.823670605612999e-06,
"loss": 0.15983881950378417,
"step": 2900
},
{
"epoch": 2.156630956778722,
"grad_norm": 1.897062063217163,
"learning_rate": 9.805206794682424e-06,
"loss": 0.2480917453765869,
"step": 2920
},
{
"epoch": 2.171407462135205,
"grad_norm": 1.1563146114349365,
"learning_rate": 9.786742983751846e-06,
"loss": 0.1365828275680542,
"step": 2940
},
{
"epoch": 2.1861839674916883,
"grad_norm": 2.501188278198242,
"learning_rate": 9.76827917282127e-06,
"loss": 0.13099013566970824,
"step": 2960
},
{
"epoch": 2.2009604728481715,
"grad_norm": 0.732958197593689,
"learning_rate": 9.749815361890695e-06,
"loss": 0.09902547597885132,
"step": 2980
},
{
"epoch": 2.2157369782046548,
"grad_norm": 2.27915358543396,
"learning_rate": 9.731351550960118e-06,
"loss": 0.13958550691604615,
"step": 3000
},
{
"epoch": 2.230513483561138,
"grad_norm": 2.758756160736084,
"learning_rate": 9.712887740029543e-06,
"loss": 0.1868541955947876,
"step": 3020
},
{
"epoch": 2.245289988917621,
"grad_norm": 8.475456237792969,
"learning_rate": 9.694423929098967e-06,
"loss": 0.11908481121063233,
"step": 3040
},
{
"epoch": 2.260066494274104,
"grad_norm": 2.9064548015594482,
"learning_rate": 9.67596011816839e-06,
"loss": 0.18359187841415406,
"step": 3060
},
{
"epoch": 2.2748429996305872,
"grad_norm": 2.3748366832733154,
"learning_rate": 9.657496307237814e-06,
"loss": 0.21851837635040283,
"step": 3080
},
{
"epoch": 2.2896195049870705,
"grad_norm": 1.0969339609146118,
"learning_rate": 9.639032496307239e-06,
"loss": 0.18293980360031128,
"step": 3100
},
{
"epoch": 2.3043960103435537,
"grad_norm": 0.8778420090675354,
"learning_rate": 9.620568685376662e-06,
"loss": 0.17181634902954102,
"step": 3120
},
{
"epoch": 2.319172515700037,
"grad_norm": 4.310705184936523,
"learning_rate": 9.602104874446086e-06,
"loss": 0.12769193649291993,
"step": 3140
},
{
"epoch": 2.33394902105652,
"grad_norm": 2.7653613090515137,
"learning_rate": 9.58364106351551e-06,
"loss": 0.2905233383178711,
"step": 3160
},
{
"epoch": 2.3487255264130034,
"grad_norm": 5.924228191375732,
"learning_rate": 9.565177252584933e-06,
"loss": 0.11291065216064453,
"step": 3180
},
{
"epoch": 2.3635020317694866,
"grad_norm": 1.3305809497833252,
"learning_rate": 9.546713441654358e-06,
"loss": 0.22106215953826905,
"step": 3200
},
{
"epoch": 2.37827853712597,
"grad_norm": 5.5327372550964355,
"learning_rate": 9.528249630723782e-06,
"loss": 0.19483805894851686,
"step": 3220
},
{
"epoch": 2.393055042482453,
"grad_norm": 2.095848798751831,
"learning_rate": 9.509785819793205e-06,
"loss": 0.1981823682785034,
"step": 3240
},
{
"epoch": 2.4078315478389363,
"grad_norm": 0.7926581501960754,
"learning_rate": 9.49132200886263e-06,
"loss": 0.13002758026123046,
"step": 3260
},
{
"epoch": 2.422608053195419,
"grad_norm": 2.6668643951416016,
"learning_rate": 9.472858197932054e-06,
"loss": 0.11931681632995605,
"step": 3280
},
{
"epoch": 2.4373845585519023,
"grad_norm": 7.154099464416504,
"learning_rate": 9.454394387001477e-06,
"loss": 0.15694849491119384,
"step": 3300
},
{
"epoch": 2.4521610639083855,
"grad_norm": 2.389171600341797,
"learning_rate": 9.435930576070901e-06,
"loss": 0.13917235136032105,
"step": 3320
},
{
"epoch": 2.4669375692648687,
"grad_norm": 1.6435991525650024,
"learning_rate": 9.417466765140326e-06,
"loss": 0.13349064588546752,
"step": 3340
},
{
"epoch": 2.481714074621352,
"grad_norm": 2.9867262840270996,
"learning_rate": 9.399002954209749e-06,
"loss": 0.08199175596237182,
"step": 3360
},
{
"epoch": 2.496490579977835,
"grad_norm": 1.4562466144561768,
"learning_rate": 9.380539143279173e-06,
"loss": 0.17275774478912354,
"step": 3380
},
{
"epoch": 2.5112670853343184,
"grad_norm": 1.253039836883545,
"learning_rate": 9.362075332348598e-06,
"loss": 0.12911561727523804,
"step": 3400
},
{
"epoch": 2.5260435906908016,
"grad_norm": 6.884113788604736,
"learning_rate": 9.34361152141802e-06,
"loss": 0.134329092502594,
"step": 3420
},
{
"epoch": 2.540820096047285,
"grad_norm": 2.045487403869629,
"learning_rate": 9.325147710487445e-06,
"loss": 0.1398937702178955,
"step": 3440
},
{
"epoch": 2.555596601403768,
"grad_norm": 2.4884042739868164,
"learning_rate": 9.30668389955687e-06,
"loss": 0.18259624242782593,
"step": 3460
},
{
"epoch": 2.5703731067602513,
"grad_norm": 11.555817604064941,
"learning_rate": 9.288220088626292e-06,
"loss": 0.1363913059234619,
"step": 3480
},
{
"epoch": 2.5851496121167346,
"grad_norm": 6.275540351867676,
"learning_rate": 9.269756277695717e-06,
"loss": 0.12403000593185425,
"step": 3500
},
{
"epoch": 2.599926117473218,
"grad_norm": 1.1736960411071777,
"learning_rate": 9.251292466765141e-06,
"loss": 0.1681079864501953,
"step": 3520
},
{
"epoch": 2.614702622829701,
"grad_norm": 1.200361728668213,
"learning_rate": 9.232828655834564e-06,
"loss": 0.20239112377166749,
"step": 3540
},
{
"epoch": 2.6294791281861842,
"grad_norm": 5.843613624572754,
"learning_rate": 9.214364844903988e-06,
"loss": 0.09815734624862671,
"step": 3560
},
{
"epoch": 2.644255633542667,
"grad_norm": 12.455564498901367,
"learning_rate": 9.195901033973413e-06,
"loss": 0.1492748498916626,
"step": 3580
},
{
"epoch": 2.6590321388991502,
"grad_norm": 3.805860996246338,
"learning_rate": 9.177437223042836e-06,
"loss": 0.10711218118667602,
"step": 3600
},
{
"epoch": 2.6738086442556335,
"grad_norm": 1.4953904151916504,
"learning_rate": 9.15897341211226e-06,
"loss": 0.09400691390037537,
"step": 3620
},
{
"epoch": 2.6885851496121167,
"grad_norm": 6.474602699279785,
"learning_rate": 9.140509601181685e-06,
"loss": 0.133670175075531,
"step": 3640
},
{
"epoch": 2.7033616549686,
"grad_norm": 7.189492702484131,
"learning_rate": 9.122045790251108e-06,
"loss": 0.13258401155471802,
"step": 3660
},
{
"epoch": 2.718138160325083,
"grad_norm": 8.304774284362793,
"learning_rate": 9.103581979320532e-06,
"loss": 0.1859143614768982,
"step": 3680
},
{
"epoch": 2.7329146656815664,
"grad_norm": 2.485971212387085,
"learning_rate": 9.085118168389956e-06,
"loss": 0.18038097620010377,
"step": 3700
},
{
"epoch": 2.7476911710380496,
"grad_norm": 1.9786618947982788,
"learning_rate": 9.066654357459381e-06,
"loss": 0.10348873138427735,
"step": 3720
},
{
"epoch": 2.762467676394533,
"grad_norm": 1.285863995552063,
"learning_rate": 9.048190546528804e-06,
"loss": 0.08862318992614746,
"step": 3740
},
{
"epoch": 2.7772441817510156,
"grad_norm": 1.6725132465362549,
"learning_rate": 9.029726735598228e-06,
"loss": 0.09215317368507385,
"step": 3760
},
{
"epoch": 2.792020687107499,
"grad_norm": 1.084094524383545,
"learning_rate": 9.011262924667653e-06,
"loss": 0.14049065113067627,
"step": 3780
},
{
"epoch": 2.806797192463982,
"grad_norm": 0.41341111063957214,
"learning_rate": 8.992799113737076e-06,
"loss": 0.10442180633544922,
"step": 3800
},
{
"epoch": 2.8215736978204653,
"grad_norm": 20.94047737121582,
"learning_rate": 8.9743353028065e-06,
"loss": 0.2757225513458252,
"step": 3820
},
{
"epoch": 2.8363502031769485,
"grad_norm": 0.6462209820747375,
"learning_rate": 8.955871491875925e-06,
"loss": 0.08133713006973267,
"step": 3840
},
{
"epoch": 2.8511267085334318,
"grad_norm": 1.7239296436309814,
"learning_rate": 8.937407680945347e-06,
"loss": 0.13443011045455933,
"step": 3860
},
{
"epoch": 2.865903213889915,
"grad_norm": 0.952746570110321,
"learning_rate": 8.918943870014772e-06,
"loss": 0.16512211561203002,
"step": 3880
},
{
"epoch": 2.880679719246398,
"grad_norm": 2.0119361877441406,
"learning_rate": 8.900480059084196e-06,
"loss": 0.14362579584121704,
"step": 3900
},
{
"epoch": 2.8954562246028814,
"grad_norm": 0.6607625484466553,
"learning_rate": 8.882016248153619e-06,
"loss": 0.11665700674057007,
"step": 3920
},
{
"epoch": 2.9102327299593647,
"grad_norm": 1.506514549255371,
"learning_rate": 8.863552437223044e-06,
"loss": 0.15756337642669677,
"step": 3940
},
{
"epoch": 2.925009235315848,
"grad_norm": 8.464256286621094,
"learning_rate": 8.845088626292468e-06,
"loss": 0.16639748811721802,
"step": 3960
},
{
"epoch": 2.939785740672331,
"grad_norm": 2.5918128490448,
"learning_rate": 8.82662481536189e-06,
"loss": 0.12925074100494385,
"step": 3980
},
{
"epoch": 2.9545622460288143,
"grad_norm": 5.9357218742370605,
"learning_rate": 8.808161004431315e-06,
"loss": 0.17214598655700683,
"step": 4000
},
{
"epoch": 2.9693387513852976,
"grad_norm": 4.953963279724121,
"learning_rate": 8.78969719350074e-06,
"loss": 0.16206299066543578,
"step": 4020
},
{
"epoch": 2.984115256741781,
"grad_norm": 1.3762701749801636,
"learning_rate": 8.771233382570163e-06,
"loss": 0.12783533334732056,
"step": 4040
},
{
"epoch": 2.998891762098264,
"grad_norm": 1.2369712591171265,
"learning_rate": 8.752769571639587e-06,
"loss": 0.14763396978378296,
"step": 4060
},
{
"epoch": 3.0,
"eval_f1": 0.029633535460058,
"eval_f1_author": 0.888888888888889,
"eval_f1_chapter": 0.674757281553398,
"eval_f1_quote": 0.0,
"eval_f1_sabche": 0.028981581798483206,
"eval_f1_tsawa": 0.002870264064293915,
"eval_f1_yigchung": 0.005260850504164839,
"eval_loss": 0.07181419432163239,
"eval_precision": 0.022804739490342476,
"eval_recall": 0.04230016558783682,
"eval_runtime": 164.6639,
"eval_samples_per_second": 8.599,
"eval_soft_f1_tol0": 0.029633535460058,
"eval_soft_f1_tol1": 0.055892433430002636,
"eval_soft_precision_tol0": 0.022804739490342476,
"eval_soft_precision_tol1": 0.043012497971108586,
"eval_soft_recall_tol0": 0.04230016558783682,
"eval_soft_recall_tol1": 0.07978323046816198,
"eval_steps_per_second": 4.3,
"step": 4062
},
{
"epoch": 3.013298854820835,
"grad_norm": 0.6305031180381775,
"learning_rate": 8.734305760709012e-06,
"loss": 0.1073186993598938,
"step": 4080
},
{
"epoch": 3.028075360177318,
"grad_norm": 1.3140232563018799,
"learning_rate": 8.715841949778436e-06,
"loss": 0.09768721461296082,
"step": 4100
},
{
"epoch": 3.0428518655338013,
"grad_norm": 2.1695148944854736,
"learning_rate": 8.697378138847859e-06,
"loss": 0.09707651138305665,
"step": 4120
},
{
"epoch": 3.0576283708902845,
"grad_norm": 0.9397019743919373,
"learning_rate": 8.678914327917283e-06,
"loss": 0.10999850034713746,
"step": 4140
},
{
"epoch": 3.0724048762467677,
"grad_norm": 0.7979065179824829,
"learning_rate": 8.660450516986708e-06,
"loss": 0.19756799936294556,
"step": 4160
},
{
"epoch": 3.087181381603251,
"grad_norm": 1.9831281900405884,
"learning_rate": 8.64198670605613e-06,
"loss": 0.134338641166687,
"step": 4180
},
{
"epoch": 3.101957886959734,
"grad_norm": 1.703490138053894,
"learning_rate": 8.623522895125555e-06,
"loss": 0.10789951086044311,
"step": 4200
},
{
"epoch": 3.1167343923162174,
"grad_norm": 3.2855417728424072,
"learning_rate": 8.60505908419498e-06,
"loss": 0.08941381573677062,
"step": 4220
},
{
"epoch": 3.1315108976727,
"grad_norm": 2.0211169719696045,
"learning_rate": 8.586595273264402e-06,
