PhoBert-MultiLabel / checkpoint-7386 /trainer_state.json
daccuong2002's picture
Upload folder using huggingface_hub
49a9107 verified
raw
history blame contribute delete
No virus
54.2 kB
{
"best_metric": 0.24498265981674194,
"best_model_checkpoint": "PhoBert-MultiLabel/checkpoint-7386",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 7386,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.010154346060113728,
"grad_norm": 3.567084312438965,
"learning_rate": 1.6914749661705008e-06,
"loss": 1.7799,
"step": 25
},
{
"epoch": 0.020308692120227456,
"grad_norm": 3.705420732498169,
"learning_rate": 3.3829499323410016e-06,
"loss": 1.6722,
"step": 50
},
{
"epoch": 0.030463038180341188,
"grad_norm": 3.097123384475708,
"learning_rate": 5.074424898511502e-06,
"loss": 1.5722,
"step": 75
},
{
"epoch": 0.04061738424045491,
"grad_norm": 14.346776008605957,
"learning_rate": 6.765899864682003e-06,
"loss": 1.5003,
"step": 100
},
{
"epoch": 0.05077173030056864,
"grad_norm": 3.2664577960968018,
"learning_rate": 8.457374830852504e-06,
"loss": 1.4085,
"step": 125
},
{
"epoch": 0.060926076360682375,
"grad_norm": 3.7164502143859863,
"learning_rate": 1.0148849797023005e-05,
"loss": 1.3505,
"step": 150
},
{
"epoch": 0.0710804224207961,
"grad_norm": 3.933560848236084,
"learning_rate": 1.1840324763193506e-05,
"loss": 1.217,
"step": 175
},
{
"epoch": 0.08123476848090982,
"grad_norm": 5.295672416687012,
"learning_rate": 1.3531799729364006e-05,
"loss": 1.0736,
"step": 200
},
{
"epoch": 0.09138911454102355,
"grad_norm": 12.415136337280273,
"learning_rate": 1.5223274695534506e-05,
"loss": 1.1182,
"step": 225
},
{
"epoch": 0.10154346060113728,
"grad_norm": 10.874429702758789,
"learning_rate": 1.6914749661705008e-05,
"loss": 1.123,
"step": 250
},
{
"epoch": 0.11169780666125101,
"grad_norm": 6.618790149688721,
"learning_rate": 1.8606224627875505e-05,
"loss": 1.1378,
"step": 275
},
{
"epoch": 0.12185215272136475,
"grad_norm": 9.960480690002441,
"learning_rate": 2.029769959404601e-05,
"loss": 1.0658,
"step": 300
},
{
"epoch": 0.13200649878147847,
"grad_norm": 3.2485241889953613,
"learning_rate": 2.198917456021651e-05,
"loss": 0.9226,
"step": 325
},
{
"epoch": 0.1421608448415922,
"grad_norm": 14.158449172973633,
"learning_rate": 2.368064952638701e-05,
"loss": 0.93,
"step": 350
},
{
"epoch": 0.15231519090170592,
"grad_norm": 2.6080679893493652,
"learning_rate": 2.5372124492557515e-05,
"loss": 0.7421,
"step": 375
},
{
"epoch": 0.16246953696181965,
"grad_norm": 4.75559663772583,
"learning_rate": 2.7063599458728013e-05,
"loss": 0.8481,
"step": 400
},
{
"epoch": 0.17262388302193338,
"grad_norm": 13.718697547912598,
"learning_rate": 2.8755074424898514e-05,
"loss": 0.8549,
"step": 425
},
{
"epoch": 0.1827782290820471,
"grad_norm": 5.8711466789245605,
"learning_rate": 3.044654939106901e-05,
"loss": 0.911,
"step": 450
},
{
"epoch": 0.19293257514216083,
"grad_norm": 4.887762546539307,
"learning_rate": 3.2138024357239515e-05,
"loss": 0.8915,
"step": 475
},
{
"epoch": 0.20308692120227456,
"grad_norm": 5.983439922332764,
"learning_rate": 3.3829499323410016e-05,
"loss": 0.8632,
"step": 500
},
{
"epoch": 0.2132412672623883,
"grad_norm": 2.231613874435425,
"learning_rate": 3.552097428958052e-05,
"loss": 0.7462,
"step": 525
},
{
"epoch": 0.22339561332250202,
"grad_norm": 13.936301231384277,
"learning_rate": 3.721244925575101e-05,
"loss": 0.7668,
"step": 550
},
{
"epoch": 0.23354995938261575,
"grad_norm": 15.290505409240723,
"learning_rate": 3.890392422192152e-05,
"loss": 0.7142,
"step": 575
},
{
"epoch": 0.2437043054427295,
"grad_norm": 33.517913818359375,
"learning_rate": 4.059539918809202e-05,
"loss": 0.6321,
"step": 600
},
{
"epoch": 0.2538586515028432,
"grad_norm": 8.801501274108887,
"learning_rate": 4.228687415426252e-05,
"loss": 0.7626,
"step": 625
},
{
"epoch": 0.26401299756295693,
"grad_norm": 16.529769897460938,
"learning_rate": 4.397834912043302e-05,
"loss": 0.811,
"step": 650
},
{
"epoch": 0.27416734362307066,
"grad_norm": 15.602673530578613,
"learning_rate": 4.566982408660352e-05,
"loss": 0.8739,
"step": 675
},
{
"epoch": 0.2843216896831844,
"grad_norm": 4.3945393562316895,
"learning_rate": 4.736129905277402e-05,
"loss": 0.8839,
"step": 700
},
{
"epoch": 0.2944760357432981,
"grad_norm": 6.59278678894043,
"learning_rate": 4.9052774018944517e-05,
"loss": 0.7022,
"step": 725
},
{
"epoch": 0.30463038180341184,
"grad_norm": 42.47446060180664,
"learning_rate": 4.991725590491951e-05,
"loss": 0.8486,
"step": 750
},
{
"epoch": 0.31478472786352557,
"grad_norm": 7.104182243347168,
"learning_rate": 4.972920114337295e-05,
"loss": 0.8155,
"step": 775
},
{
"epoch": 0.3249390739236393,
"grad_norm": 2.5681631565093994,
"learning_rate": 4.954114638182639e-05,
"loss": 0.6559,
"step": 800
},
{
"epoch": 0.335093419983753,
"grad_norm": 7.099673271179199,
"learning_rate": 4.935309162027983e-05,
"loss": 0.6985,
"step": 825
},
{
"epoch": 0.34524776604386676,
"grad_norm": 6.138451099395752,
"learning_rate": 4.9165036858733264e-05,
"loss": 0.8701,
"step": 850
},
{
"epoch": 0.3554021121039805,
"grad_norm": 2.4096810817718506,
"learning_rate": 4.89769820971867e-05,
"loss": 0.5512,
"step": 875
},
{
"epoch": 0.3655564581640942,
"grad_norm": 17.88941192626953,
"learning_rate": 4.8788927335640136e-05,
"loss": 0.8775,
"step": 900
},
{
"epoch": 0.37571080422420794,