"loss": 0.13170883655548096,
"step": 4240
},
{
"epoch": 3.1462874030291834,
"grad_norm": 1.729666829109192,
"learning_rate": 8.568131462333827e-06,
"loss": 0.0766973614692688,
"step": 4260
},
{
"epoch": 3.1610639083856666,
"grad_norm": 9.713820457458496,
"learning_rate": 8.549667651403251e-06,
"loss": 0.10216113328933715,
"step": 4280
},
{
"epoch": 3.17584041374215,
"grad_norm": 2.2032101154327393,
"learning_rate": 8.531203840472674e-06,
"loss": 0.12167798280715943,
"step": 4300
},
{
"epoch": 3.190616919098633,
"grad_norm": 1.2277432680130005,
"learning_rate": 8.512740029542099e-06,
"loss": 0.10992389917373657,
"step": 4320
},
{
"epoch": 3.2053934244551163,
"grad_norm": 1.0262017250061035,
"learning_rate": 8.494276218611523e-06,
"loss": 0.10613970756530762,
"step": 4340
},
{
"epoch": 3.2201699298115996,
"grad_norm": 1.11785089969635,
"learning_rate": 8.475812407680946e-06,
"loss": 0.10162975788116455,
"step": 4360
},
{
"epoch": 3.234946435168083,
"grad_norm": 3.5607283115386963,
"learning_rate": 8.45734859675037e-06,
"loss": 0.14789507389068604,
"step": 4380
},
{
"epoch": 3.249722940524566,
"grad_norm": 1.9668165445327759,
"learning_rate": 8.438884785819795e-06,
"loss": 0.16140552759170532,
"step": 4400
},
{
"epoch": 3.2644994458810492,
"grad_norm": 1.740909218788147,
"learning_rate": 8.420420974889218e-06,
"loss": 0.18682413101196288,
"step": 4420
},
{
"epoch": 3.2792759512375325,
"grad_norm": 2.2434346675872803,
"learning_rate": 8.401957163958642e-06,
"loss": 0.10888447761535644,
"step": 4440
},
{
"epoch": 3.2940524565940157,
"grad_norm": 1.9172331094741821,
"learning_rate": 8.383493353028067e-06,
"loss": 0.10014368295669555,
"step": 4460
},
{
"epoch": 3.308828961950499,
"grad_norm": 1.8549606800079346,
"learning_rate": 8.36502954209749e-06,
"loss": 0.1427286148071289,
"step": 4480
},
{
"epoch": 3.323605467306982,
"grad_norm": 4.047844886779785,
"learning_rate": 8.346565731166914e-06,
"loss": 0.10859538316726684,
"step": 4500
},
{
"epoch": 3.338381972663465,
"grad_norm": 1.578848958015442,
"learning_rate": 8.328101920236338e-06,
"loss": 0.09976358413696289,
"step": 4520
},
{
"epoch": 3.353158478019948,
"grad_norm": 5.167227745056152,
"learning_rate": 8.309638109305761e-06,
"loss": 0.10787239074707031,
"step": 4540
},
{
"epoch": 3.3679349833764314,
"grad_norm": 0.9531060457229614,
"learning_rate": 8.291174298375186e-06,
"loss": 0.11763765811920165,
"step": 4560
},
{
"epoch": 3.3827114887329146,
"grad_norm": 2.150413751602173,
"learning_rate": 8.27271048744461e-06,
"loss": 0.12325513362884521,
"step": 4580
},
{
"epoch": 3.397487994089398,
"grad_norm": 12.400345802307129,
"learning_rate": 8.254246676514033e-06,
"loss": 0.15270819664001464,
"step": 4600
},
{
"epoch": 3.412264499445881,
"grad_norm": 4.488905906677246,
"learning_rate": 8.235782865583457e-06,
"loss": 0.09554807543754577,
"step": 4620
},
{
"epoch": 3.4270410048023643,
"grad_norm": 2.558509588241577,
"learning_rate": 8.217319054652882e-06,
"loss": 0.12064318656921387,
"step": 4640
},
{
"epoch": 3.4418175101588475,
"grad_norm": 2.08709979057312,
"learning_rate": 8.198855243722305e-06,
"loss": 0.15861705541610718,
"step": 4660
},
{
"epoch": 3.4565940155153307,
"grad_norm": 1.7005308866500854,
"learning_rate": 8.18039143279173e-06,
"loss": 0.1255167841911316,
"step": 4680
},
{
"epoch": 3.471370520871814,
"grad_norm": 7.888983726501465,
"learning_rate": 8.161927621861154e-06,
"loss": 0.11569286584854126,
"step": 4700
},
{
"epoch": 3.486147026228297,
"grad_norm": 1.8542848825454712,
"learning_rate": 8.143463810930576e-06,
"loss": 0.1580866813659668,
"step": 4720
},
{
"epoch": 3.50092353158478,
"grad_norm": 0.7920698523521423,
"learning_rate": 8.125000000000001e-06,
"loss": 0.1474738359451294,
"step": 4740
},
{
"epoch": 3.515700036941263,
"grad_norm": 1.21330726146698,
"learning_rate": 8.106536189069425e-06,
"loss": 0.11481826305389405,
"step": 4760
},
{
"epoch": 3.5304765422977464,
"grad_norm": 1.0535153150558472,
"learning_rate": 8.088072378138848e-06,
"loss": 0.095521080493927,
"step": 4780
},
{
"epoch": 3.5452530476542297,
"grad_norm": 1.4608540534973145,
"learning_rate": 8.069608567208273e-06,
"loss": 0.254551100730896,
"step": 4800
},
{
"epoch": 3.560029553010713,
"grad_norm": 0.3008294701576233,
"learning_rate": 8.051144756277697e-06,
"loss": 0.1144513487815857,
"step": 4820
},
{
"epoch": 3.574806058367196,
"grad_norm": 1.6606552600860596,
"learning_rate": 8.03268094534712e-06,
"loss": 0.09389815926551819,
"step": 4840
},
{
"epoch": 3.5895825637236793,
"grad_norm": 1.3775110244750977,
"learning_rate": 8.014217134416545e-06,
"loss": 0.11952614784240723,
"step": 4860
},
{
"epoch": 3.6043590690801626,
"grad_norm": 1.700050711631775,
"learning_rate": 7.995753323485969e-06,
"loss": 0.14653095006942748,
"step": 4880
},
{
"epoch": 3.619135574436646,
"grad_norm": 0.46003827452659607,
"learning_rate": 7.977289512555392e-06,
"loss": 0.08345560431480407,
"step": 4900
},
{
"epoch": 3.633912079793129,
"grad_norm": 5.208398342132568,
"learning_rate": 7.958825701624816e-06,
"loss": 0.11663490533828735,
"step": 4920
},
{
"epoch": 3.6486885851496123,
"grad_norm": 0.8145765662193298,
"learning_rate": 7.94036189069424e-06,
"loss": 0.12496718168258666,
"step": 4940
},
{
"epoch": 3.6634650905060955,
"grad_norm": 13.380167961120605,
"learning_rate": 7.921898079763664e-06,
"loss": 0.1970830202102661,
"step": 4960
},
{
"epoch": 3.6782415958625787,
"grad_norm": 2.564222812652588,
"learning_rate": 7.903434268833088e-06,
"loss": 0.12315770387649536,
"step": 4980
},
{
"epoch": 3.693018101219062,
"grad_norm": 1.4905750751495361,
"learning_rate": 7.884970457902513e-06,
"loss": 0.08848263025283813,
"step": 5000
},
{
"epoch": 3.707794606575545,
"grad_norm": 1.9406968355178833,
"learning_rate": 7.866506646971935e-06,
"loss": 0.100133216381073,
"step": 5020
},
{
"epoch": 3.722571111932028,
"grad_norm": 3.955491304397583,
"learning_rate": 7.84804283604136e-06,
"loss": 0.174168598651886,
"step": 5040
},
{
"epoch": 3.737347617288511,
"grad_norm": 1.5576092004776,
"learning_rate": 7.829579025110784e-06,
"loss": 0.10718483924865722,
"step": 5060
},
{
"epoch": 3.7521241226449944,
"grad_norm": 1.526227355003357,
"learning_rate": 7.811115214180207e-06,
"loss": 0.1036676049232483,
"step": 5080
},
{
"epoch": 3.7669006280014776,
"grad_norm": 0.6412363648414612,
"learning_rate": 7.792651403249632e-06,
"loss": 0.11313272714614868,
"step": 5100
},
{
"epoch": 3.781677133357961,
"grad_norm": 5.545438766479492,
"learning_rate": 7.774187592319056e-06,
"loss": 0.1373060941696167,
"step": 5120
},
{
"epoch": 3.796453638714444,
"grad_norm": 1.2549275159835815,
"learning_rate": 7.755723781388479e-06,
"loss": 0.15525555610656738,
"step": 5140
},
{
"epoch": 3.8112301440709273,
"grad_norm": 0.48289623856544495,
"learning_rate": 7.737259970457903e-06,
"loss": 0.17651475667953492,
"step": 5160
},
{
"epoch": 3.8260066494274105,
"grad_norm": 1.1303938627243042,
"learning_rate": 7.718796159527328e-06,
"loss": 0.11483552455902099,
"step": 5180
},
{
"epoch": 3.8407831547838938,
"grad_norm": 11.766563415527344,
"learning_rate": 7.70033234859675e-06,
"loss": 0.1212962508201599,
"step": 5200
},
{
"epoch": 3.8555596601403765,
"grad_norm": 2.0833210945129395,
"learning_rate": 7.681868537666175e-06,
"loss": 0.1305975317955017,
"step": 5220
},
{
"epoch": 3.8703361654968598,
"grad_norm": 4.1130218505859375,
"learning_rate": 7.6634047267356e-06,
"loss": 0.08251273036003112,
"step": 5240
},
{
"epoch": 3.885112670853343,
"grad_norm": 0.5774154663085938,
"learning_rate": 7.644940915805022e-06,
"loss": 0.07953848242759705,
"step": 5260
},
{
"epoch": 3.8998891762098262,
"grad_norm": 1.2997376918792725,
"learning_rate": 7.626477104874447e-06,
"loss": 0.15589237213134766,
"step": 5280
},
{
"epoch": 3.9146656815663095,
"grad_norm": 1.507757544517517,
"learning_rate": 7.608013293943871e-06,
"loss": 0.13908222913742066,
"step": 5300
},
{
"epoch": 3.9294421869227927,
"grad_norm": 6.963959693908691,
"learning_rate": 7.589549483013294e-06,
"loss": 0.11550743579864502,
"step": 5320
},
{
"epoch": 3.944218692279276,
"grad_norm": 1.6579861640930176,
"learning_rate": 7.571085672082719e-06,
"loss": 0.11281369924545288,
"step": 5340
},
{
"epoch": 3.958995197635759,
"grad_norm": 2.205768585205078,
"learning_rate": 7.552621861152143e-06,
"loss": 0.1273674726486206,
"step": 5360
},
{
"epoch": 3.9737717029922424,
"grad_norm": 2.665320873260498,
"learning_rate": 7.534158050221566e-06,
"loss": 0.12502450942993165,
"step": 5380
},
{
"epoch": 3.9885482083487256,
"grad_norm": 1.5980299711227417,
"learning_rate": 7.51569423929099e-06,
"loss": 0.09247097373008728,
"step": 5400
},
{
"epoch": 4.0,
"eval_f1": 0.039779361436566414,
"eval_f1_author": 0.9259259259259259,
"eval_f1_chapter": 0.6498855835240275,
"eval_f1_quote": 0.009715475364330326,
"eval_f1_sabche": 0.05898690649385003,
"eval_f1_tsawa": 0.020779220779220776,
"eval_f1_yigchung": 0.011371712864250176,
"eval_loss": 0.09073026478290558,
"eval_precision": 0.02715180828844674,
"eval_recall": 0.07436399217221135,
"eval_runtime": 164.6726,
"eval_samples_per_second": 8.599,
"eval_soft_f1_tol0": 0.039779361436566414,
"eval_soft_f1_tol1": 0.05371019044167975,
"eval_soft_precision_tol0": 0.02715180828844674,
"eval_soft_precision_tol1": 0.0366604375068704,
"eval_soft_recall_tol0": 0.07436399217221135,
"eval_soft_recall_tol1": 0.1004064428721963,
"eval_steps_per_second": 4.299,
"step": 5416
},
{
"epoch": 4.002955301071297,
"grad_norm": 2.9630157947540283,
"learning_rate": 7.497230428360415e-06,
"loss": 0.11431716680526734,
"step": 5420
},
{
"epoch": 4.01773180642778,
"grad_norm": 0.46785759925842285,
"learning_rate": 7.478766617429838e-06,
"loss": 0.08863309025764465,
"step": 5440
},
{
"epoch": 4.032508311784263,
"grad_norm": 7.329707145690918,
"learning_rate": 7.460302806499262e-06,
"loss": 0.10789968967437744,
"step": 5460
},
{
"epoch": 4.0472848171407465,
"grad_norm": 5.6308488845825195,
"learning_rate": 7.441838995568687e-06,
"loss": 0.10790928602218627,
"step": 5480
},
{
"epoch": 4.06206132249723,
"grad_norm": 1.398536205291748,
"learning_rate": 7.4233751846381094e-06,
"loss": 0.1399625301361084,
"step": 5500
},
{
"epoch": 4.076837827853713,
"grad_norm": 1.297676920890808,
"learning_rate": 7.404911373707534e-06,
"loss": 0.08576329350471497,
"step": 5520
},
{
"epoch": 4.091614333210196,
"grad_norm": 6.379153728485107,
"learning_rate": 7.386447562776958e-06,
"loss": 0.10660150051116943,
"step": 5540
},
{
"epoch": 4.106390838566679,
"grad_norm": 1.7524080276489258,
"learning_rate": 7.367983751846381e-06,
"loss": 0.1278483271598816,
"step": 5560
},
{
"epoch": 4.121167343923162,
"grad_norm": 1.3190034627914429,
"learning_rate": 7.349519940915806e-06,