"grad_norm": 3.2206945419311523,
"learning_rate": 4.860087257409358e-05,
"loss": 0.6589,
"step": 925
},
{
"epoch": 0.38586515028432167,
"grad_norm": 12.562983512878418,
"learning_rate": 4.8412817812547015e-05,
"loss": 0.6729,
"step": 950
},
{
"epoch": 0.3960194963444354,
"grad_norm": 0.8055168986320496,
"learning_rate": 4.8224763051000455e-05,
"loss": 0.6476,
"step": 975
},
{
"epoch": 0.4061738424045491,
"grad_norm": 3.906461715698242,
"learning_rate": 4.803670828945389e-05,
"loss": 0.8366,
"step": 1000
},
{
"epoch": 0.41632818846466285,
"grad_norm": 10.65334415435791,
"learning_rate": 4.784865352790733e-05,
"loss": 0.7228,
"step": 1025
},
{
"epoch": 0.4264825345247766,
"grad_norm": 3.829928398132324,
"learning_rate": 4.766059876636077e-05,
"loss": 0.5464,
"step": 1050
},
{
"epoch": 0.4366368805848903,
"grad_norm": 14.11302375793457,
"learning_rate": 4.747254400481421e-05,
"loss": 0.7691,
"step": 1075
},
{
"epoch": 0.44679122664500404,
"grad_norm": 7.801684379577637,
"learning_rate": 4.7284489243267647e-05,
"loss": 0.7456,
"step": 1100
},
{
"epoch": 0.45694557270511776,
"grad_norm": 21.654991149902344,
"learning_rate": 4.709643448172108e-05,
"loss": 0.6827,
"step": 1125
},
{
"epoch": 0.4670999187652315,
"grad_norm": 5.018062114715576,
"learning_rate": 4.690837972017452e-05,
"loss": 0.7129,
"step": 1150
},
{
"epoch": 0.4772542648253452,
"grad_norm": 1.8878921270370483,
"learning_rate": 4.672032495862795e-05,
"loss": 0.8354,
"step": 1175
},
{
"epoch": 0.487408610885459,
"grad_norm": 28.074739456176758,
"learning_rate": 4.653227019708139e-05,
"loss": 0.6568,
"step": 1200
},
{
"epoch": 0.49756295694557273,
"grad_norm": 16.48390769958496,
"learning_rate": 4.634421543553483e-05,
"loss": 0.5789,
"step": 1225
},
{
"epoch": 0.5077173030056864,
"grad_norm": 6.18392276763916,
"learning_rate": 4.615616067398827e-05,
"loss": 0.6729,
"step": 1250
},
{
"epoch": 0.5178716490658002,
"grad_norm": 5.78372859954834,
"learning_rate": 4.5968105912441704e-05,
"loss": 0.7166,
"step": 1275
},
{
"epoch": 0.5280259951259139,
"grad_norm": 21.222583770751953,
"learning_rate": 4.5780051150895143e-05,
"loss": 0.8119,
"step": 1300
},
{
"epoch": 0.5381803411860276,
"grad_norm": 23.661069869995117,
"learning_rate": 4.5591996389348576e-05,
"loss": 0.5273,
"step": 1325
},
{
"epoch": 0.5483346872461413,
"grad_norm": 0.8338175415992737,
"learning_rate": 4.5403941627802016e-05,
"loss": 0.5088,
"step": 1350
},
{
"epoch": 0.5584890333062551,
"grad_norm": 12.653846740722656,
"learning_rate": 4.5215886866255456e-05,
"loss": 0.7058,
"step": 1375
},
{
"epoch": 0.5686433793663688,
"grad_norm": 12.017010688781738,
"learning_rate": 4.5027832104708895e-05,
"loss": 0.4224,
"step": 1400
},
{
"epoch": 0.5787977254264826,
"grad_norm": 19.048152923583984,
"learning_rate": 4.483977734316233e-05,
"loss": 0.7842,
"step": 1425
},
{
"epoch": 0.5889520714865962,
"grad_norm": 7.068014621734619,
"learning_rate": 4.465172258161577e-05,
"loss": 0.68,
"step": 1450
},
{
"epoch": 0.59910641754671,
"grad_norm": 10.340466499328613,
"learning_rate": 4.446366782006921e-05,
"loss": 0.8232,
"step": 1475
},
{
"epoch": 0.6092607636068237,
"grad_norm": 23.22475814819336,
"learning_rate": 4.427561305852264e-05,
"loss": 0.5502,
"step": 1500
},
{
"epoch": 0.6194151096669375,
"grad_norm": 1.5949617624282837,
"learning_rate": 4.408755829697609e-05,
"loss": 0.5688,
"step": 1525
},
{
"epoch": 0.6295694557270511,
"grad_norm": 2.9755280017852783,
"learning_rate": 4.389950353542952e-05,
"loss": 0.6534,
"step": 1550
},
{
"epoch": 0.6397238017871649,
"grad_norm": 3.379225492477417,
"learning_rate": 4.371144877388296e-05,
"loss": 0.7196,
"step": 1575
},
{
"epoch": 0.6498781478472786,
"grad_norm": 9.963435173034668,
"learning_rate": 4.352339401233639e-05,
"loss": 0.6822,
"step": 1600
},
{
"epoch": 0.6600324939073924,
"grad_norm": 7.474037170410156,
"learning_rate": 4.333533925078983e-05,
"loss": 0.7572,
"step": 1625
},
{
"epoch": 0.670186839967506,
"grad_norm": 2.3705031871795654,
"learning_rate": 4.3147284489243265e-05,
"loss": 0.7087,
"step": 1650
},
{
"epoch": 0.6803411860276198,
"grad_norm": 18.592605590820312,
"learning_rate": 4.295922972769671e-05,
"loss": 0.8911,
"step": 1675
},
{
"epoch": 0.6904955320877335,
"grad_norm": 3.978590965270996,
"learning_rate": 4.2771174966150144e-05,
"loss": 0.5713,
"step": 1700
},
{
"epoch": 0.7006498781478473,
"grad_norm": 65.83806610107422,
"learning_rate": 4.2583120204603584e-05,
"loss": 0.6628,
"step": 1725
},
{
"epoch": 0.710804224207961,
"grad_norm": 16.577617645263672,
"learning_rate": 4.2395065443057016e-05,
"loss": 0.8093,
"step": 1750
},
{
"epoch": 0.7209585702680747,
"grad_norm": 14.462265968322754,
"learning_rate": 4.2207010681510456e-05,
"loss": 0.6299,
"step": 1775
},
{
"epoch": 0.7311129163281884,
"grad_norm": 2.203425407409668,
"learning_rate": 4.2018955919963896e-05,
"loss": 0.6891,
"step": 1800
},
{
"epoch": 0.7412672623883022,
"grad_norm": 9.452720642089844,
"learning_rate": 4.1830901158417335e-05,
"loss": 0.7139,
"step": 1825
},
{
"epoch": 0.7514216084484159,
"grad_norm": 5.190005302429199,
"learning_rate": 4.164284639687077e-05,
"loss": 0.6791,
"step": 1850
},
{
"epoch": 0.7615759545085297,
"grad_norm": 31.0141544342041,
"learning_rate": 4.145479163532421e-05,
"loss": 0.8139,
"step": 1875
},
{
"epoch": 0.7717303005686433,
"grad_norm": 2.5944440364837646,
"learning_rate": 4.126673687377765e-05,
"loss": 0.6534,
"step": 1900
},
{
"epoch": 0.7818846466287571,
"grad_norm": 75.8336181640625,
"learning_rate": 4.107868211223108e-05,
"loss": 0.7027,
"step": 1925
},
{
"epoch": 0.7920389926888708,
"grad_norm": 5.533077239990234,
"learning_rate": 4.089062735068453e-05,
"loss": 0.5782,
"step": 1950
},
{
"epoch": 0.8021933387489846,
"grad_norm": 1.3959672451019287,
"learning_rate": 4.070257258913796e-05,
"loss": 0.7102,
"step": 1975
},
{
"epoch": 0.8123476848090982,
"grad_norm": 3.2874767780303955,
"learning_rate": 4.05145178275914e-05,
"loss": 0.3529,
"step": 2000
},
{
"epoch": 0.822502030869212,
"grad_norm": 6.342546463012695,
"learning_rate": 4.032646306604483e-05,
"loss": 0.8077,
"step": 2025
},
{
"epoch": 0.8326563769293257,
"grad_norm": 10.019979476928711,
"learning_rate": 4.013840830449827e-05,
"loss": 0.7253,
"step": 2050
},
{
"epoch": 0.8428107229894395,
"grad_norm": 7.302906513214111,
"learning_rate": 3.9950353542951705e-05,
"loss": 0.707,
"step": 2075
},
{
"epoch": 0.8529650690495532,
"grad_norm": 2.442748546600342,
"learning_rate": 3.976229878140515e-05,
"loss": 0.6455,
"step": 2100
},
{
"epoch": 0.8631194151096669,
"grad_norm": 32.23735809326172,
"learning_rate": 3.9574244019858584e-05,
"loss": 0.5444,
"step": 2125
},
{
"epoch": 0.8732737611697806,
"grad_norm": 32.863529205322266,
"learning_rate": 3.9386189258312024e-05,
"loss": 0.6351,
"step": 2150
},
{
"epoch": 0.8834281072298944,
"grad_norm": 2.3048183917999268,
"learning_rate": 3.919813449676546e-05,
"loss": 0.5735,
"step": 2175
},
{
"epoch": 0.8935824532900081,
"grad_norm": 2.6550726890563965,
"learning_rate": 3.9010079735218896e-05,
"loss": 0.7734,
"step": 2200
},
{
"epoch": 0.9037367993501219,
"grad_norm": 9.991121292114258,
"learning_rate": 3.8822024973672336e-05,
"loss": 0.8157,
"step": 2225
},
{
"epoch": 0.9138911454102355,
"grad_norm": 13.777947425842285,
"learning_rate": 3.8633970212125776e-05,
"loss": 0.5001,
"step": 2250
},
{
"epoch": 0.9240454914703493,
"grad_norm": 21.878284454345703,
"learning_rate": 3.844591545057921e-05,
"loss": 0.7351,
"step": 2275
},
{
"epoch": 0.934199837530463,
"grad_norm": 25.31257438659668,
"learning_rate": 3.825786068903265e-05,
"loss": 0.7697,
"step": 2300
},
{
"epoch": 0.9443541835905768,
"grad_norm": 11.627613067626953,
"learning_rate": 3.806980592748609e-05,
"loss": 0.6896,
"step": 2325
},
{
"epoch": 0.9545085296506904,
"grad_norm": 3.0957629680633545,
"learning_rate": 3.788175116593952e-05,
"loss": 0.7445,
"step": 2350
},
{
"epoch": 0.9646628757108042,
"grad_norm": 0.6913394927978516,
"learning_rate": 3.769369640439296e-05,
"loss": 0.6054,
"step": 2375
},
{
"epoch": 0.974817221770918,
"grad_norm": 18.786376953125,
"learning_rate": 3.75056416428464e-05,
"loss": 0.8017,
"step": 2400
},
{
"epoch": 0.9849715678310317,
"grad_norm": 4.412717342376709,
"learning_rate": 3.731758688129984e-05,
"loss": 0.6515,
"step": 2425
},
{
"epoch": 0.9951259138911455,
"grad_norm": 12.414152145385742,
"learning_rate": 3.712953211975327e-05,
"loss": 0.6862,
"step": 2450
},
{
"epoch": 1.0,
"eval_accuracy": 0.8931388955295243,
"eval_f1_macro": 0.8264839311317734,
"eval_f1_micro": 0.8931388955295243,
"eval_f1_weighted": 0.8989228701567059,
"eval_loss": 0.3588244616985321,
"eval_precision_macro": 0.805949898458524,
"eval_precision_micro": 0.8931388955295243,
"eval_precision_weighted": 0.9113590658232466,
"eval_recall_macro": 0.8824212045028931,
"eval_recall_micro": 0.8931388955295243,
"eval_recall_weighted": 0.8931388955295243,
"eval_runtime": 771.6514,
"eval_samples_per_second": 5.421,
"eval_steps_per_second": 0.34,
"step": 2462
},
{
"epoch": 1.0052802599512591,
"grad_norm": 24.999309539794922,
"learning_rate": 3.694147735820671e-05,
"loss": 0.54,
"step": 2475
},
{
"epoch": 1.0154346060113728,
"grad_norm": 8.744691848754883,
"learning_rate": 3.6753422596660145e-05,
"loss": 0.6095,
"step": 2500
},
{
"epoch": 1.0255889520714867,
"grad_norm": 0.3475080132484436,
"learning_rate": 3.6565367835113585e-05,
"loss": 0.5011,
"step": 2525
},
{
"epoch": 1.0357432981316004,
"grad_norm": 6.633773326873779,
"learning_rate": 3.6377313073567024e-05,
"loss": 0.5915,
"step": 2550
},
{
"epoch": 1.045897644191714,
"grad_norm": 29.779521942138672,
"learning_rate": 3.6189258312020464e-05,
"loss": 0.5742,
"step": 2575
},
{
"epoch": 1.0560519902518277,
"grad_norm": 7.780822277069092,
"learning_rate": 3.60012035504739e-05,
"loss": 0.6241,
"step": 2600
},
{
"epoch": 1.0662063363119416,
"grad_norm": 4.101163864135742,
"learning_rate": 3.5813148788927336e-05,
"loss": 0.6369,
"step": 2625
},
{
"epoch": 1.0763606823720553,
"grad_norm": 1.4056626558303833,
"learning_rate": 3.5625094027380776e-05,
"loss": 0.528,
"step": 2650
},
{
"epoch": 1.086515028432169,
"grad_norm": 3.9203994274139404,
"learning_rate": 3.543703926583421e-05,
"loss": 0.5903,
"step": 2675
},
{
"epoch": 1.0966693744922826,
"grad_norm": 65.12606811523438,
"learning_rate": 3.5248984504287655e-05,
"loss": 0.5847,
"step": 2700
},
{
"epoch": 1.1068237205523965,
"grad_norm": 0.19117872416973114,
"learning_rate": 3.506092974274109e-05,
"loss": 0.6722,
"step": 2725
},
{
"epoch": 1.1169780666125102,
"grad_norm": 20.18349838256836,
"learning_rate": 3.487287498119453e-05,
"loss": 0.6545,
"step": 2750
},