"loss": 0.09753898978233337,
"step": 5580
},
{
"epoch": 4.135943849279645,
"grad_norm": 1.9287397861480713,
"learning_rate": 7.33105612998523e-06,
"loss": 0.07210677862167358,
"step": 5600
},
{
"epoch": 4.150720354636128,
"grad_norm": 3.451411485671997,
"learning_rate": 7.312592319054653e-06,
"loss": 0.1124524474143982,
"step": 5620
},
{
"epoch": 4.165496859992611,
"grad_norm": 15.183464050292969,
"learning_rate": 7.2941285081240775e-06,
"loss": 0.11533975601196289,
"step": 5640
},
{
"epoch": 4.180273365349095,
"grad_norm": 0.7561500668525696,
"learning_rate": 7.275664697193502e-06,
"loss": 0.10243216753005982,
"step": 5660
},
{
"epoch": 4.195049870705578,
"grad_norm": 1.1861071586608887,
"learning_rate": 7.257200886262925e-06,
"loss": 0.1663222312927246,
"step": 5680
},
{
"epoch": 4.209826376062061,
"grad_norm": 3.785529375076294,
"learning_rate": 7.238737075332349e-06,
"loss": 0.08857283592224122,
"step": 5700
},
{
"epoch": 4.224602881418544,
"grad_norm": 0.39788898825645447,
"learning_rate": 7.220273264401773e-06,
"loss": 0.10370031595230103,
"step": 5720
},
{
"epoch": 4.239379386775028,
"grad_norm": 0.4169798493385315,
"learning_rate": 7.2018094534711965e-06,
"loss": 0.13269611597061157,
"step": 5740
},
{
"epoch": 4.254155892131511,
"grad_norm": 1.4433329105377197,
"learning_rate": 7.183345642540621e-06,
"loss": 0.15055701732635499,
"step": 5760
},
{
"epoch": 4.268932397487994,
"grad_norm": 0.8108705282211304,
"learning_rate": 7.164881831610045e-06,
"loss": 0.10328505039215088,
"step": 5780
},
{
"epoch": 4.283708902844477,
"grad_norm": 4.685944557189941,
"learning_rate": 7.146418020679468e-06,
"loss": 0.09680783748626709,
"step": 5800
},
{
"epoch": 4.2984854082009605,
"grad_norm": 1.9428914785385132,
"learning_rate": 7.127954209748893e-06,
"loss": 0.15268460512161255,
"step": 5820
},
{
"epoch": 4.313261913557444,
"grad_norm": 2.181502103805542,
"learning_rate": 7.109490398818316e-06,
"loss": 0.12270368337631225,
"step": 5840
},
{
"epoch": 4.328038418913927,
"grad_norm": 1.7029106616973877,
"learning_rate": 7.091026587887741e-06,
"loss": 0.06979374885559082,
"step": 5860
},
{
"epoch": 4.34281492427041,
"grad_norm": 1.2654433250427246,
"learning_rate": 7.0725627769571645e-06,
"loss": 0.0858349323272705,
"step": 5880
},
{
"epoch": 4.357591429626893,
"grad_norm": 3.6451213359832764,
"learning_rate": 7.054098966026588e-06,
"loss": 0.06293165683746338,
"step": 5900
},
{
"epoch": 4.372367934983377,
"grad_norm": 1.0352520942687988,
"learning_rate": 7.035635155096013e-06,
"loss": 0.10849316120147705,
"step": 5920
},
{
"epoch": 4.38714444033986,
"grad_norm": 1.2292581796646118,
"learning_rate": 7.017171344165436e-06,
"loss": 0.10018128156661987,
"step": 5940
},
{
"epoch": 4.401920945696343,
"grad_norm": 1.4362941980361938,
"learning_rate": 6.99870753323486e-06,
"loss": 0.11148455142974853,
"step": 5960
},
{
"epoch": 4.416697451052826,
"grad_norm": 1.1057559251785278,
"learning_rate": 6.980243722304284e-06,
"loss": 0.11582520008087158,
"step": 5980
},
{
"epoch": 4.4314739564093095,
"grad_norm": 0.5521154999732971,
"learning_rate": 6.961779911373708e-06,
"loss": 0.11034280061721802,
"step": 6000
},
{
"epoch": 4.446250461765793,
"grad_norm": 3.496638298034668,
"learning_rate": 6.943316100443132e-06,
"loss": 0.11924157142639161,
"step": 6020
},
{
"epoch": 4.461026967122276,
"grad_norm": 1.4034616947174072,
"learning_rate": 6.924852289512556e-06,
"loss": 0.10902374982833862,
"step": 6040
},
{
"epoch": 4.475803472478759,
"grad_norm": 2.7527520656585693,
"learning_rate": 6.90638847858198e-06,
"loss": 0.13944618701934813,
"step": 6060
},
{
"epoch": 4.490579977835242,
"grad_norm": 1.5506138801574707,
"learning_rate": 6.8879246676514034e-06,
"loss": 0.09381868839263915,
"step": 6080
},
{
"epoch": 4.505356483191725,
"grad_norm": 1.1348156929016113,
"learning_rate": 6.869460856720828e-06,
"loss": 0.08152715563774109,
"step": 6100
},
{
"epoch": 4.520132988548208,
"grad_norm": 0.597363293170929,
"learning_rate": 6.8509970457902516e-06,
"loss": 0.08730922937393189,
"step": 6120
},
{
"epoch": 4.534909493904691,
"grad_norm": 3.6667511463165283,
"learning_rate": 6.832533234859675e-06,
"loss": 0.10671879053115844,
"step": 6140
},
{
"epoch": 4.5496859992611745,
"grad_norm": 5.5172929763793945,
"learning_rate": 6.8140694239291e-06,
"loss": 0.10335360765457154,
"step": 6160
},
{
"epoch": 4.564462504617658,
"grad_norm": 1.7363708019256592,
"learning_rate": 6.795605612998523e-06,
"loss": 0.10552057027816772,
"step": 6180
},
{
"epoch": 4.579239009974141,
"grad_norm": 5.793086528778076,
"learning_rate": 6.777141802067947e-06,
"loss": 0.10906326770782471,
"step": 6200
},
{
"epoch": 4.594015515330624,
"grad_norm": 1.9142320156097412,
"learning_rate": 6.7586779911373715e-06,
"loss": 0.13999695777893068,
"step": 6220
},
{
"epoch": 4.608792020687107,
"grad_norm": 2.449648141860962,
"learning_rate": 6.740214180206795e-06,
"loss": 0.13046315908432007,
"step": 6240
},
{
"epoch": 4.623568526043591,
"grad_norm": 2.355130910873413,
"learning_rate": 6.721750369276219e-06,
"loss": 0.1251004934310913,
"step": 6260
},
{
"epoch": 4.638345031400074,
"grad_norm": 2.4113264083862305,
"learning_rate": 6.703286558345643e-06,
"loss": 0.09771038293838501,
"step": 6280
},
{
"epoch": 4.653121536756557,
"grad_norm": 1.411844253540039,
"learning_rate": 6.684822747415068e-06,
"loss": 0.1343335270881653,
"step": 6300
},
{
"epoch": 4.66789804211304,
"grad_norm": 11.726256370544434,
"learning_rate": 6.6663589364844905e-06,
"loss": 0.0975439727306366,
"step": 6320
},
{
"epoch": 4.6826745474695235,
"grad_norm": 1.5821865797042847,
"learning_rate": 6.647895125553915e-06,
"loss": 0.07771993279457093,
"step": 6340
},
{
"epoch": 4.697451052826007,
"grad_norm": 0.5408990383148193,
"learning_rate": 6.6294313146233395e-06,
"loss": 0.164067542552948,
"step": 6360
},
{
"epoch": 4.71222755818249,
"grad_norm": 2.295057535171509,
"learning_rate": 6.610967503692762e-06,
"loss": 0.11107258796691895,
"step": 6380
},
{
"epoch": 4.727004063538973,
"grad_norm": 1.214127779006958,
"learning_rate": 6.592503692762187e-06,
"loss": 0.12151973247528076,
"step": 6400
},
{
"epoch": 4.741780568895456,
"grad_norm": 2.180757999420166,
"learning_rate": 6.574039881831611e-06,
"loss": 0.10375571250915527,
"step": 6420
},
{
"epoch": 4.75655707425194,
"grad_norm": 0.531566321849823,
"learning_rate": 6.555576070901034e-06,
"loss": 0.08612127900123596,
"step": 6440
},
{
"epoch": 4.771333579608423,
"grad_norm": 3.769385814666748,
"learning_rate": 6.5371122599704585e-06,
"loss": 0.12149454355239868,
"step": 6460
},
{
"epoch": 4.786110084964906,
"grad_norm": 0.27902674674987793,
"learning_rate": 6.518648449039883e-06,
"loss": 0.07460282444953918,
"step": 6480
},
{
"epoch": 4.800886590321389,
"grad_norm": 15.586052894592285,
"learning_rate": 6.500184638109306e-06,
"loss": 0.13748433589935302,
"step": 6500
},
{
"epoch": 4.8156630956778725,
"grad_norm": 0.934836208820343,
"learning_rate": 6.48172082717873e-06,
"loss": 0.14621957540512084,
"step": 6520
},
{
"epoch": 4.830439601034355,
"grad_norm": 0.968586266040802,
"learning_rate": 6.463257016248155e-06,
"loss": 0.09820839166641235,
"step": 6540
},
{
"epoch": 4.845216106390838,
"grad_norm": 4.744210243225098,
"learning_rate": 6.4447932053175776e-06,
"loss": 0.09205281734466553,
"step": 6560
},
{
"epoch": 4.859992611747321,
"grad_norm": 1.620653748512268,
"learning_rate": 6.426329394387002e-06,
"loss": 0.07514939308166504,
"step": 6580
},
{
"epoch": 4.874769117103805,
"grad_norm": 2.3648438453674316,
"learning_rate": 6.4078655834564265e-06,
"loss": 0.10629445314407349,
"step": 6600
},
{
"epoch": 4.889545622460288,
"grad_norm": 6.438984394073486,
"learning_rate": 6.389401772525849e-06,
"loss": 0.0764173448085785,
"step": 6620
},
{
"epoch": 4.904322127816771,
"grad_norm": 1.7192474603652954,
"learning_rate": 6.370937961595274e-06,
"loss": 0.0950875997543335,
"step": 6640
},
{
"epoch": 4.919098633173254,
"grad_norm": 10.558757781982422,
"learning_rate": 6.352474150664698e-06,
"loss": 0.10921791791915894,
"step": 6660
},
{
"epoch": 4.9338751385297375,
"grad_norm": 2.2420549392700195,
"learning_rate": 6.334010339734121e-06,
"loss": 0.10243178606033325,
"step": 6680
},
{
"epoch": 4.948651643886221,
"grad_norm": 3.40336012840271,
"learning_rate": 6.3155465288035456e-06,
"loss": 0.07892192006111146,
"step": 6700
},
{
"epoch": 4.963428149242704,
"grad_norm": 1.6610172986984253,
"learning_rate": 6.29708271787297e-06,
"loss": 0.09818499684333801,
"step": 6720
},
{
"epoch": 4.978204654599187,
"grad_norm": 4.773355960845947,
"learning_rate": 6.278618906942393e-06,
"loss": 0.11357412338256836,
"step": 6740
},
{
"epoch": 4.99298115995567,
"grad_norm": 0.8417530655860901,
"learning_rate": 6.260155096011817e-06,
"loss": 0.10627554655075074,
"step": 6760
},
{
"epoch": 5.0,
"eval_f1": 0.04659303049159925,
"eval_f1_author": 0.43243243243243235,
"eval_f1_chapter": 0.6038543897216274,
"eval_f1_quote": 0.014361224693328015,
"eval_f1_sabche": 0.07387317577166473,
"eval_f1_tsawa": 0.030442135781589753,
"eval_f1_yigchung": 0.00806201550387597,
"eval_loss": 0.09770610183477402,
"eval_precision": 0.031412239760868425,
"eval_recall": 0.090170103868734,
"eval_runtime": 164.6317,
"eval_samples_per_second": 8.601,
"eval_soft_f1_tol0": 0.04659303049159925,
"eval_soft_f1_tol1": 0.061838830118232734,
"eval_soft_precision_tol0": 0.031412239760868425,
"eval_soft_precision_tol1": 0.041690702186795325,
"eval_soft_recall_tol0": 0.090170103868734,
"eval_soft_recall_tol1": 0.11967484570224296,
"eval_steps_per_second": 4.301,
"step": 6770
},
{
"epoch": 5.007388252678242,
"grad_norm": 3.236814498901367,
"learning_rate": 6.241691285081242e-06,
"loss": 0.07577576637268066,
"step": 6780
},
{
"epoch": 5.022164758034725,
"grad_norm": 1.0791494846343994,
"learning_rate": 6.223227474150665e-06,
"loss": 0.08623950481414795,
"step": 6800
},
{
"epoch": 5.036941263391208,
"grad_norm": 1.114840030670166,
"learning_rate": 6.204763663220089e-06,
"loss": 0.08475393652915955,
"step": 6820
},
{
"epoch": 5.051717768747691,
"grad_norm": 2.4118924140930176,
"learning_rate": 6.186299852289514e-06,
"loss": 0.09248427748680114,
"step": 6840
},
{
"epoch": 5.0664942741041745,
"grad_norm": 0.8156068325042725,
"learning_rate": 6.167836041358936e-06,
"loss": 0.10605623722076415,
"step": 6860
},
{
"epoch": 5.081270779460658,
"grad_norm": 1.6148840188980103,
"learning_rate": 6.149372230428361e-06,
"loss": 0.09941831827163697,
"step": 6880
},
{
"epoch": 5.096047284817141,
"grad_norm": 0.7418000102043152,
"learning_rate": 6.130908419497785e-06,
"loss": 0.11596554517745972,
"step": 6900
},
{
"epoch": 5.110823790173624,
"grad_norm": 0.12603075802326202,