{
"epoch": 1.1271324126726239,
"grad_norm": 6.374608993530273,
"learning_rate": 3.468482021964796e-05,
"loss": 0.5155,
"step": 2775
},
{
"epoch": 1.1372867587327375,
"grad_norm": 1.4384276866912842,
"learning_rate": 3.44967654581014e-05,
"loss": 0.5108,
"step": 2800
},
{
"epoch": 1.1474411047928514,
"grad_norm": 2.850290298461914,
"learning_rate": 3.430871069655484e-05,
"loss": 0.698,
"step": 2825
},
{
"epoch": 1.1575954508529651,
"grad_norm": 0.23200608789920807,
"learning_rate": 3.412065593500828e-05,
"loss": 0.5569,
"step": 2850
},
{
"epoch": 1.1677497969130788,
"grad_norm": 21.061634063720703,
"learning_rate": 3.393260117346171e-05,
"loss": 0.6227,
"step": 2875
},
{
"epoch": 1.1779041429731925,
"grad_norm": 13.794580459594727,
"learning_rate": 3.374454641191515e-05,
"loss": 0.5611,
"step": 2900
},
{
"epoch": 1.1880584890333061,
"grad_norm": 2.9508566856384277,
"learning_rate": 3.3556491650368585e-05,
"loss": 0.5975,
"step": 2925
},
{
"epoch": 1.19821283509342,
"grad_norm": 6.502300262451172,
"learning_rate": 3.3368436888822025e-05,
"loss": 0.5307,
"step": 2950
},
{
"epoch": 1.2083671811535337,
"grad_norm": 0.9668971300125122,
"learning_rate": 3.3180382127275464e-05,
"loss": 0.3585,
"step": 2975
},
{
"epoch": 1.2185215272136474,
"grad_norm": 87.11711883544922,
"learning_rate": 3.2992327365728904e-05,
"loss": 0.5552,
"step": 3000
},
{
"epoch": 1.2286758732737613,
"grad_norm": 46.89622116088867,
"learning_rate": 3.280427260418234e-05,
"loss": 0.5145,
"step": 3025
},
{
"epoch": 1.238830219333875,
"grad_norm": 8.770398139953613,
"learning_rate": 3.261621784263578e-05,
"loss": 0.6135,
"step": 3050
},
{
"epoch": 1.2489845653939886,
"grad_norm": 50.35541915893555,
"learning_rate": 3.2428163081089216e-05,
"loss": 0.5482,
"step": 3075
},
{
"epoch": 1.2591389114541023,
"grad_norm": 4.785242557525635,
"learning_rate": 3.224010831954265e-05,
"loss": 0.5847,
"step": 3100
},
{
"epoch": 1.269293257514216,
"grad_norm": 78.41075134277344,
"learning_rate": 3.2052053557996096e-05,
"loss": 0.7707,
"step": 3125
},
{
"epoch": 1.2794476035743299,
"grad_norm": 15.466938018798828,
"learning_rate": 3.186399879644953e-05,
"loss": 0.533,
"step": 3150
},
{
"epoch": 1.2896019496344435,
"grad_norm": 54.91196060180664,
"learning_rate": 3.167594403490297e-05,
"loss": 0.3996,
"step": 3175
},
{
"epoch": 1.2997562956945572,
"grad_norm": 6.946578502655029,
"learning_rate": 3.14878892733564e-05,
"loss": 0.5956,
"step": 3200
},
{
"epoch": 1.309910641754671,
"grad_norm": 46.90751647949219,
"learning_rate": 3.129983451180984e-05,
"loss": 0.5211,
"step": 3225
},
{
"epoch": 1.3200649878147848,
"grad_norm": 1.6958080530166626,
"learning_rate": 3.1111779750263274e-05,
"loss": 0.7166,
"step": 3250
},
{
"epoch": 1.3302193338748984,
"grad_norm": 15.985214233398438,
"learning_rate": 3.092372498871672e-05,
"loss": 0.6351,
"step": 3275
},
{
"epoch": 1.340373679935012,
"grad_norm": 13.915630340576172,
"learning_rate": 3.073567022717015e-05,
"loss": 0.5382,
"step": 3300
},
{
"epoch": 1.3505280259951258,
"grad_norm": 5.265201568603516,
"learning_rate": 3.054761546562359e-05,
"loss": 0.5942,
"step": 3325
},
{
"epoch": 1.3606823720552397,
"grad_norm": 15.926793098449707,
"learning_rate": 3.035956070407703e-05,
"loss": 0.5539,
"step": 3350
},
{
"epoch": 1.3708367181153533,
"grad_norm": 0.9688799381256104,
"learning_rate": 3.0171505942530465e-05,
"loss": 0.5066,
"step": 3375
},
{
"epoch": 1.380991064175467,
"grad_norm": 3.8147382736206055,
"learning_rate": 2.99834511809839e-05,
"loss": 0.6402,
"step": 3400
},
{
"epoch": 1.391145410235581,
"grad_norm": 54.062618255615234,
"learning_rate": 2.9795396419437344e-05,
"loss": 0.6448,
"step": 3425
},
{
"epoch": 1.4012997562956946,
"grad_norm": 2.0628786087036133,
"learning_rate": 2.960734165789078e-05,
"loss": 0.7356,
"step": 3450
},
{
"epoch": 1.4114541023558083,
"grad_norm": 23.24148178100586,
"learning_rate": 2.9419286896344217e-05,
"loss": 0.6129,
"step": 3475
},
{
"epoch": 1.421608448415922,
"grad_norm": 61.582332611083984,
"learning_rate": 2.9231232134797653e-05,
"loss": 0.6045,
"step": 3500
},
{
"epoch": 1.4317627944760356,
"grad_norm": 21.00168228149414,
"learning_rate": 2.904317737325109e-05,
"loss": 0.6363,
"step": 3525
},
{
"epoch": 1.4419171405361495,
"grad_norm": 3.503591299057007,
"learning_rate": 2.8855122611704526e-05,
"loss": 0.5809,
"step": 3550
},
{
"epoch": 1.4520714865962632,
"grad_norm": 39.078346252441406,
"learning_rate": 2.866706785015797e-05,
"loss": 0.6195,
"step": 3575
},
{
"epoch": 1.4622258326563768,
"grad_norm": 5.405745983123779,
"learning_rate": 2.8479013088611405e-05,
"loss": 0.5682,
"step": 3600
},
{
"epoch": 1.4723801787164907,
"grad_norm": 2.4771933555603027,
"learning_rate": 2.829095832706484e-05,
"loss": 0.7841,
"step": 3625
},
{
"epoch": 1.4825345247766044,
"grad_norm": 39.39826202392578,
"learning_rate": 2.810290356551828e-05,
"loss": 0.6259,
"step": 3650
},
{
"epoch": 1.492688870836718,
"grad_norm": 15.72121810913086,
"learning_rate": 2.7914848803971717e-05,
"loss": 0.5468,
"step": 3675
},
{
"epoch": 1.502843216896832,
"grad_norm": 22.185754776000977,
"learning_rate": 2.7726794042425157e-05,
"loss": 0.4637,
"step": 3700
},
{
"epoch": 1.5129975629569454,
"grad_norm": 3.0825910568237305,
"learning_rate": 2.7538739280878596e-05,
"loss": 0.5223,
"step": 3725
},
{