"learning_rate": 6.112444608567208e-06,
"loss": 0.08732989430427551,
"step": 6920
},
{
"epoch": 5.125600295530107,
"grad_norm": 1.6711703538894653,
"learning_rate": 6.093980797636633e-06,
"loss": 0.08074650764465333,
"step": 6940
},
{
"epoch": 5.140376800886591,
"grad_norm": 0.7734578847885132,
"learning_rate": 6.075516986706057e-06,
"loss": 0.13434559106826782,
"step": 6960
},
{
"epoch": 5.155153306243074,
"grad_norm": 1.5082166194915771,
"learning_rate": 6.05705317577548e-06,
"loss": 0.1005518078804016,
"step": 6980
},
{
"epoch": 5.169929811599557,
"grad_norm": 1.3656419515609741,
"learning_rate": 6.038589364844904e-06,
"loss": 0.10323455333709716,
"step": 7000
},
{
"epoch": 5.18470631695604,
"grad_norm": 1.3703151941299438,
"learning_rate": 6.020125553914329e-06,
"loss": 0.10618985891342163,
"step": 7020
},
{
"epoch": 5.199482822312523,
"grad_norm": 1.234379529953003,
"learning_rate": 6.001661742983752e-06,
"loss": 0.07805829644203185,
"step": 7040
},
{
"epoch": 5.214259327669006,
"grad_norm": 2.1165268421173096,
"learning_rate": 5.983197932053176e-06,
"loss": 0.08039488196372986,
"step": 7060
},
{
"epoch": 5.229035833025489,
"grad_norm": 1.6822233200073242,
"learning_rate": 5.964734121122601e-06,
"loss": 0.049975207448005675,
"step": 7080
},
{
"epoch": 5.243812338381972,
"grad_norm": 1.404208779335022,
"learning_rate": 5.9462703101920234e-06,
"loss": 0.06693402528762818,
"step": 7100
},
{
"epoch": 5.258588843738456,
"grad_norm": 1.9500081539154053,
"learning_rate": 5.927806499261448e-06,
"loss": 0.10228079557418823,
"step": 7120
},
{
"epoch": 5.273365349094939,
"grad_norm": 1.7617027759552002,
"learning_rate": 5.909342688330872e-06,
"loss": 0.1681894540786743,
"step": 7140
},
{
"epoch": 5.288141854451422,
"grad_norm": 0.44583550095558167,
"learning_rate": 5.890878877400295e-06,
"loss": 0.10674363374710083,
"step": 7160
},
{
"epoch": 5.302918359807905,
"grad_norm": 4.596474647521973,
"learning_rate": 5.87241506646972e-06,
"loss": 0.08000558614730835,
"step": 7180
},
{
"epoch": 5.3176948651643885,
"grad_norm": 0.9269393682479858,
"learning_rate": 5.853951255539144e-06,
"loss": 0.10894120931625366,
"step": 7200
},
{
"epoch": 5.332471370520872,
"grad_norm": 9.17103385925293,
"learning_rate": 5.835487444608568e-06,
"loss": 0.08934349417686463,
"step": 7220
},
{
"epoch": 5.347247875877355,
"grad_norm": 1.095739722251892,
"learning_rate": 5.8170236336779915e-06,
"loss": 0.10206352472305298,
"step": 7240
},
{
"epoch": 5.362024381233838,
"grad_norm": 5.57783317565918,
"learning_rate": 5.798559822747416e-06,
"loss": 0.08475146889686584,
"step": 7260
},
{
"epoch": 5.376800886590321,
"grad_norm": 7.2847418785095215,
"learning_rate": 5.78009601181684e-06,
"loss": 0.07707643508911133,
"step": 7280
},
{
"epoch": 5.391577391946805,
"grad_norm": 1.0415109395980835,
"learning_rate": 5.761632200886263e-06,
"loss": 0.0841111421585083,
"step": 7300
},
{
"epoch": 5.406353897303288,
"grad_norm": 0.524057924747467,
"learning_rate": 5.743168389955688e-06,
"loss": 0.07095835208892823,
"step": 7320
},
{
"epoch": 5.421130402659771,
"grad_norm": 1.6371711492538452,
"learning_rate": 5.724704579025111e-06,
"loss": 0.11882846355438233,
"step": 7340
},
{
"epoch": 5.435906908016254,
"grad_norm": 4.54400110244751,
"learning_rate": 5.706240768094535e-06,
"loss": 0.07246030569076538,
"step": 7360
},
{
"epoch": 5.4506834133727375,
"grad_norm": 4.792078018188477,
"learning_rate": 5.6877769571639595e-06,
"loss": 0.0953561544418335,
"step": 7380
},
{
"epoch": 5.465459918729221,
"grad_norm": 0.9032992124557495,
"learning_rate": 5.669313146233383e-06,
"loss": 0.10105686187744141,
"step": 7400
},
{
"epoch": 5.480236424085704,
"grad_norm": 1.3699769973754883,
"learning_rate": 5.650849335302807e-06,
"loss": 0.0782034695148468,
"step": 7420
},
{
"epoch": 5.495012929442187,
"grad_norm": 2.4443414211273193,
"learning_rate": 5.632385524372231e-06,
"loss": 0.08563000559806824,
"step": 7440
},
{
"epoch": 5.5097894347986704,
"grad_norm": 8.921721458435059,
"learning_rate": 5.613921713441655e-06,
"loss": 0.13999418020248414,
"step": 7460
},
{
"epoch": 5.524565940155154,
"grad_norm": 5.58736515045166,
"learning_rate": 5.5954579025110785e-06,
"loss": 0.058961677551269534,
"step": 7480
},
{
"epoch": 5.539342445511636,
"grad_norm": 2.391704559326172,
"learning_rate": 5.576994091580503e-06,
"loss": 0.09335577487945557,
"step": 7500
},
{
"epoch": 5.554118950868119,
"grad_norm": 1.5417615175247192,
"learning_rate": 5.558530280649927e-06,
"loss": 0.06352685689926148,
"step": 7520
},
{
"epoch": 5.5688954562246025,
"grad_norm": 1.3531591892242432,
"learning_rate": 5.54006646971935e-06,
"loss": 0.13267632722854614,
"step": 7540
},
{
"epoch": 5.583671961581086,
"grad_norm": 1.7334518432617188,
"learning_rate": 5.521602658788775e-06,
"loss": 0.07966671586036682,
"step": 7560
},
{
"epoch": 5.598448466937569,
"grad_norm": 2.0580809116363525,
"learning_rate": 5.503138847858198e-06,
"loss": 0.11016982793807983,
"step": 7580
},
{
"epoch": 5.613224972294052,
"grad_norm": 0.6512215733528137,
"learning_rate": 5.484675036927623e-06,
"loss": 0.09333600401878357,
"step": 7600
},
{
"epoch": 5.628001477650535,
"grad_norm": 3.10050892829895,
"learning_rate": 5.4662112259970465e-06,
"loss": 0.08624144196510315,
"step": 7620
},
{
"epoch": 5.642777983007019,
"grad_norm": 2.6260881423950195,
"learning_rate": 5.44774741506647e-06,
"loss": 0.10535945892333984,
"step": 7640
},
{
"epoch": 5.657554488363502,
"grad_norm": 2.299725294113159,
"learning_rate": 5.429283604135895e-06,
"loss": 0.08017481565475464,
"step": 7660
},
{
"epoch": 5.672330993719985,
"grad_norm": 0.5010847449302673,
"learning_rate": 5.4108197932053174e-06,
"loss": 0.08154807090759278,
"step": 7680
},
{
"epoch": 5.687107499076468,
"grad_norm": 13.15144157409668,
"learning_rate": 5.392355982274742e-06,
"loss": 0.09692487716674805,
"step": 7700
},
{
"epoch": 5.7018840044329515,
"grad_norm": 3.256175994873047,
"learning_rate": 5.373892171344166e-06,
"loss": 0.05518702268600464,
"step": 7720
},
{
"epoch": 5.716660509789435,
"grad_norm": 2.2086923122406006,
"learning_rate": 5.355428360413589e-06,
"loss": 0.06719712615013122,
"step": 7740
},
{
"epoch": 5.731437015145918,
"grad_norm": 0.9702446460723877,
"learning_rate": 5.336964549483014e-06,
"loss": 0.10411953926086426,
"step": 7760
},
{
"epoch": 5.746213520502401,
"grad_norm": 0.532471239566803,
"learning_rate": 5.318500738552438e-06,
"loss": 0.10964715480804443,
"step": 7780
},
{
"epoch": 5.760990025858884,
"grad_norm": 1.3106942176818848,
"learning_rate": 5.300036927621861e-06,
"loss": 0.10351897478103637,
"step": 7800
},
{
"epoch": 5.775766531215368,
"grad_norm": 0.3648535907268524,
"learning_rate": 5.2815731166912855e-06,
"loss": 0.08998883366584778,
"step": 7820
},
{
"epoch": 5.790543036571851,
"grad_norm": 1.4343498945236206,
"learning_rate": 5.26310930576071e-06,
"loss": 0.04865207970142364,
"step": 7840
},
{
"epoch": 5.805319541928334,
"grad_norm": 4.40683126449585,
"learning_rate": 5.244645494830133e-06,
"loss": 0.0694089949131012,
"step": 7860
},
{
"epoch": 5.820096047284817,
"grad_norm": 6.955454349517822,
"learning_rate": 5.226181683899557e-06,
"loss": 0.06251799464225768,
"step": 7880
},
{
"epoch": 5.834872552641301,
"grad_norm": 0.4440311789512634,
"learning_rate": 5.207717872968982e-06,
"loss": 0.08427314758300782,
"step": 7900
},
{
"epoch": 5.849649057997784,
"grad_norm": 0.7029963731765747,
"learning_rate": 5.1892540620384045e-06,
"loss": 0.062427854537963866,
"step": 7920
},
{
"epoch": 5.864425563354267,
"grad_norm": 1.3285729885101318,
"learning_rate": 5.170790251107829e-06,
"loss": 0.10214477777481079,
"step": 7940
},
{
"epoch": 5.87920206871075,
"grad_norm": 3.2660179138183594,
"learning_rate": 5.1523264401772535e-06,
"loss": 0.06842342615127564,
"step": 7960
},
{
"epoch": 5.8939785740672335,
"grad_norm": 5.0024261474609375,
"learning_rate": 5.133862629246676e-06,
"loss": 0.12226139307022095,
"step": 7980
},
{
"epoch": 5.908755079423717,
"grad_norm": 2.479198932647705,
"learning_rate": 5.115398818316101e-06,
"loss": 0.08909531831741332,
"step": 8000
},
{
"epoch": 5.9235315847802,
"grad_norm": 1.43873929977417,
"learning_rate": 5.096935007385525e-06,
"loss": 0.10576851367950439,
"step": 8020
},
{
"epoch": 5.938308090136683,
"grad_norm": 39.283939361572266,
"learning_rate": 5.078471196454948e-06,
"loss": 0.09854817986488343,
"step": 8040
},
{
"epoch": 5.9530845954931655,
"grad_norm": 13.951441764831543,
"learning_rate": 5.0600073855243725e-06,
"loss": 0.08711436986923218,
"step": 8060
},
{
"epoch": 5.967861100849649,
"grad_norm": 2.365631580352783,
"learning_rate": 5.041543574593797e-06,
"loss": 0.112136709690094,
"step": 8080
},
{
"epoch": 5.982637606206132,
"grad_norm": 6.945087909698486,
"learning_rate": 5.02307976366322e-06,
"loss": 0.106019127368927,
"step": 8100
},
{
"epoch": 5.997414111562615,
"grad_norm": 2.7114408016204834,
"learning_rate": 5.004615952732644e-06,
"loss": 0.11385865211486816,
"step": 8120
},
{
"epoch": 6.0,
"eval_f1": 0.06835117773019272,
"eval_f1_author": 0.8275862068965517,
"eval_f1_chapter": 0.6409090909090909,
"eval_f1_quote": 0.013410356921807302,
"eval_f1_sabche": 0.15945257797581158,
"eval_f1_tsawa": 0.021653133458255258,
"eval_f1_yigchung": 0.014485755673587638,
"eval_loss": 0.10273216664791107,
"eval_precision": 0.04776441012749147,
"eval_recall": 0.12012644889357219,
"eval_runtime": 165.5234,
"eval_samples_per_second": 8.555,
"eval_soft_f1_tol0": 0.06835117773019272,
"eval_soft_f1_tol1": 0.08231263383297645,
"eval_soft_precision_tol0": 0.04776441012749147,
"eval_soft_precision_tol1": 0.057520799664811155,
"eval_soft_recall_tol0": 0.12012644889357219,
"eval_soft_recall_tol1": 0.14466355562245972,
"eval_steps_per_second": 4.277,
"step": 8124
},
{
"epoch": 6.011821204285186,
"grad_norm": 0.33957645297050476,
"learning_rate": 4.986152141802068e-06,
"loss": 0.055154663324356076,
"step": 8140
},
{
"epoch": 6.02659770964167,
"grad_norm": 0.9566740989685059,
"learning_rate": 4.967688330871492e-06,
"loss": 0.09199487566947936,
"step": 8160
},
{
"epoch": 6.041374214998153,
"grad_norm": 1.062593936920166,
"learning_rate": 4.949224519940916e-06,
"loss": 0.07991627454757691,
"step": 8180
},
{
"epoch": 6.056150720354636,
"grad_norm": 0.7422909140586853,
"learning_rate": 4.93076070901034e-06,
"loss": 0.10874149799346924,
"step": 8200
},
{
"epoch": 6.070927225711119,
"grad_norm": 1.391255497932434,
"learning_rate": 4.912296898079764e-06,
"loss": 0.0733675241470337,
"step": 8220
},
{
"epoch": 6.0857037310676025,
"grad_norm": 2.0628108978271484,
"learning_rate": 4.893833087149188e-06,
"loss": 0.07705639600753784,
"step": 8240
},
{
"epoch": 6.100480236424086,
"grad_norm": 10.096761703491211,