"epoch": 1.5231519090170593,
"grad_norm": 5.231273174285889,
"learning_rate": 2.7350684519332033e-05,
"loss": 0.6151,
"step": 3750
},
{
"epoch": 1.533306255077173,
"grad_norm": 0.22756709158420563,
"learning_rate": 2.716262975778547e-05,
"loss": 0.6018,
"step": 3775
},
{
"epoch": 1.5434606011372867,
"grad_norm": 0.42972368001937866,
"learning_rate": 2.6974574996238905e-05,
"loss": 0.5058,
"step": 3800
},
{
"epoch": 1.5536149471974006,
"grad_norm": 21.145174026489258,
"learning_rate": 2.678652023469234e-05,
"loss": 0.7302,
"step": 3825
},
{
"epoch": 1.5637692932575142,
"grad_norm": 2.556708812713623,
"learning_rate": 2.6598465473145784e-05,
"loss": 0.4961,
"step": 3850
},
{
"epoch": 1.573923639317628,
"grad_norm": 24.811382293701172,
"learning_rate": 2.641041071159922e-05,
"loss": 0.5132,
"step": 3875
},
{
"epoch": 1.5840779853777418,
"grad_norm": 2.887291669845581,
"learning_rate": 2.6222355950052657e-05,
"loss": 0.6373,
"step": 3900
},
{
"epoch": 1.5942323314378553,
"grad_norm": 3.0445516109466553,
"learning_rate": 2.6034301188506093e-05,
"loss": 0.5825,
"step": 3925
},
{
"epoch": 1.6043866774979691,
"grad_norm": 6.381601333618164,
"learning_rate": 2.584624642695953e-05,
"loss": 0.6217,
"step": 3950
},
{
"epoch": 1.6145410235580828,
"grad_norm": 2.4623990058898926,
"learning_rate": 2.5658191665412966e-05,
"loss": 0.6727,
"step": 3975
},
{
"epoch": 1.6246953696181965,
"grad_norm": 21.089733123779297,
"learning_rate": 2.547013690386641e-05,
"loss": 0.5148,
"step": 4000
},
{
"epoch": 1.6348497156783104,
"grad_norm": 1.0210952758789062,
"learning_rate": 2.5282082142319845e-05,
"loss": 0.5116,
"step": 4025
},
{
"epoch": 1.645004061738424,
"grad_norm": 6.323028564453125,
"learning_rate": 2.509402738077328e-05,
"loss": 0.4013,
"step": 4050
},
{
"epoch": 1.6551584077985377,
"grad_norm": 15.812409400939941,
"learning_rate": 2.490597261922672e-05,
"loss": 0.4226,
"step": 4075
},
{
"epoch": 1.6653127538586516,
"grad_norm": 4.813828945159912,
"learning_rate": 2.471791785768016e-05,
"loss": 0.5652,
"step": 4100
},
{
"epoch": 1.675467099918765,
"grad_norm": 0.253533273935318,
"learning_rate": 2.4529863096133597e-05,
"loss": 0.5531,
"step": 4125
},
{
"epoch": 1.685621445978879,
"grad_norm": 0.4044888913631439,
"learning_rate": 2.4341808334587033e-05,
"loss": 0.494,
"step": 4150
},
{
"epoch": 1.6957757920389926,
"grad_norm": 3.0946457386016846,
"learning_rate": 2.4153753573040473e-05,
"loss": 0.6151,
"step": 4175
},
{
"epoch": 1.7059301380991063,
"grad_norm": 1.8007519245147705,
"learning_rate": 2.396569881149391e-05,
"loss": 0.7379,
"step": 4200
},
{
"epoch": 1.7160844841592202,
"grad_norm": 7.954397201538086,
"learning_rate": 2.3777644049947345e-05,
"loss": 0.5232,
"step": 4225
},
{
"epoch": 1.7262388302193339,
"grad_norm": 1.1328774690628052,
"learning_rate": 2.3589589288400785e-05,
"loss": 0.5858,
"step": 4250
},
{
"epoch": 1.7363931762794476,
"grad_norm": 22.545045852661133,
"learning_rate": 2.340153452685422e-05,
"loss": 0.5951,
"step": 4275
},
{
"epoch": 1.7465475223395615,
"grad_norm": 8.525069236755371,
"learning_rate": 2.3213479765307658e-05,
"loss": 0.4659,
"step": 4300
},
{
"epoch": 1.756701868399675,
"grad_norm": 2.1010477542877197,
"learning_rate": 2.3025425003761097e-05,
"loss": 0.4882,
"step": 4325
},
{
"epoch": 1.7668562144597888,
"grad_norm": 10.944445610046387,
"learning_rate": 2.2837370242214533e-05,
"loss": 0.5209,
"step": 4350
},
{
"epoch": 1.7770105605199025,
"grad_norm": 34.85451889038086,
"learning_rate": 2.264931548066797e-05,
"loss": 0.6565,
"step": 4375
},
{
"epoch": 1.7871649065800161,
"grad_norm": 11.516502380371094,
"learning_rate": 2.246126071912141e-05,
"loss": 0.6836,
"step": 4400
},
{
"epoch": 1.79731925264013,
"grad_norm": 1.427713394165039,
"learning_rate": 2.2273205957574846e-05,
"loss": 0.5473,
"step": 4425
},
{
"epoch": 1.8074735987002437,
"grad_norm": 22.646167755126953,
"learning_rate": 2.2085151196028285e-05,
"loss": 0.6735,
"step": 4450
},
{
"epoch": 1.8176279447603574,
"grad_norm": 2.9643514156341553,
"learning_rate": 2.189709643448172e-05,
"loss": 0.4089,
"step": 4475
},
{
"epoch": 1.8277822908204713,
"grad_norm": 5.935336589813232,
"learning_rate": 2.170904167293516e-05,
"loss": 0.6947,
"step": 4500
},
{
"epoch": 1.8379366368805847,
"grad_norm": 5.152228832244873,
"learning_rate": 2.1520986911388597e-05,
"loss": 0.4509,
"step": 4525
},
{
"epoch": 1.8480909829406986,
"grad_norm": 13.407612800598145,
"learning_rate": 2.1332932149842037e-05,
"loss": 0.5937,
"step": 4550
},
{
"epoch": 1.8582453290008123,
"grad_norm": 3.732926368713379,
"learning_rate": 2.1144877388295473e-05,
"loss": 0.5812,
"step": 4575
},
{
"epoch": 1.868399675060926,
"grad_norm": 10.97332763671875,
"learning_rate": 2.095682262674891e-05,
"loss": 0.4815,
"step": 4600
},
{
"epoch": 1.8785540211210399,
"grad_norm": 0.9578274488449097,
"learning_rate": 2.076876786520235e-05,
"loss": 0.4805,
"step": 4625
},
{
"epoch": 1.8887083671811535,
"grad_norm": 4.262126445770264,
"learning_rate": 2.0580713103655786e-05,
"loss": 0.6214,
"step": 4650
},
{
"epoch": 1.8988627132412672,
"grad_norm": 2.12185001373291,
"learning_rate": 2.0392658342109222e-05,
"loss": 0.4471,
"step": 4675
},
{
"epoch": 1.909017059301381,
"grad_norm": 2.6735076904296875,
"learning_rate": 2.020460358056266e-05,
"loss": 0.427,
"step": 4700