"learning_rate": 4.8753692762186115e-06,
"loss": 0.09721676111221314,
"step": 8260
},
{
"epoch": 6.115256741780569,
"grad_norm": 0.3869010806083679,
"learning_rate": 4.856905465288036e-06,
"loss": 0.07016111016273499,
"step": 8280
},
{
"epoch": 6.130033247137052,
"grad_norm": 0.6973243355751038,
"learning_rate": 4.83844165435746e-06,
"loss": 0.07618046402931214,
"step": 8300
},
{
"epoch": 6.1448097524935354,
"grad_norm": 3.699690341949463,
"learning_rate": 4.819977843426883e-06,
"loss": 0.12102062702178955,
"step": 8320
},
{
"epoch": 6.159586257850019,
"grad_norm": 1.2516862154006958,
"learning_rate": 4.801514032496308e-06,
"loss": 0.0931439995765686,
"step": 8340
},
{
"epoch": 6.174362763206502,
"grad_norm": 0.5968925952911377,
"learning_rate": 4.783050221565731e-06,
"loss": 0.056948763132095334,
"step": 8360
},
{
"epoch": 6.189139268562985,
"grad_norm": 0.3200990557670593,
"learning_rate": 4.764586410635155e-06,
"loss": 0.0628507137298584,
"step": 8380
},
{
"epoch": 6.203915773919468,
"grad_norm": 20.919809341430664,
"learning_rate": 4.7461225997045795e-06,
"loss": 0.06474959850311279,
"step": 8400
},
{
"epoch": 6.218692279275952,
"grad_norm": 3.4046616554260254,
"learning_rate": 4.727658788774003e-06,
"loss": 0.06481179594993591,
"step": 8420
},
{
"epoch": 6.233468784632435,
"grad_norm": 1.7347246408462524,
"learning_rate": 4.709194977843427e-06,
"loss": 0.10528444051742554,
"step": 8440
},
{
"epoch": 6.248245289988918,
"grad_norm": 2.050334930419922,
"learning_rate": 4.690731166912851e-06,
"loss": 0.07203145623207093,
"step": 8460
},
{
"epoch": 6.2630217953454,
"grad_norm": 2.2779390811920166,
"learning_rate": 4.672267355982275e-06,
"loss": 0.054803645610809325,
"step": 8480
},
{
"epoch": 6.277798300701884,
"grad_norm": 2.4324991703033447,
"learning_rate": 4.6538035450516985e-06,
"loss": 0.06333977580070496,
"step": 8500
},
{
"epoch": 6.292574806058367,
"grad_norm": 6.123317718505859,
"learning_rate": 4.635339734121123e-06,
"loss": 0.08894148468971252,
"step": 8520
},
{
"epoch": 6.30735131141485,
"grad_norm": 1.25343656539917,
"learning_rate": 4.616875923190547e-06,
"loss": 0.07934771776199341,
"step": 8540
},
{
"epoch": 6.322127816771333,
"grad_norm": 1.2314735651016235,
"learning_rate": 4.59841211225997e-06,
"loss": 0.10709916353225708,
"step": 8560
},
{
"epoch": 6.3369043221278165,
"grad_norm": 0.7263938784599304,
"learning_rate": 4.579948301329395e-06,
"loss": 0.07681664824485779,
"step": 8580
},
{
"epoch": 6.3516808274843,
"grad_norm": 1.6503888368606567,
"learning_rate": 4.561484490398818e-06,
"loss": 0.05886760950088501,
"step": 8600
},
{
"epoch": 6.366457332840783,
"grad_norm": 1.1397356986999512,
"learning_rate": 4.543020679468242e-06,
"loss": 0.10109728574752808,
"step": 8620
},
{
"epoch": 6.381233838197266,
"grad_norm": 7.9713616371154785,
"learning_rate": 4.5245568685376665e-06,
"loss": 0.09045670032501221,
"step": 8640
},
{
"epoch": 6.396010343553749,
"grad_norm": 1.228232741355896,
"learning_rate": 4.50609305760709e-06,
"loss": 0.07134175300598145,
"step": 8660
},
{
"epoch": 6.410786848910233,
"grad_norm": 0.9247950911521912,
"learning_rate": 4.487629246676514e-06,
"loss": 0.1270041823387146,
"step": 8680
},
{
"epoch": 6.425563354266716,
"grad_norm": 4.016371726989746,
"learning_rate": 4.469165435745938e-06,
"loss": 0.09379560947418213,
"step": 8700
},
{
"epoch": 6.440339859623199,
"grad_norm": 1.6210134029388428,
"learning_rate": 4.450701624815362e-06,
"loss": 0.06940361857414246,
"step": 8720
},
{
"epoch": 6.455116364979682,
"grad_norm": 0.48715081810951233,
"learning_rate": 4.432237813884786e-06,
"loss": 0.07216532230377197,
"step": 8740
},
{
"epoch": 6.469892870336166,
"grad_norm": 0.6929494142532349,
"learning_rate": 4.41377400295421e-06,
"loss": 0.09313917756080628,
"step": 8760
},
{
"epoch": 6.484669375692649,
"grad_norm": 0.48092567920684814,
"learning_rate": 4.395310192023634e-06,
"loss": 0.09580454230308533,
"step": 8780
},
{
"epoch": 6.499445881049132,
"grad_norm": 0.8014270663261414,
"learning_rate": 4.376846381093058e-06,
"loss": 0.07025495171546936,
"step": 8800
},
{
"epoch": 6.514222386405615,
"grad_norm": 1.358403205871582,
"learning_rate": 4.358382570162482e-06,
"loss": 0.06858280301094055,
"step": 8820
},
{
"epoch": 6.5289988917620985,
"grad_norm": 0.38887038826942444,
"learning_rate": 4.3399187592319055e-06,
"loss": 0.07649755477905273,
"step": 8840
},
{
"epoch": 6.543775397118582,
"grad_norm": 1.3405340909957886,
"learning_rate": 4.32145494830133e-06,
"loss": 0.049575993418693544,
"step": 8860
},
{
"epoch": 6.558551902475065,
"grad_norm": 16.84498405456543,
"learning_rate": 4.302991137370754e-06,
"loss": 0.09844129681587219,
"step": 8880
},
{
"epoch": 6.573328407831548,
"grad_norm": 10.134000778198242,
"learning_rate": 4.284527326440178e-06,
"loss": 0.09954258799552917,
"step": 8900
},
{
"epoch": 6.588104913188031,
"grad_norm": 1.415053367614746,
"learning_rate": 4.266063515509602e-06,
"loss": 0.07141712307929993,
"step": 8920
},
{
"epoch": 6.602881418544515,
"grad_norm": 8.267929077148438,
"learning_rate": 4.247599704579025e-06,
"loss": 0.06639363765716552,
"step": 8940
},
{
"epoch": 6.617657923900998,
"grad_norm": 0.6367068886756897,
"learning_rate": 4.22913589364845e-06,
"loss": 0.05888218879699707,
"step": 8960
},
{
"epoch": 6.632434429257481,
"grad_norm": 2.2817111015319824,
"learning_rate": 4.2106720827178735e-06,
"loss": 0.09119194149971008,
"step": 8980
},
{
"epoch": 6.647210934613964,
"grad_norm": 1.2428474426269531,
"learning_rate": 4.192208271787297e-06,
"loss": 0.05470389127731323,
"step": 9000
},
{
"epoch": 6.661987439970447,
"grad_norm": 0.5352773666381836,
"learning_rate": 4.173744460856722e-06,
"loss": 0.07605255246162415,
"step": 9020
},
{
"epoch": 6.67676394532693,
"grad_norm": 3.7526636123657227,
"learning_rate": 4.155280649926145e-06,
"loss": 0.09152576327323914,
"step": 9040
},
{
"epoch": 6.691540450683413,
"grad_norm": 1.0769250392913818,
"learning_rate": 4.136816838995569e-06,
"loss": 0.11174876689910888,
"step": 9060
},
{
"epoch": 6.706316956039896,
"grad_norm": 6.872859477996826,
"learning_rate": 4.118353028064993e-06,
"loss": 0.07698031663894653,
"step": 9080
},
{
"epoch": 6.7210934613963795,
"grad_norm": 1.2562944889068604,
"learning_rate": 4.099889217134417e-06,
"loss": 0.06367176175117492,
"step": 9100
},
{
"epoch": 6.735869966752863,
"grad_norm": 0.6717840433120728,
"learning_rate": 4.081425406203841e-06,
"loss": 0.13568817377090453,
"step": 9120
},
{
"epoch": 6.750646472109346,
"grad_norm": 4.257383346557617,
"learning_rate": 4.062961595273265e-06,
"loss": 0.0583439290523529,
"step": 9140
},
{
"epoch": 6.765422977465829,
"grad_norm": 1.3550347089767456,
"learning_rate": 4.044497784342689e-06,
"loss": 0.04487316012382507,
"step": 9160
},
{
"epoch": 6.780199482822312,
"grad_norm": 0.5879141688346863,
"learning_rate": 4.026033973412112e-06,
"loss": 0.04259286224842072,
"step": 9180
},
{
"epoch": 6.794975988178796,
"grad_norm": 4.346455097198486,
"learning_rate": 4.007570162481537e-06,
"loss": 0.10025652647018432,
"step": 9200
},
{
"epoch": 6.809752493535279,
"grad_norm": 6.066633701324463,
"learning_rate": 3.9891063515509605e-06,
"loss": 0.0661650002002716,
"step": 9220
},
{
"epoch": 6.824528998891762,
"grad_norm": 0.8743476271629333,
"learning_rate": 3.970642540620384e-06,
"loss": 0.0719166338443756,
"step": 9240
},
{
"epoch": 6.839305504248245,
"grad_norm": 1.3412960767745972,
"learning_rate": 3.952178729689809e-06,
"loss": 0.08500291109085083,
"step": 9260
},
{
"epoch": 6.854082009604729,
"grad_norm": 1.5456814765930176,
"learning_rate": 3.933714918759232e-06,
"loss": 0.052108824253082275,
"step": 9280
},
{
"epoch": 6.868858514961212,
"grad_norm": 1.0171066522598267,
"learning_rate": 3.915251107828656e-06,
"loss": 0.09150219559669495,
"step": 9300
},
{
"epoch": 6.883635020317695,
"grad_norm": 5.048430919647217,
"learning_rate": 3.8967872968980804e-06,
"loss": 0.0888733685016632,
"step": 9320
},
{
"epoch": 6.898411525674178,
"grad_norm": 2.7720024585723877,
"learning_rate": 3.878323485967504e-06,
"loss": 0.08731088638305665,
"step": 9340
},
{
"epoch": 6.9131880310306615,
"grad_norm": 2.109351873397827,
"learning_rate": 3.859859675036928e-06,
"loss": 0.09720221757888795,
"step": 9360
},
{
"epoch": 6.927964536387145,
"grad_norm": 2.3287665843963623,
"learning_rate": 3.841395864106352e-06,
"loss": 0.059489428997039795,
"step": 9380
},
{
"epoch": 6.942741041743628,
"grad_norm": 2.034480094909668,
"learning_rate": 3.822932053175776e-06,
"loss": 0.06460795998573303,
"step": 9400
},
{
"epoch": 6.957517547100111,
"grad_norm": 2.556817054748535,
"learning_rate": 3.8044682422451995e-06,
"loss": 0.07196953296661376,
"step": 9420
},
{
"epoch": 6.972294052456594,
"grad_norm": 2.8893795013427734,
"learning_rate": 3.786004431314624e-06,
"loss": 0.0890947163105011,
"step": 9440
},
{
"epoch": 6.987070557813077,
"grad_norm": 1.2682381868362427,
"learning_rate": 3.7675406203840476e-06,
"loss": 0.056380295753479005,
"step": 9460
},
{
"epoch": 7.0,
"eval_f1": 0.0746774788057501,
"eval_f1_author": 1.0,
"eval_f1_chapter": 0.5286506469500925,
"eval_f1_quote": 0.02836991837705048,
"eval_f1_sabche": 0.1967704344930914,
"eval_f1_tsawa": 0.018205892088712348,
"eval_f1_yigchung": 0.021378941742383754,
"eval_loss": 0.15662674605846405,
"eval_precision": 0.04944599014008884,
"eval_recall": 0.15249134427216618,
"eval_runtime": 165.1098,
"eval_samples_per_second": 8.576,
"eval_soft_f1_tol0": 0.0746774788057501,
"eval_soft_f1_tol1": 0.08551419093254699,
"eval_soft_precision_tol0": 0.04944599014008884,
"eval_soft_precision_tol1": 0.05662127202616293,
"eval_soft_recall_tol0": 0.15249134427216618,
"eval_soft_recall_tol1": 0.1746199006472979,
"eval_steps_per_second": 4.288,
"step": 9478
},
{
"epoch": 7.001477650535648,
"grad_norm": 1.2800287008285522,
"learning_rate": 3.7490768094534712e-06,
"loss": 0.05819381475448608,
"step": 9480
},
{
"epoch": 7.016254155892131,
"grad_norm": 0.7783945202827454,
"learning_rate": 3.7306129985228957e-06,
"loss": 0.09244761466979981,
"step": 9500
},
{
"epoch": 7.031030661248614,
"grad_norm": 1.0024983882904053,
"learning_rate": 3.7121491875923194e-06,
"loss": 0.06930415034294128,
"step": 9520
},
{
"epoch": 7.045807166605098,
"grad_norm": 1.8368946313858032,
"learning_rate": 3.693685376661743e-06,
"loss": 0.06354544758796692,
"step": 9540
},
{
"epoch": 7.060583671961581,
"grad_norm": 1.0531907081604004,
"learning_rate": 3.6752215657311675e-06,
"loss": 0.052252662181854245,
"step": 9560
},
{
"epoch": 7.075360177318064,
"grad_norm": 1.5543427467346191,
"learning_rate": 3.656757754800591e-06,
"loss": 0.05461403727531433,
"step": 9580
},
{
"epoch": 7.090136682674547,
"grad_norm": 0.5904586911201477,
"learning_rate": 3.6382939438700148e-06,
"loss": 0.09829541444778442,
"step": 9600
},
{
"epoch": 7.104913188031031,
"grad_norm": 1.911216378211975,
"learning_rate": 3.6198301329394393e-06,
"loss": 0.07265669703483582,
"step": 9620
},
{
"epoch": 7.119689693387514,
"grad_norm": 0.660009503364563,
"learning_rate": 3.601366322008863e-06,
"loss": 0.05682058930397034,
"step": 9640
},
{
"epoch": 7.134466198743997,
"grad_norm": 0.8126732110977173,
"learning_rate": 3.5829025110782865e-06,
"loss": 0.06120790839195252,
"step": 9660
},
{
"epoch": 7.14924270410048,
"grad_norm": 4.380861282348633,
"learning_rate": 3.564438700147711e-06,
"loss": 0.08501878380775452,
"step": 9680
},
{
"epoch": 7.1640192094569635,
"grad_norm": 4.681258678436279,
"learning_rate": 3.5459748892171347e-06,
"loss": 0.06353046894073486,
"step": 9700
},
{
"epoch": 7.178795714813447,
"grad_norm": 35.70468521118164,
"learning_rate": 3.5275110782865583e-06,
"loss": 0.08770065903663635,
"step": 9720
},
{
"epoch": 7.19357222016993,
"grad_norm": 1.4713128805160522,
"learning_rate": 3.5090472673559828e-06,
"loss": 0.05192849636077881,
"step": 9740
},
{
"epoch": 7.208348725526413,
"grad_norm": 1.2047797441482544,
"learning_rate": 3.4905834564254064e-06,
"loss": 0.04381631016731262,
"step": 9760
},
{
"epoch": 7.223125230882896,
"grad_norm": 10.057792663574219,
"learning_rate": 3.4721196454948305e-06,
"loss": 0.09565553069114685,
"step": 9780
},
{
"epoch": 7.23790173623938,
"grad_norm": 1.5531599521636963,
"learning_rate": 3.4536558345642545e-06,
"loss": 0.07716665863990783,
"step": 9800
},
{
"epoch": 7.252678241595863,
"grad_norm": 0.5546455979347229,
"learning_rate": 3.435192023633678e-06,
"loss": 0.08550006747245789,
"step": 9820
},
{
"epoch": 7.267454746952346,
"grad_norm": 0.5165857076644897,
"learning_rate": 3.4167282127031022e-06,
"loss": 0.04989692568778992,
"step": 9840
},
{
"epoch": 7.282231252308829,
"grad_norm": 0.5987501740455627,
"learning_rate": 3.3982644017725263e-06,
"loss": 0.05026379823684692,
"step": 9860
},
{
"epoch": 7.2970077576653125,
"grad_norm": 3.912698268890381,
"learning_rate": 3.37980059084195e-06,
"loss": 0.0808017373085022,
"step": 9880
},
{
"epoch": 7.311784263021796,
"grad_norm": 4.0901031494140625,
"learning_rate": 3.361336779911374e-06,
"loss": 0.07793263792991638,
"step": 9900
},
{
"epoch": 7.326560768378279,
"grad_norm": 2.155484676361084,
"learning_rate": 3.342872968980798e-06,
"loss": 0.07728356122970581,
"step": 9920
},
{
"epoch": 7.341337273734762,
"grad_norm": 1.693259596824646,
"learning_rate": 3.3244091580502217e-06,
"loss": 0.08032504916191101,
"step": 9940
},
{
"epoch": 7.3561137790912445,
"grad_norm": 2.041797161102295,
"learning_rate": 3.3059453471196458e-06,
"loss": 0.06163349151611328,
"step": 9960
},
{
"epoch": 7.370890284447728,
"grad_norm": 1.0255249738693237,
"learning_rate": 3.28748153618907e-06,
"loss": 0.047976037859916686,
"step": 9980
},
{
"epoch": 7.385666789804211,
"grad_norm": 2.119737386703491,
"learning_rate": 3.269017725258494e-06,
"loss": 0.07665503025054932,
"step": 10000
},
{
"epoch": 7.400443295160694,
"grad_norm": 21.90088653564453,
"learning_rate": 3.2505539143279175e-06,
"loss": 0.0909754455089569,
"step": 10020
},
{
"epoch": 7.415219800517177,
"grad_norm": 0.9481786489486694,
"learning_rate": 3.2320901033973416e-06,
"loss": 0.08256807327270507,
"step": 10040
},
{
"epoch": 7.429996305873661,
"grad_norm": 0.6522788405418396,
"learning_rate": 3.2136262924667657e-06,
"loss": 0.057797348499298094,
"step": 10060
},
{
"epoch": 7.444772811230144,
"grad_norm": 1.4195839166641235,
"learning_rate": 3.1951624815361893e-06,
"loss": 0.06721503138542176,
"step": 10080
},
{
"epoch": 7.459549316586627,
"grad_norm": 5.7831711769104,
"learning_rate": 3.176698670605613e-06,
"loss": 0.05335658192634583,
"step": 10100
},
{
"epoch": 7.47432582194311,
"grad_norm": 1.6023027896881104,
"learning_rate": 3.1582348596750374e-06,
"loss": 0.07950699925422669,
"step": 10120
},
{
"epoch": 7.489102327299594,
"grad_norm": 0.9103567600250244,
"learning_rate": 3.139771048744461e-06,
"loss": 0.06585381627082824,
"step": 10140
},
{
"epoch": 7.503878832656077,
"grad_norm": 2.5598886013031006,
"learning_rate": 3.1213072378138847e-06,
"loss": 0.06898097395896911,
"step": 10160
},
{
"epoch": 7.51865533801256,
"grad_norm": 0.6023147702217102,
"learning_rate": 3.102843426883309e-06,
"loss": 0.04684567451477051,
"step": 10180
},
{
"epoch": 7.533431843369043,
"grad_norm": 0.4245656132698059,
"learning_rate": 3.084379615952733e-06,
"loss": 0.09609147906303406,
"step": 10200
},
{
"epoch": 7.5482083487255265,
"grad_norm": 1.4760165214538574,
"learning_rate": 3.0659158050221565e-06,
"loss": 0.07743613719940186,
"step": 10220
},
{
"epoch": 7.56298485408201,
"grad_norm": 0.7457749247550964,
"learning_rate": 3.047451994091581e-06,
"loss": 0.07156471610069275,
"step": 10240
},
{
"epoch": 7.577761359438493,
"grad_norm": 2.0685207843780518,
"learning_rate": 3.0289881831610046e-06,
"loss": 0.07083943486213684,
"step": 10260
},
{
"epoch": 7.592537864794976,
"grad_norm": 0.3690468668937683,
"learning_rate": 3.0105243722304282e-06,
"loss": 0.047225388884544375,
"step": 10280
},
{
"epoch": 7.607314370151459,
"grad_norm": 0.4887411892414093,
"learning_rate": 2.9920605612998527e-06,
"loss": 0.06672727465629577,
"step": 10300
},
{
"epoch": 7.622090875507943,
"grad_norm": 4.116847515106201,
"learning_rate": 2.9735967503692764e-06,
"loss": 0.0581961989402771,
"step": 10320
},
{
"epoch": 7.636867380864426,
"grad_norm": 23.37555694580078,
"learning_rate": 2.9551329394387e-06,
"loss": 0.0588326096534729,
"step": 10340
},
{
"epoch": 7.651643886220909,
"grad_norm": 0.48335275053977966,
"learning_rate": 2.9366691285081245e-06,
"loss": 0.08263421654701233,
"step": 10360
},
{
"epoch": 7.666420391577392,
"grad_norm": 0.7323867082595825,
"learning_rate": 2.918205317577548e-06,
"loss": 0.06744208335876464,
"step": 10380
},
{
"epoch": 7.681196896933875,
"grad_norm": 1.5117905139923096,
"learning_rate": 2.8997415066469718e-06,
"loss": 0.07729549407958984,
"step": 10400
},
{
"epoch": 7.695973402290358,
"grad_norm": 3.720348358154297,
"learning_rate": 2.8812776957163963e-06,
"loss": 0.0746698796749115,
"step": 10420
},
{
"epoch": 7.710749907646841,
"grad_norm": 3.8074681758880615,
"learning_rate": 2.86281388478582e-06,
"loss": 0.06685426831245422,
"step": 10440
},
{
"epoch": 7.725526413003324,
"grad_norm": 1.1172499656677246,
"learning_rate": 2.844350073855244e-06,
"loss": 0.04182016849517822,
"step": 10460
},
{
"epoch": 7.7403029183598075,
"grad_norm": 0.5046330094337463,
"learning_rate": 2.825886262924668e-06,
"loss": 0.0584184467792511,
"step": 10480
},
{
"epoch": 7.755079423716291,
"grad_norm": 6.000629901885986,
"learning_rate": 2.8074224519940917e-06,
"loss": 0.06922175884246826,
"step": 10500
},
{
"epoch": 7.769855929072774,
"grad_norm": 1.0158432722091675,
"learning_rate": 2.7889586410635157e-06,
"loss": 0.08278453350067139,
"step": 10520
},
{
"epoch": 7.784632434429257,
"grad_norm": 1.0153056383132935,
"learning_rate": 2.7704948301329398e-06,
"loss": 0.05775232315063476,
"step": 10540
},
{
"epoch": 7.7994089397857405,
"grad_norm": 0.3082149624824524,
"learning_rate": 2.7520310192023634e-06,
"loss": 0.07670551538467407,
"step": 10560
},
{
"epoch": 7.814185445142224,
"grad_norm": 1.472342848777771,
"learning_rate": 2.7335672082717875e-06,
"loss": 0.05249335765838623,
"step": 10580
},
{
"epoch": 7.828961950498707,
"grad_norm": 1.928495168685913,
"learning_rate": 2.7151033973412115e-06,
"loss": 0.04385626614093781,
"step": 10600
},
{
"epoch": 7.84373845585519,
"grad_norm": 0.6438698768615723,
"learning_rate": 2.696639586410635e-06,
"loss": 0.05634819269180298,
"step": 10620
},
{
"epoch": 7.858514961211673,
"grad_norm": 0.61338210105896,
"learning_rate": 2.6781757754800592e-06,
"loss": 0.06107587218284607,
"step": 10640
},
{
"epoch": 7.873291466568157,
"grad_norm": 5.929930686950684,
"learning_rate": 2.6597119645494833e-06,
"loss": 0.06847046017646789,
"step": 10660
},
{
"epoch": 7.88806797192464,
"grad_norm": 1.9930670261383057,
"learning_rate": 2.6412481536189074e-06,
"loss": 0.06411972045898437,
"step": 10680
},
{
"epoch": 7.902844477281123,
"grad_norm": 4.4224138259887695,
"learning_rate": 2.622784342688331e-06,
"loss": 0.053265047073364255,
"step": 10700
},
{
"epoch": 7.917620982637606,
"grad_norm": 0.4610840976238251,
"learning_rate": 2.604320531757755e-06,
"loss": 0.06436032056808472,
"step": 10720
},
{
"epoch": 7.9323974879940895,
"grad_norm": 4.301944732666016,
"learning_rate": 2.585856720827179e-06,
"loss": 0.049570322036743164,
"step": 10740
},
{
"epoch": 7.947173993350573,
"grad_norm": 1.7284632921218872,
"learning_rate": 2.5673929098966028e-06,
"loss": 0.05916706919670105,
"step": 10760
},
{
"epoch": 7.961950498707056,
"grad_norm": 0.6008065938949585,
"learning_rate": 2.548929098966027e-06,
"loss": 0.06731182932853699,
"step": 10780
},
{
"epoch": 7.976727004063539,
"grad_norm": 0.3111315667629242,
"learning_rate": 2.530465288035451e-06,
"loss": 0.1318001627922058,
"step": 10800
},
{
"epoch": 7.991503509420022,
"grad_norm": 11.532929420471191,
"learning_rate": 2.5120014771048745e-06,
"loss": 0.06037134528160095,
"step": 10820
},
{
"epoch": 8.0,
"eval_f1": 0.078113428181641,
"eval_f1_author": 0.6329113924050632,
"eval_f1_chapter": 0.5358490566037736,
"eval_f1_quote": 0.022925944252020453,
"eval_f1_sabche": 0.19551934826883913,
"eval_f1_tsawa": 0.03828125,
"eval_f1_yigchung": 0.02306079664570231,
"eval_loss": 0.15565519034862518,
"eval_precision": 0.052703555649063746,
"eval_recall": 0.15083546590395905,
"eval_runtime": 165.0116,
"eval_samples_per_second": 8.581,
"eval_soft_f1_tol0": 0.078113428181641,
"eval_soft_f1_tol1": 0.09284739816799845,
"eval_soft_precision_tol0": 0.052703555649063746,
"eval_soft_precision_tol1": 0.06264464548706081,
"eval_soft_recall_tol0": 0.15083546590395905,
"eval_soft_recall_tol1": 0.17928646695769984,
"eval_steps_per_second": 4.291,
"step": 10832
},
{
"epoch": 8.005910602142594,
"grad_norm": 2.1579151153564453,
"learning_rate": 2.4935376661742986e-06,
"loss": 0.07711859941482543,
"step": 10840
},
{
"epoch": 8.020687107499077,
"grad_norm": 3.3946733474731445,
"learning_rate": 2.4750738552437227e-06,
"loss": 0.05248526334762573,
"step": 10860
},
{
"epoch": 8.03546361285556,
"grad_norm": 0.8030837178230286,
"learning_rate": 2.4566100443131463e-06,
"loss": 0.05882420539855957,
"step": 10880
},
{
"epoch": 8.050240118212043,
"grad_norm": 1.4665626287460327,
"learning_rate": 2.4381462333825704e-06,
"loss": 0.05229646563529968,
"step": 10900
},
{
"epoch": 8.065016623568527,
"grad_norm": 0.7068586945533752,
"learning_rate": 2.4196824224519944e-06,
"loss": 0.05621843934059143,