},
{
"epoch": 1.9191714053614946,
"grad_norm": 18.710649490356445,
"learning_rate": 2.0016548819016098e-05,
"loss": 0.6322,
"step": 4725
},
{
"epoch": 1.9293257514216084,
"grad_norm": 8.641931533813477,
"learning_rate": 1.9828494057469534e-05,
"loss": 0.5399,
"step": 4750
},
{
"epoch": 1.9394800974817223,
"grad_norm": 3.205247640609741,
"learning_rate": 1.9640439295922974e-05,
"loss": 0.5887,
"step": 4775
},
{
"epoch": 1.9496344435418358,
"grad_norm": 1.3619911670684814,
"learning_rate": 1.945238453437641e-05,
"loss": 0.5996,
"step": 4800
},
{
"epoch": 1.9597887896019497,
"grad_norm": 6.821827411651611,
"learning_rate": 1.9264329772829846e-05,
"loss": 0.4801,
"step": 4825
},
{
"epoch": 1.9699431356620634,
"grad_norm": 2.5747969150543213,
"learning_rate": 1.9076275011283286e-05,
"loss": 0.5523,
"step": 4850
},
{
"epoch": 1.980097481722177,
"grad_norm": 13.470471382141113,
"learning_rate": 1.8888220249736725e-05,
"loss": 0.5534,
"step": 4875
},
{
"epoch": 1.990251827782291,
"grad_norm": 12.533121109008789,
"learning_rate": 1.8700165488190162e-05,
"loss": 0.6055,
"step": 4900
},
{
"epoch": 2.0,
"eval_accuracy": 0.9266076978245279,
"eval_f1_macro": 0.9119749098386866,
"eval_f1_micro": 0.9266076978245279,
"eval_f1_weighted": 0.926625315413396,
"eval_loss": 0.2657528519630432,
"eval_precision_macro": 0.928091787369496,
"eval_precision_micro": 0.9266076978245279,
"eval_precision_weighted": 0.9272787083264409,
"eval_recall_macro": 0.8972230372979126,
"eval_recall_micro": 0.9266076978245279,
"eval_recall_weighted": 0.9266076978245279,
"eval_runtime": 805.7166,
"eval_samples_per_second": 5.192,
"eval_steps_per_second": 0.325,
"step": 4924
},
{
"epoch": 2.0004061738424044,
"grad_norm": 0.43904566764831543,
"learning_rate": 1.85121107266436e-05,
"loss": 0.5567,
"step": 4925
},
{
"epoch": 2.0105605199025183,
"grad_norm": 25.5123291015625,
"learning_rate": 1.8324055965097038e-05,
"loss": 0.4346,
"step": 4950
},
{
"epoch": 2.020714865962632,
"grad_norm": 15.89987850189209,
"learning_rate": 1.8136001203550474e-05,
"loss": 0.5333,
"step": 4975
},
{
"epoch": 2.0308692120227456,
"grad_norm": 2.8034896850585938,
"learning_rate": 1.7947946442003914e-05,
"loss": 0.4765,
"step": 5000
},
{
"epoch": 2.0410235580828595,
"grad_norm": 2.8935348987579346,
"learning_rate": 1.775989168045735e-05,
"loss": 0.4422,
"step": 5025
},
{
"epoch": 2.0511779041429734,
"grad_norm": 8.14145565032959,
"learning_rate": 1.757183691891079e-05,
"loss": 0.5282,
"step": 5050
},
{
"epoch": 2.061332250203087,
"grad_norm": 6.452521800994873,
"learning_rate": 1.7383782157364226e-05,
"loss": 0.4882,
"step": 5075
},
{
"epoch": 2.0714865962632008,
"grad_norm": 3.1078271865844727,
"learning_rate": 1.7195727395817662e-05,
"loss": 0.4243,
"step": 5100
},
{
"epoch": 2.081640942323314,
"grad_norm": 4.052325248718262,
"learning_rate": 1.70076726342711e-05,
"loss": 0.3915,
"step": 5125
},
{
"epoch": 2.091795288383428,
"grad_norm": 0.33482909202575684,
"learning_rate": 1.6819617872724538e-05,
"loss": 0.4279,
"step": 5150
},
{
"epoch": 2.101949634443542,
"grad_norm": 0.27442964911460876,
"learning_rate": 1.6631563111177974e-05,
"loss": 0.4043,
"step": 5175
},
{
"epoch": 2.1121039805036554,
"grad_norm": 0.5872493982315063,
"learning_rate": 1.6443508349631414e-05,
"loss": 0.5726,
"step": 5200
},
{
"epoch": 2.1222583265637693,
"grad_norm": 2.22892689704895,
"learning_rate": 1.625545358808485e-05,
"loss": 0.52,
"step": 5225
},
{
"epoch": 2.1324126726238832,
"grad_norm": 2.56426739692688,
"learning_rate": 1.6067398826538286e-05,
"loss": 0.4345,
"step": 5250
},
{
"epoch": 2.1425670186839967,
"grad_norm": 13.771442413330078,
"learning_rate": 1.5879344064991726e-05,
"loss": 0.4729,
"step": 5275
},
{
"epoch": 2.1527213647441106,
"grad_norm": 0.1530083268880844,
"learning_rate": 1.5691289303445166e-05,
"loss": 0.446,
"step": 5300
},
{
"epoch": 2.162875710804224,
"grad_norm": 2.819397211074829,
"learning_rate": 1.5503234541898602e-05,
"loss": 0.7085,
"step": 5325
},
{
"epoch": 2.173030056864338,
"grad_norm": 12.847749710083008,
"learning_rate": 1.531517978035204e-05,
"loss": 0.6421,
"step": 5350
},
{
"epoch": 2.183184402924452,
"grad_norm": 9.512947082519531,
"learning_rate": 1.5127125018805476e-05,
"loss": 0.535,
"step": 5375
},
{
"epoch": 2.1933387489845653,
"grad_norm": 27.62982749938965,
"learning_rate": 1.4939070257258914e-05,
"loss": 0.5626,
"step": 5400
},
{
"epoch": 2.203493095044679,
"grad_norm": 10.81323528289795,
"learning_rate": 1.4751015495712354e-05,
"loss": 0.4339,
"step": 5425
},
{
"epoch": 2.213647441104793,
"grad_norm": 3.875645637512207,
"learning_rate": 1.456296073416579e-05,
"loss": 0.4962,
"step": 5450
},
{
"epoch": 2.2238017871649065,
"grad_norm": 0.1911429613828659,
"learning_rate": 1.4374905972619226e-05,
"loss": 0.5207,
"step": 5475
},
{
"epoch": 2.2339561332250204,
"grad_norm": 96.48568725585938,
"learning_rate": 1.4186851211072666e-05,
"loss": 0.5451,
"step": 5500
},
{
"epoch": 2.244110479285134,
"grad_norm": 2.502739191055298,
"learning_rate": 1.3998796449526102e-05,
"loss": 0.4988,
"step": 5525
},
{
"epoch": 2.2542648253452477,
"grad_norm": 5.941136360168457,
"learning_rate": 1.3810741687979538e-05,
"loss": 0.4889,
"step": 5550
},
{
"epoch": 2.2644191714053616,
"grad_norm": 20.13005828857422,
"learning_rate": 1.3622686926432978e-05,