"step": 10920
},
{
"epoch": 8.07979312892501,
"grad_norm": 13.662188529968262,
"learning_rate": 2.401218611521418e-06,
"loss": 0.07908115386962891,
"step": 10940
},
{
"epoch": 8.094569634281493,
"grad_norm": 1.4691482782363892,
"learning_rate": 2.382754800590842e-06,
"loss": 0.04945688545703888,
"step": 10960
},
{
"epoch": 8.109346139637976,
"grad_norm": 1.5256794691085815,
"learning_rate": 2.364290989660266e-06,
"loss": 0.07540469765663146,
"step": 10980
},
{
"epoch": 8.12412264499446,
"grad_norm": 5.053011894226074,
"learning_rate": 2.34582717872969e-06,
"loss": 0.0591805636882782,
"step": 11000
},
{
"epoch": 8.138899150350943,
"grad_norm": 52.21064376831055,
"learning_rate": 2.327363367799114e-06,
"loss": 0.07968745231628419,
"step": 11020
},
{
"epoch": 8.153675655707426,
"grad_norm": 0.35048380494117737,
"learning_rate": 2.308899556868538e-06,
"loss": 0.07585124969482422,
"step": 11040
},
{
"epoch": 8.16845216106391,
"grad_norm": 1.5223101377487183,
"learning_rate": 2.2904357459379616e-06,
"loss": 0.047140184044837954,
"step": 11060
},
{
"epoch": 8.183228666420392,
"grad_norm": 0.5402227640151978,
"learning_rate": 2.2719719350073857e-06,
"loss": 0.09294419288635254,
"step": 11080
},
{
"epoch": 8.198005171776876,
"grad_norm": 3.652620792388916,
"learning_rate": 2.2535081240768097e-06,
"loss": 0.07985466718673706,
"step": 11100
},
{
"epoch": 8.212781677133359,
"grad_norm": 16.917766571044922,
"learning_rate": 2.2350443131462334e-06,
"loss": 0.06262078881263733,
"step": 11120
},
{
"epoch": 8.22755818248984,
"grad_norm": 24.27214813232422,
"learning_rate": 2.2165805022156574e-06,
"loss": 0.05749679803848266,
"step": 11140
},
{
"epoch": 8.242334687846324,
"grad_norm": 5.471474647521973,
"learning_rate": 2.1981166912850815e-06,
"loss": 0.04422816038131714,
"step": 11160
},
{
"epoch": 8.257111193202807,
"grad_norm": 0.7701852917671204,
"learning_rate": 2.179652880354505e-06,
"loss": 0.07289736270904541,
"step": 11180
},
{
"epoch": 8.27188769855929,
"grad_norm": 1.4652774333953857,
"learning_rate": 2.161189069423929e-06,
"loss": 0.04339292943477631,
"step": 11200
},
{
"epoch": 8.286664203915773,
"grad_norm": 1.381983995437622,
"learning_rate": 2.1427252584933533e-06,
"loss": 0.0735504686832428,
"step": 11220
},
{
"epoch": 8.301440709272256,
"grad_norm": 0.3620763421058655,
"learning_rate": 2.124261447562777e-06,
"loss": 0.04663418531417847,
"step": 11240
},
{
"epoch": 8.31621721462874,
"grad_norm": 0.6030099987983704,
"learning_rate": 2.105797636632201e-06,
"loss": 0.08779561519622803,
"step": 11260
},
{
"epoch": 8.330993719985223,
"grad_norm": 0.49633920192718506,
"learning_rate": 2.087333825701625e-06,
"loss": 0.043836405873298644,
"step": 11280
},
{
"epoch": 8.345770225341706,
"grad_norm": 2.935232162475586,
"learning_rate": 2.068870014771049e-06,
"loss": 0.07331466078758239,
"step": 11300
},
{
"epoch": 8.36054673069819,
"grad_norm": 2.249917984008789,
"learning_rate": 2.0504062038404727e-06,
"loss": 0.0779447615146637,
"step": 11320
},
{
"epoch": 8.375323236054673,
"grad_norm": 2.958724021911621,
"learning_rate": 2.0319423929098968e-06,
"loss": 0.04790572226047516,
"step": 11340
},
{
"epoch": 8.390099741411156,
"grad_norm": 1.1372202634811401,
"learning_rate": 2.013478581979321e-06,
"loss": 0.0684406042098999,
"step": 11360
},
{
"epoch": 8.404876246767639,
"grad_norm": 0.6064414978027344,
"learning_rate": 1.9950147710487445e-06,
"loss": 0.07383196949958801,
"step": 11380
},
{
"epoch": 8.419652752124122,
"grad_norm": 1.1597403287887573,
"learning_rate": 1.9765509601181685e-06,
"loss": 0.06087034344673157,
"step": 11400
},
{
"epoch": 8.434429257480605,
"grad_norm": 0.303718239068985,
"learning_rate": 1.9580871491875926e-06,
"loss": 0.05310549139976502,
"step": 11420
},
{
"epoch": 8.449205762837089,
"grad_norm": 1.0593205690383911,
"learning_rate": 1.9396233382570167e-06,
"loss": 0.08573430180549621,
"step": 11440
},
{
"epoch": 8.463982268193572,
"grad_norm": 0.6051086187362671,
"learning_rate": 1.9211595273264403e-06,
"loss": 0.04655522108078003,
"step": 11460
},
{
"epoch": 8.478758773550055,
"grad_norm": 0.7293269634246826,
"learning_rate": 1.9026957163958642e-06,
"loss": 0.047673153877258304,
"step": 11480
},
{
"epoch": 8.493535278906538,
"grad_norm": 3.2550477981567383,
"learning_rate": 1.8842319054652882e-06,
"loss": 0.0773697853088379,
"step": 11500
},
{
"epoch": 8.508311784263022,
"grad_norm": 6.078882217407227,
"learning_rate": 1.865768094534712e-06,
"loss": 0.065925931930542,
"step": 11520
},
{
"epoch": 8.523088289619505,
"grad_norm": 0.7785726189613342,
"learning_rate": 1.8473042836041361e-06,
"loss": 0.04466622471809387,
"step": 11540
},
{
"epoch": 8.537864794975988,
"grad_norm": 10.585920333862305,
"learning_rate": 1.82884047267356e-06,
"loss": 0.05552770495414734,
"step": 11560
},
{
"epoch": 8.552641300332471,
"grad_norm": 1.586756944656372,
"learning_rate": 1.8103766617429838e-06,
"loss": 0.05492196679115295,
"step": 11580
},
{
"epoch": 8.567417805688955,
"grad_norm": 4.502561092376709,
"learning_rate": 1.791912850812408e-06,
"loss": 0.04593832492828369,
"step": 11600
},
{
"epoch": 8.582194311045438,
"grad_norm": 0.3592228889465332,
"learning_rate": 1.773449039881832e-06,
"loss": 0.05370086431503296,
"step": 11620
},
{
"epoch": 8.596970816401921,
"grad_norm": 2.192084789276123,
"learning_rate": 1.7549852289512556e-06,
"loss": 0.057416385412216185,
"step": 11640
},
{
"epoch": 8.611747321758404,
"grad_norm": 7.801477909088135,
"learning_rate": 1.7365214180206797e-06,
"loss": 0.04873884320259094,
"step": 11660
},
{
"epoch": 8.626523827114887,
"grad_norm": 1.4078447818756104,
"learning_rate": 1.7180576070901037e-06,
"loss": 0.06578179001808167,
"step": 11680
},
{
"epoch": 8.64130033247137,
"grad_norm": 0.5382224321365356,
"learning_rate": 1.6995937961595274e-06,
"loss": 0.04348756074905395,
"step": 11700
},
{
"epoch": 8.656076837827854,
"grad_norm": 9.631117820739746,
"learning_rate": 1.6811299852289514e-06,
"loss": 0.044504037499427794,
"step": 11720
},
{
"epoch": 8.670853343184337,
"grad_norm": 2.4778292179107666,
"learning_rate": 1.6626661742983755e-06,
"loss": 0.06356271505355834,
"step": 11740
},
{
"epoch": 8.68562984854082,
"grad_norm": 0.491955429315567,
"learning_rate": 1.6442023633677991e-06,
"loss": 0.04952188134193421,
"step": 11760
},
{
"epoch": 8.700406353897304,
"grad_norm": 4.607267379760742,
"learning_rate": 1.6257385524372232e-06,
"loss": 0.04706520736217499,
"step": 11780
},
{
"epoch": 8.715182859253787,
"grad_norm": 0.7008641958236694,
"learning_rate": 1.607274741506647e-06,
"loss": 0.05864681601524353,
"step": 11800
},
{
"epoch": 8.72995936461027,
"grad_norm": 0.5549156665802002,
"learning_rate": 1.588810930576071e-06,
"loss": 0.04091382026672363,
"step": 11820
},
{
"epoch": 8.744735869966753,
"grad_norm": 1.034030795097351,
"learning_rate": 1.570347119645495e-06,
"loss": 0.06150263547897339,
"step": 11840
},
{
"epoch": 8.759512375323236,
"grad_norm": 0.10387372225522995,
"learning_rate": 1.5518833087149188e-06,
"loss": 0.08394623398780823,
"step": 11860
},
{
"epoch": 8.77428888067972,
"grad_norm": 2.6215879917144775,
"learning_rate": 1.5334194977843429e-06,
"loss": 0.06966426372528076,
"step": 11880
},
{
"epoch": 8.789065386036203,
"grad_norm": 1.2103021144866943,
"learning_rate": 1.5149556868537667e-06,
"loss": 0.06575006246566772,
"step": 11900
},
{
"epoch": 8.803841891392686,
"grad_norm": 0.6398591995239258,
"learning_rate": 1.4964918759231906e-06,
"loss": 0.0421683132648468,
"step": 11920
},
{
"epoch": 8.81861839674917,
"grad_norm": 1.3616020679473877,
"learning_rate": 1.4780280649926146e-06,
"loss": 0.0612963855266571,
"step": 11940
},
{
"epoch": 8.833394902105653,
"grad_norm": 4.912907123565674,
"learning_rate": 1.4595642540620387e-06,
"loss": 0.06581094861030579,
"step": 11960
},
{
"epoch": 8.848171407462136,
"grad_norm": 2.9496781826019287,
"learning_rate": 1.4411004431314623e-06,
"loss": 0.053212988376617434,
"step": 11980
},
{
"epoch": 8.862947912818619,
"grad_norm": 2.9502012729644775,
"learning_rate": 1.4226366322008864e-06,
"loss": 0.0668389618396759,
"step": 12000
},
{
"epoch": 8.877724418175102,
"grad_norm": 2.433690309524536,
"learning_rate": 1.4041728212703105e-06,
"loss": 0.037620559334754944,
"step": 12020
},
{
"epoch": 8.892500923531585,
"grad_norm": 2.284485340118408,
"learning_rate": 1.3857090103397341e-06,
"loss": 0.0484234482049942,
"step": 12040
},
{
"epoch": 8.907277428888069,
"grad_norm": 1.8322745561599731,
"learning_rate": 1.3672451994091582e-06,
"loss": 0.06214856505393982,
"step": 12060
},
{
"epoch": 8.922053934244552,
"grad_norm": 0.7853118777275085,
"learning_rate": 1.3487813884785822e-06,
"loss": 0.055500417947769165,
"step": 12080
},
{
"epoch": 8.936830439601035,
"grad_norm": 4.10518741607666,
"learning_rate": 1.3303175775480059e-06,
"loss": 0.048936331272125246,
"step": 12100
},
{
"epoch": 8.951606944957518,
"grad_norm": 1.1195242404937744,
"learning_rate": 1.31185376661743e-06,
"loss": 0.06584148406982422,
"step": 12120
},
{
"epoch": 8.966383450314002,
"grad_norm": 0.641355037689209,
"learning_rate": 1.293389955686854e-06,
"loss": 0.044033628702163694,
"step": 12140
},
{
"epoch": 8.981159955670485,
"grad_norm": 0.42096570134162903,
"learning_rate": 1.2749261447562776e-06,
"loss": 0.05240891575813293,
"step": 12160
},
{
"epoch": 8.995936461026966,
"grad_norm": 0.38925522565841675,
"learning_rate": 1.2564623338257017e-06,
"loss": 0.05426003932952881,
"step": 12180
},
{
"epoch": 9.0,
"eval_f1": 0.07275034366078037,
"eval_f1_author": 0.8474576271186441,
"eval_f1_chapter": 0.5394990366088631,
"eval_f1_quote": 0.02517042475091767,
"eval_f1_sabche": 0.19645203679369252,
"eval_f1_tsawa": 0.02471066624960901,
"eval_f1_yigchung": 0.02242609582059123,
"eval_loss": 0.1835169643163681,
"eval_precision": 0.047496318114874814,
"eval_recall": 0.15535149781725124,
"eval_runtime": 165.1087,
"eval_samples_per_second": 8.576,
"eval_soft_f1_tol0": 0.07275034366078037,
"eval_soft_f1_tol1": 0.08677875295195799,
"eval_soft_precision_tol0": 0.047496318114874814,
"eval_soft_precision_tol1": 0.05665500736377025,
"eval_soft_recall_tol0": 0.15535149781725124,
"eval_soft_recall_tol1": 0.18530784284208943,
"eval_steps_per_second": 4.288,
"step": 12186
},
{
"epoch": 9.010343553749538,
"grad_norm": 2.0108277797698975,
"learning_rate": 1.2379985228951256e-06,
"loss": 0.052083301544189456,
"step": 12200
},
{
"epoch": 9.02512005910602,
"grad_norm": 1.2710344791412354,
"learning_rate": 1.2195347119645496e-06,
"loss": 0.04657279849052429,
"step": 12220
},
{
"epoch": 9.039896564462504,
"grad_norm": 3.290432929992676,
"learning_rate": 1.2010709010339735e-06,
"loss": 0.053932797908782956,
"step": 12240
},
{
"epoch": 9.054673069818987,
"grad_norm": 3.455592632293701,
"learning_rate": 1.1826070901033975e-06,
"loss": 0.04181999266147614,
"step": 12260
},
{
"epoch": 9.06944957517547,
"grad_norm": 0.8768973350524902,
"learning_rate": 1.1641432791728214e-06,
"loss": 0.04498501718044281,
"step": 12280
},
{
"epoch": 9.084226080531954,
"grad_norm": 1.0547517538070679,
"learning_rate": 1.1456794682422454e-06,
"loss": 0.05230042338371277,
"step": 12300
},
{
"epoch": 9.099002585888437,
"grad_norm": 0.5589583516120911,
"learning_rate": 1.1272156573116693e-06,
"loss": 0.029669377207756042,
"step": 12320
},
{
"epoch": 9.11377909124492,
"grad_norm": 1.2545840740203857,
"learning_rate": 1.1087518463810931e-06,
"loss": 0.054693788290023804,
"step": 12340
},
{
"epoch": 9.128555596601403,
"grad_norm": 0.7975963354110718,
"learning_rate": 1.090288035450517e-06,
"loss": 0.043471553921699525,
"step": 12360
},
{
"epoch": 9.143332101957887,
"grad_norm": 0.8609389662742615,
"learning_rate": 1.071824224519941e-06,
"loss": 0.058015328645706174,
"step": 12380
},
{
"epoch": 9.15810860731437,
"grad_norm": 0.8450402617454529,
"learning_rate": 1.053360413589365e-06,
"loss": 0.05661097168922424,
"step": 12400
},
{
"epoch": 9.172885112670853,
"grad_norm": 0.9121461510658264,
"learning_rate": 1.0348966026587888e-06,
"loss": 0.0575255274772644,
"step": 12420
},
{
"epoch": 9.187661618027336,
"grad_norm": 4.955350399017334,
"learning_rate": 1.0164327917282128e-06,
"loss": 0.06455204486846924,
"step": 12440
},
{
"epoch": 9.20243812338382,
"grad_norm": 2.467707395553589,
"learning_rate": 9.979689807976367e-07,
"loss": 0.05920677185058594,
"step": 12460
},
{
"epoch": 9.217214628740303,
"grad_norm": 3.3803417682647705,
"learning_rate": 9.795051698670605e-07,
"loss": 0.06505635380744934,
"step": 12480
},
{
"epoch": 9.231991134096786,
"grad_norm": 1.9070857763290405,
"learning_rate": 9.610413589364846e-07,
"loss": 0.05703251957893372,
"step": 12500
},
{
"epoch": 9.24676763945327,
"grad_norm": 0.7532405257225037,
"learning_rate": 9.425775480059085e-07,
"loss": 0.07430781722068787,
"step": 12520
},
{
"epoch": 9.261544144809752,
"grad_norm": 0.5228182077407837,
"learning_rate": 9.241137370753324e-07,
"loss": 0.04709105491638184,
"step": 12540
},
{
"epoch": 9.276320650166236,
"grad_norm": 2.1428382396698,
"learning_rate": 9.056499261447565e-07,
"loss": 0.03247714936733246,
"step": 12560
},
{
"epoch": 9.291097155522719,
"grad_norm": 0.8673068881034851,
"learning_rate": 8.871861152141803e-07,
"loss": 0.061164742708206175,
"step": 12580
},
{
"epoch": 9.305873660879202,
"grad_norm": 0.7757630348205566,
"learning_rate": 8.687223042836042e-07,
"loss": 0.0636709451675415,
"step": 12600
},
{
"epoch": 9.320650166235685,
"grad_norm": 0.3789798319339752,
"learning_rate": 8.502584933530281e-07,
"loss": 0.06991657614707947,
"step": 12620
},
{
"epoch": 9.335426671592169,
"grad_norm": 1.289706826210022,
"learning_rate": 8.317946824224521e-07,
"loss": 0.0571079432964325,
"step": 12640
},
{
"epoch": 9.350203176948652,
"grad_norm": 2.217298746109009,
"learning_rate": 8.13330871491876e-07,
"loss": 0.06639298200607299,
"step": 12660
},
{
"epoch": 9.364979682305135,
"grad_norm": 2.0172104835510254,
"learning_rate": 7.948670605612999e-07,
"loss": 0.049657991528511046,
"step": 12680
},
{
"epoch": 9.379756187661618,
"grad_norm": 0.7771289944648743,
"learning_rate": 7.764032496307238e-07,
"loss": 0.054209810495376584,
"step": 12700
},
{
"epoch": 9.394532693018101,
"grad_norm": 0.8247066140174866,
"learning_rate": 7.579394387001478e-07,
"loss": 0.051841634511947635,
"step": 12720
},
{
"epoch": 9.409309198374585,
"grad_norm": 1.73972749710083,
"learning_rate": 7.394756277695716e-07,
"loss": 0.05889207124710083,
"step": 12740
},
{
"epoch": 9.424085703731068,
"grad_norm": 0.8737736940383911,
"learning_rate": 7.210118168389957e-07,
"loss": 0.04698338210582733,
"step": 12760
},
{
"epoch": 9.438862209087551,
"grad_norm": 0.6996101140975952,
"learning_rate": 7.025480059084196e-07,
"loss": 0.04271376430988312,
"step": 12780
},
{
"epoch": 9.453638714444034,
"grad_norm": 1.103256344795227,
"learning_rate": 6.840841949778434e-07,
"loss": 0.049988079071044925,
"step": 12800
},
{
"epoch": 9.468415219800518,
"grad_norm": 2.9897520542144775,
"learning_rate": 6.656203840472675e-07,
"loss": 0.04576165974140167,
"step": 12820
},
{
"epoch": 9.483191725157,
"grad_norm": 1.117850422859192,
"learning_rate": 6.471565731166913e-07,
"loss": 0.06554396748542786,
"step": 12840
},
{
"epoch": 9.497968230513484,
"grad_norm": 0.35472193360328674,
"learning_rate": 6.286927621861153e-07,
"loss": 0.03557739555835724,
"step": 12860
},
{
"epoch": 9.512744735869967,
"grad_norm": 0.48933377861976624,
"learning_rate": 6.102289512555392e-07,
"loss": 0.06364312171936035,
"step": 12880
},
{
"epoch": 9.52752124122645,
"grad_norm": 0.7897116541862488,
"learning_rate": 5.917651403249632e-07,
"loss": 0.0609613299369812,
"step": 12900
},
{
"epoch": 9.542297746582934,
"grad_norm": 0.7731443047523499,
"learning_rate": 5.73301329394387e-07,
"loss": 0.06103636622428894,
"step": 12920
},
{
"epoch": 9.557074251939417,
"grad_norm": 1.5260238647460938,
"learning_rate": 5.54837518463811e-07,
"loss": 0.045841604471206665,
"step": 12940
},
{
"epoch": 9.5718507572959,
"grad_norm": 1.6814101934432983,
"learning_rate": 5.363737075332349e-07,
"loss": 0.05903136730194092,
"step": 12960
},
{
"epoch": 9.586627262652383,
"grad_norm": 0.8358045816421509,
"learning_rate": 5.179098966026588e-07,
"loss": 0.038200438022613525,
"step": 12980
},
{
"epoch": 9.601403768008867,
"grad_norm": 1.6988420486450195,
"learning_rate": 4.994460856720828e-07,
"loss": 0.04223043322563171,
"step": 13000
},
{
"epoch": 9.61618027336535,
"grad_norm": 1.2412596940994263,
"learning_rate": 4.809822747415067e-07,
"loss": 0.04779085218906402,
"step": 13020
},
{
"epoch": 9.630956778721833,
"grad_norm": 3.573017120361328,
"learning_rate": 4.6251846381093063e-07,
"loss": 0.04191693961620331,
"step": 13040
},
{
"epoch": 9.645733284078315,
"grad_norm": 1.7911430597305298,
"learning_rate": 4.4405465288035453e-07,
"loss": 0.05826124548912048,
"step": 13060
},
{
"epoch": 9.660509789434798,
"grad_norm": 0.962003767490387,
"learning_rate": 4.255908419497785e-07,
"loss": 0.044104385375976565,
"step": 13080
},
{
"epoch": 9.675286294791281,
"grad_norm": 7.5156660079956055,
"learning_rate": 4.0712703101920245e-07,
"loss": 0.0587022602558136,
"step": 13100
},
{
"epoch": 9.690062800147764,
"grad_norm": 4.779650688171387,
"learning_rate": 3.886632200886263e-07,
"loss": 0.05364291667938233,
"step": 13120
},
{
"epoch": 9.704839305504247,
"grad_norm": 1.7882009744644165,
"learning_rate": 3.7019940915805025e-07,
"loss": 0.053678327798843385,
"step": 13140
},
{
"epoch": 9.71961581086073,
"grad_norm": 0.4839322566986084,
"learning_rate": 3.5173559822747416e-07,
"loss": 0.06118068695068359,
"step": 13160
},
{
"epoch": 9.734392316217214,
"grad_norm": 1.5121403932571411,
"learning_rate": 3.332717872968981e-07,
"loss": 0.0560242235660553,
"step": 13180
},
{
"epoch": 9.749168821573697,
"grad_norm": 2.458397626876831,
"learning_rate": 3.1480797636632207e-07,
"loss": 0.06006203293800354,
"step": 13200
},
{
"epoch": 9.76394532693018,
"grad_norm": 2.3938162326812744,
"learning_rate": 2.96344165435746e-07,
"loss": 0.03910043239593506,
"step": 13220
},
{
"epoch": 9.778721832286664,
"grad_norm": 1.685270071029663,
"learning_rate": 2.778803545051699e-07,
"loss": 0.04443977177143097,
"step": 13240
},
{
"epoch": 9.793498337643147,
"grad_norm": 1.0561131238937378,
"learning_rate": 2.5941654357459384e-07,
"loss": 0.04850934445858002,
"step": 13260
},
{
"epoch": 9.80827484299963,
"grad_norm": 1.5571168661117554,
"learning_rate": 2.4095273264401774e-07,
"loss": 0.07422905564308166,
"step": 13280
},
{
"epoch": 9.823051348356113,
"grad_norm": 1.0894001722335815,
"learning_rate": 2.2248892171344167e-07,
"loss": 0.05378046035766602,
"step": 13300
},
{
"epoch": 9.837827853712596,
"grad_norm": 0.5299264192581177,
"learning_rate": 2.040251107828656e-07,
"loss": 0.08799682259559631,
"step": 13320
},
{
"epoch": 9.85260435906908,
"grad_norm": 3.1349055767059326,
"learning_rate": 1.8556129985228953e-07,
"loss": 0.0586885929107666,
"step": 13340
},
{
"epoch": 9.867380864425563,
"grad_norm": 1.3758455514907837,
"learning_rate": 1.6709748892171346e-07,
"loss": 0.04619386196136475,
"step": 13360
},
{
"epoch": 9.882157369782046,
"grad_norm": 2.4516711235046387,
"learning_rate": 1.486336779911374e-07,
"loss": 0.04068346321582794,
"step": 13380
},
{
"epoch": 9.89693387513853,
"grad_norm": 0.3849327564239502,
"learning_rate": 1.301698670605613e-07,
"loss": 0.04838703870773316,
"step": 13400
},
{
"epoch": 9.911710380495013,
"grad_norm": 2.082285165786743,
"learning_rate": 1.1170605612998524e-07,
"loss": 0.037339362502098086,
"step": 13420
},
{
"epoch": 9.926486885851496,
"grad_norm": 0.25150424242019653,
"learning_rate": 9.324224519940917e-08,
"loss": 0.03626784682273865,
"step": 13440
},
{
"epoch": 9.941263391207979,
"grad_norm": 9.97179126739502,
"learning_rate": 7.47784342688331e-08,
"loss": 0.08576468229293824,
"step": 13460
},
{
"epoch": 9.956039896564462,
"grad_norm": 2.037799835205078,
"learning_rate": 5.631462333825702e-08,
"loss": 0.05722345113754272,
"step": 13480
},
{
"epoch": 9.970816401920946,
"grad_norm": 1.3057677745819092,
"learning_rate": 3.7850812407680953e-08,
"loss": 0.03660567104816437,
"step": 13500
},
{
"epoch": 9.985592907277429,
"grad_norm": 0.693729043006897,
"learning_rate": 1.9387001477104877e-08,
"loss": 0.04069242477416992,
"step": 13520
},
{
"epoch": 10.0,
"grad_norm": 0.5595923066139221,
"learning_rate": 9.231905465288037e-10,
"loss": 0.04209006726741791,
"step": 13540
},
{
"epoch": 10.0,
"eval_f1": 0.07393462262536368,
"eval_f1_author": 0.8771929824561403,
"eval_f1_chapter": 0.5661914460285132,
"eval_f1_quote": 0.027990716646740278,
"eval_f1_sabche": 0.1922019090762013,
"eval_f1_tsawa": 0.03337266138547109,
"eval_f1_yigchung": 0.02056555269922879,
"eval_loss": 0.20336957275867462,
"eval_precision": 0.04784688995215311,
"eval_recall": 0.16257714887851873,
"eval_runtime": 165.0793,
"eval_samples_per_second": 8.578,
"eval_soft_f1_tol0": 0.07393462262536368,
"eval_soft_f1_tol1": 0.08748930344001368,
"eval_soft_precision_tol0": 0.04784688995215311,
"eval_soft_precision_tol1": 0.05661881977671451,
"eval_soft_recall_tol0": 0.16257714887851873,
"eval_soft_recall_tol1": 0.19238295950624718,
"eval_steps_per_second": 4.289,
"step": 13540
}
],
"logging_steps": 20,
"max_steps": 13540,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 2
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.903188156251791e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}