"loss": 0.5544,
"step": 5575
},
{
"epoch": 2.274573517465475,
"grad_norm": 5.842233657836914,
"learning_rate": 1.3434632164886416e-05,
"loss": 0.5751,
"step": 5600
},
{
"epoch": 2.284727863525589,
"grad_norm": 11.564367294311523,
"learning_rate": 1.3246577403339852e-05,
"loss": 0.5099,
"step": 5625
},
{
"epoch": 2.294882209585703,
"grad_norm": 0.15794846415519714,
"learning_rate": 1.3058522641793292e-05,
"loss": 0.4425,
"step": 5650
},
{
"epoch": 2.3050365556458163,
"grad_norm": 4.0853142738342285,
"learning_rate": 1.2870467880246728e-05,
"loss": 0.3685,
"step": 5675
},
{
"epoch": 2.3151909017059302,
"grad_norm": 9.024371147155762,
"learning_rate": 1.2682413118700164e-05,
"loss": 0.4964,
"step": 5700
},
{
"epoch": 2.3253452477660437,
"grad_norm": 15.076045989990234,
"learning_rate": 1.2494358357153604e-05,
"loss": 0.5681,
"step": 5725
},
{
"epoch": 2.3354995938261576,
"grad_norm": 0.19159801304340363,
"learning_rate": 1.230630359560704e-05,
"loss": 0.3851,
"step": 5750
},
{
"epoch": 2.3456539398862715,
"grad_norm": 54.02906036376953,
"learning_rate": 1.2118248834060478e-05,
"loss": 0.5483,
"step": 5775
},
{
"epoch": 2.355808285946385,
"grad_norm": 7.049926280975342,
"learning_rate": 1.1930194072513918e-05,
"loss": 0.5981,
"step": 5800
},
{
"epoch": 2.365962632006499,
"grad_norm": 16.41009521484375,
"learning_rate": 1.1742139310967354e-05,
"loss": 0.4977,
"step": 5825
},
{
"epoch": 2.3761169780666123,
"grad_norm": 0.19413629174232483,
"learning_rate": 1.1554084549420792e-05,
"loss": 0.5617,
"step": 5850
},
{
"epoch": 2.386271324126726,
"grad_norm": 1.1825770139694214,
"learning_rate": 1.136602978787423e-05,
"loss": 0.4328,
"step": 5875
},
{
"epoch": 2.39642567018684,
"grad_norm": 8.703160285949707,
"learning_rate": 1.1177975026327666e-05,
"loss": 0.4351,
"step": 5900
},
{
"epoch": 2.406580016246954,
"grad_norm": 3.950902223587036,
"learning_rate": 1.0989920264781104e-05,
"loss": 0.4248,
"step": 5925
},
{
"epoch": 2.4167343623070674,
"grad_norm": 2.6033504009246826,
"learning_rate": 1.0801865503234542e-05,
"loss": 0.4334,
"step": 5950
},
{
"epoch": 2.4268887083671813,
"grad_norm": 0.4781394600868225,
"learning_rate": 1.061381074168798e-05,
"loss": 0.4309,
"step": 5975
},
{
"epoch": 2.4370430544272947,
"grad_norm": 1.0080628395080566,
"learning_rate": 1.0425755980141418e-05,
"loss": 0.4494,
"step": 6000
},
{
"epoch": 2.4471974004874086,
"grad_norm": 11.38261890411377,
"learning_rate": 1.0237701218594856e-05,
"loss": 0.5053,
"step": 6025
},
{
"epoch": 2.4573517465475225,
"grad_norm": 1.4227663278579712,
"learning_rate": 1.0049646457048292e-05,
"loss": 0.4257,
"step": 6050
},
{
"epoch": 2.467506092607636,
"grad_norm": 0.9921310544013977,
"learning_rate": 9.86159169550173e-06,
"loss": 0.5595,
"step": 6075
},
{
"epoch": 2.47766043866775,
"grad_norm": 14.428972244262695,
"learning_rate": 9.673536933955168e-06,
"loss": 0.3958,
"step": 6100
},
{
"epoch": 2.4878147847278633,
"grad_norm": 1.1158331632614136,
"learning_rate": 9.485482172408605e-06,
"loss": 0.4468,
"step": 6125
},
{
"epoch": 2.497969130787977,
"grad_norm": 0.15840868651866913,
"learning_rate": 9.297427410862043e-06,
"loss": 0.4436,
"step": 6150
},
{
"epoch": 2.508123476848091,
"grad_norm": 3.016507387161255,
"learning_rate": 9.10937264931548e-06,
"loss": 0.5268,
"step": 6175
},
{
"epoch": 2.5182778229082046,
"grad_norm": 0.9153080582618713,
"learning_rate": 8.921317887768919e-06,
"loss": 0.5499,
"step": 6200
},
{
"epoch": 2.5284321689683185,
"grad_norm": 2.3704733848571777,
"learning_rate": 8.733263126222356e-06,
"loss": 0.4143,
"step": 6225
},
{
"epoch": 2.538586515028432,
"grad_norm": 2.596069574356079,
"learning_rate": 8.545208364675794e-06,
"loss": 0.388,
"step": 6250
},
{
"epoch": 2.548740861088546,
"grad_norm": 14.82557487487793,
"learning_rate": 8.357153603129232e-06,
"loss": 0.4274,
"step": 6275
},
{
"epoch": 2.5588952071486597,
"grad_norm": 1.2737632989883423,
"learning_rate": 8.169098841582669e-06,
"loss": 0.3534,
"step": 6300
},
{
"epoch": 2.5690495532087736,
"grad_norm": 18.806808471679688,
"learning_rate": 7.981044080036107e-06,
"loss": 0.6733,
"step": 6325
},
{
"epoch": 2.579203899268887,
"grad_norm": 21.513843536376953,
"learning_rate": 7.792989318489545e-06,
"loss": 0.4451,
"step": 6350
},
{
"epoch": 2.589358245329001,
"grad_norm": 4.2879815101623535,
"learning_rate": 7.604934556942982e-06,
"loss": 0.545,
"step": 6375
},
{
"epoch": 2.5995125913891144,
"grad_norm": 2.1117591857910156,
"learning_rate": 7.41687979539642e-06,
"loss": 0.4982,
"step": 6400
},
{
"epoch": 2.6096669374492283,
"grad_norm": 25.265079498291016,
"learning_rate": 7.228825033849858e-06,
"loss": 0.4269,
"step": 6425
},
{
"epoch": 2.619821283509342,
"grad_norm": 0.9816861152648926,
"learning_rate": 7.040770272303295e-06,
"loss": 0.4884,
"step": 6450
},
{
"epoch": 2.6299756295694556,
"grad_norm": 2.7001571655273438,
"learning_rate": 6.852715510756733e-06,
"loss": 0.6128,
"step": 6475
},
{
"epoch": 2.6401299756295695,
"grad_norm": 17.872499465942383,
"learning_rate": 6.664660749210171e-06,
"loss": 0.4402,
"step": 6500
},
{
"epoch": 2.650284321689683,
"grad_norm": 3.858314275741577,
"learning_rate": 6.476605987663608e-06,
"loss": 0.5872,
"step": 6525
},
{
"epoch": 2.660438667749797,
"grad_norm": 16.253244400024414,
"learning_rate": 6.288551226117046e-06,
"loss": 0.5678,
"step": 6550
},
{
"epoch": 2.6705930138099108,
"grad_norm": 0.6387231349945068,
"learning_rate": 6.100496464570484e-06,
"loss": 0.383,
"step": 6575
},
{
"epoch": 2.680747359870024,
"grad_norm": 27.796384811401367,
"learning_rate": 5.912441703023921e-06,
"loss": 0.4691,
"step": 6600
},
{
"epoch": 2.690901705930138,
"grad_norm": 1.4365334510803223,
"learning_rate": 5.724386941477358e-06,
"loss": 0.4579,
"step": 6625
},
{
"epoch": 2.7010560519902516,
"grad_norm": 6.362787246704102,
"learning_rate": 5.536332179930797e-06,
"loss": 0.5751,
"step": 6650
},
{
"epoch": 2.7112103980503655,
"grad_norm": 5.281644344329834,
"learning_rate": 5.348277418384234e-06,
"loss": 0.5035,
"step": 6675
},
{
"epoch": 2.7213647441104794,
"grad_norm": 2.8617539405822754,
"learning_rate": 5.160222656837671e-06,
"loss": 0.373,
"step": 6700
},
{
"epoch": 2.7315190901705932,
"grad_norm": 6.853511810302734,
"learning_rate": 4.972167895291109e-06,
"loss": 0.4706,
"step": 6725
},
{
"epoch": 2.7416734362307067,
"grad_norm": 2.8362090587615967,
"learning_rate": 4.784113133744547e-06,
"loss": 0.6053,
"step": 6750
},
{
"epoch": 2.7518277822908206,
"grad_norm": 6.8812031745910645,
"learning_rate": 4.596058372197985e-06,
"loss": 0.433,
"step": 6775
},
{
"epoch": 2.761982128350934,
"grad_norm": 0.7493718862533569,
"learning_rate": 4.408003610651422e-06,
"loss": 0.6035,
"step": 6800
},
{
"epoch": 2.772136474411048,
"grad_norm": 12.810718536376953,
"learning_rate": 4.219948849104859e-06,
"loss": 0.4921,
"step": 6825
},
{
"epoch": 2.782290820471162,
"grad_norm": 4.376484394073486,
"learning_rate": 4.031894087558298e-06,
"loss": 0.453,
"step": 6850
},
{
"epoch": 2.7924451665312753,
"grad_norm": 5.702888011932373,
"learning_rate": 3.843839326011735e-06,
"loss": 0.487,
"step": 6875
},
{
"epoch": 2.802599512591389,
"grad_norm": 1.284523844718933,
"learning_rate": 3.655784564465172e-06,
"loss": 0.4004,
"step": 6900
},
{
"epoch": 2.8127538586515026,
"grad_norm": 43.9447135925293,
"learning_rate": 3.4677298029186104e-06,
"loss": 0.5632,
"step": 6925
},
{
"epoch": 2.8229082047116165,
"grad_norm": 1.2876818180084229,
"learning_rate": 3.2796750413720475e-06,
"loss": 0.3177,
"step": 6950
},
{
"epoch": 2.8330625507717304,
"grad_norm": 0.49143844842910767,
"learning_rate": 3.0916202798254854e-06,
"loss": 0.4961,
"step": 6975
},
{
"epoch": 2.843216896831844,
"grad_norm": 9.238175392150879,
"learning_rate": 2.903565518278923e-06,
"loss": 0.4309,
"step": 7000
},
{
"epoch": 2.8533712428919578,
"grad_norm": 1.5201661586761475,
"learning_rate": 2.715510756732361e-06,
"loss": 0.4751,
"step": 7025
},
{
"epoch": 2.863525588952071,
"grad_norm": 0.13578936457633972,
"learning_rate": 2.527455995185798e-06,
"loss": 0.34,
"step": 7050
},
{
"epoch": 2.873679935012185,
"grad_norm": 12.835733413696289,
"learning_rate": 2.339401233639236e-06,
"loss": 0.2968,
"step": 7075
},
{
"epoch": 2.883834281072299,
"grad_norm": 0.2961287796497345,
"learning_rate": 2.1513464720926735e-06,
"loss": 0.4396,
"step": 7100
},
{
"epoch": 2.893988627132413,
"grad_norm": 12.266148567199707,
"learning_rate": 1.9632917105461115e-06,
"loss": 0.5608,
"step": 7125
},
{
"epoch": 2.9041429731925263,
"grad_norm": 13.638496398925781,
"learning_rate": 1.7752369489995486e-06,
"loss": 0.4852,
"step": 7150
},
{
"epoch": 2.9142973192526402,
"grad_norm": 8.737442016601562,
"learning_rate": 1.5871821874529863e-06,
"loss": 0.5331,
"step": 7175
},
{
"epoch": 2.9244516653127537,
"grad_norm": 1.0912017822265625,
"learning_rate": 1.399127425906424e-06,
"loss": 0.4314,
"step": 7200
},
{
"epoch": 2.9346060113728676,
"grad_norm": 4.351292610168457,
"learning_rate": 1.2110726643598616e-06,
"loss": 0.5376,
"step": 7225
},
{
"epoch": 2.9447603574329815,
"grad_norm": 6.2538065910339355,
"learning_rate": 1.0230179028132994e-06,
"loss": 0.4093,
"step": 7250
},
{
"epoch": 2.954914703493095,
"grad_norm": 5.2288126945495605,
"learning_rate": 8.349631412667369e-07,
"loss": 0.7437,
"step": 7275
},
{
"epoch": 2.965069049553209,
"grad_norm": 1.296960711479187,
"learning_rate": 6.469083797201745e-07,
"loss": 0.396,
"step": 7300
},
{
"epoch": 2.9752233956133223,
"grad_norm": 5.880867958068848,
"learning_rate": 4.5885361817361217e-07,
"loss": 0.4873,
"step": 7325
},
{
"epoch": 2.985377741673436,
"grad_norm": 2.8329901695251465,
"learning_rate": 2.707988566270498e-07,
"loss": 0.5592,
"step": 7350
},
{
"epoch": 2.99553208773355,
"grad_norm": 5.462076663970947,
"learning_rate": 8.274409508048744e-08,
"loss": 0.627,
"step": 7375
},
{
"epoch": 3.0,
"eval_accuracy": 0.9390389672483863,
"eval_f1_macro": 0.9244631728799089,
"eval_f1_micro": 0.9390389672483863,
"eval_f1_weighted": 0.9389134636561386,
"eval_loss": 0.24498265981674194,
"eval_precision_macro": 0.9458913396195016,
"eval_precision_micro": 0.9390389672483863,
"eval_precision_weighted": 0.9393976940878069,
"eval_recall_macro": 0.9051122705051101,
"eval_recall_micro": 0.9390389672483863,
"eval_recall_weighted": 0.9390389672483863,
"eval_runtime": 773.6973,
"eval_samples_per_second": 5.407,
"eval_steps_per_second": 0.339,
"step": 7386
}
],
"logging_steps": 25,
"max_steps": 7386,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.01
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3885829395485184.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}