anniew666's picture
End of training
25c46ac
{
"best_metric": 0.7387479859330638,
"best_model_checkpoint": ".exp/lora/lora-roberta-large-no-anger-f4-0927/checkpoint-24588",
"epoch": 24.99237572430619,
"eval_steps": 2049,
"global_step": 40975,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.25,
"learning_rate": 0.00019863347974621767,
"loss": 1.157,
"step": 410
},
{
"epoch": 0.5,
"learning_rate": 0.0003977550024402147,
"loss": 0.8773,
"step": 820
},
{
"epoch": 0.75,
"learning_rate": 0.0005978526110297706,
"loss": 0.8365,
"step": 1230
},
{
"epoch": 1.0,
"learning_rate": 0.0007979502196193266,
"loss": 0.8167,
"step": 1640
},
{
"epoch": 1.25,
"eval_accuracy": 0.7129724645117154,
"eval_b_acc": 0.5271913381858306,
"eval_f1": 0.7029940172494629,
"eval_f1_anger": 0.4622467771639043,
"eval_f1_disgust": 0.3897550111358575,
"eval_f1_fear": 0.4693951466859834,
"eval_f1_joy": 0.7340311547020522,
"eval_f1_neutral": 0.8173319746577467,
"eval_f1_sadness": 0.5948575399583043,
"eval_f1_surprise": 0.4043659043659043,
"eval_loss": 0.7755911946296692,
"eval_micro_f1": 0.7129724645117155,
"eval_prec": 0.7003428461797957,
"eval_prec_anger": 0.602641056422569,
"eval_prec_disgust": 0.41866028708133973,
"eval_prec_fear": 0.5368682684341343,
"eval_prec_joy": 0.7252442996742671,
"eval_prec_neutral": 0.7763002861471133,
"eval_prec_sadness": 0.6123032904148784,
"eval_prec_surprise": 0.4796547472256473,
"eval_recall": 0.7129724645117154,
"eval_recall_anger": 0.37490664675130697,
"eval_recall_disgust": 0.3645833333333333,
"eval_recall_fear": 0.416988416988417,
"eval_recall_joy": 0.7430335391289838,
"eval_recall_neutral": 0.8629432126485171,
"eval_recall_sadness": 0.5783783783783784,
"eval_recall_surprise": 0.3495058400718778,
"eval_runtime": 52.691,
"eval_samples_per_second": 443.871,
"eval_steps_per_second": 13.873,
"step": 2049
},
{
"epoch": 1.25,
"learning_rate": 0.0009980478282088825,
"loss": 0.8037,
"step": 2050
},
{
"epoch": 1.5,
"learning_rate": 0.000989569953244618,
"loss": 0.8023,
"step": 2460
},
{
"epoch": 1.75,
"learning_rate": 0.0009790371474079022,
"loss": 0.7911,
"step": 2870
},
{
"epoch": 2.0,
"learning_rate": 0.0009685043415711864,
"loss": 0.79,
"step": 3280
},
{
"epoch": 2.25,
"learning_rate": 0.0009579972255048041,
"loss": 0.7639,
"step": 3690
},
{
"epoch": 2.5,
"eval_accuracy": 0.7293056268171711,
"eval_b_acc": 0.5661640466626477,
"eval_f1": 0.7224400663459573,
"eval_f1_anger": 0.564935064935065,
"eval_f1_disgust": 0.40478564307078757,
"eval_f1_fear": 0.49217002237136465,
"eval_f1_joy": 0.7486674866748666,
"eval_f1_neutral": 0.8254268594855161,
"eval_f1_sadness": 0.6280878316559926,
"eval_f1_surprise": 0.428341384863124,
"eval_loss": 0.7301676869392395,
"eval_micro_f1": 0.7293056268171713,
"eval_prec": 0.7205685165171505,
"eval_prec_anger": 0.6186666666666667,
"eval_prec_disgust": 0.3881453154875717,
"eval_prec_fear": 0.5851063829787234,
"eval_prec_joy": 0.7360528861657529,
"eval_prec_neutral": 0.796054918317692,
"eval_prec_sadness": 0.6380111524163569,
"eval_prec_surprise": 0.532,
"eval_recall": 0.7293056268171711,
"eval_recall_anger": 0.5197908887229276,
"eval_recall_disgust": 0.42291666666666666,
"eval_recall_fear": 0.4247104247104247,
"eval_recall_joy": 0.7617220090105122,
"eval_recall_neutral": 0.8570493030217982,
"eval_recall_sadness": 0.6184684684684685,
"eval_recall_surprise": 0.3584905660377358,
"eval_runtime": 52.3088,
"eval_samples_per_second": 447.114,
"eval_steps_per_second": 13.975,
"step": 4098
},
{
"epoch": 2.5,
"learning_rate": 0.0009474644196680881,
"loss": 0.7619,
"step": 4100
},
{
"epoch": 2.75,
"learning_rate": 0.0009369316138313723,
"loss": 0.7521,
"step": 4510
},
{
"epoch": 3.0,
"learning_rate": 0.0009263988079946566,
"loss": 0.7603,
"step": 4920
},
{
"epoch": 3.25,
"learning_rate": 0.0009158660021579407,
"loss": 0.7425,
"step": 5330
},
{
"epoch": 3.5,
"learning_rate": 0.0009053331963212249,
"loss": 0.7395,
"step": 5740
},
{
"epoch": 3.75,
"eval_accuracy": 0.7286642722763811,
"eval_b_acc": 0.5792854233134773,
"eval_f1": 0.7270638257323497,
"eval_f1_anger": 0.5326678765880217,
"eval_f1_disgust": 0.4021621621621622,
"eval_f1_fear": 0.5162393162393162,
"eval_f1_joy": 0.7518889745566691,
"eval_f1_neutral": 0.8303328398834822,
"eval_f1_sadness": 0.6280009507962918,
"eval_f1_surprise": 0.46755819712729074,
"eval_loss": 0.7348284721374512,
"eval_micro_f1": 0.7286642722763811,
"eval_prec": 0.7327576856576087,
"eval_prec_anger": 0.6786127167630058,
"eval_prec_disgust": 0.41797752808988764,
"eval_prec_fear": 0.46319018404907975,
"eval_prec_joy": 0.6988677081840332,
"eval_prec_neutral": 0.8480296527506828,
"eval_prec_sadness": 0.6648213387015601,
"eval_prec_surprise": 0.5209713024282561,
"eval_recall": 0.7286642722763811,
"eval_recall_anger": 0.438386855862584,
"eval_recall_disgust": 0.3875,
"eval_recall_fear": 0.583011583011583,
"eval_recall_joy": 0.8136158851993993,
"eval_recall_neutral": 0.8133595284872298,
"eval_recall_sadness": 0.5950450450450451,
"eval_recall_surprise": 0.42407906558849956,
"eval_runtime": 52.2656,
"eval_samples_per_second": 447.483,
"eval_steps_per_second": 13.986,
"step": 6147
},
{
"epoch": 3.75,
"learning_rate": 0.0008948003904845092,
"loss": 0.7441,
"step": 6150
},
{
"epoch": 4.0,
"learning_rate": 0.0008842675846477932,
"loss": 0.7408,
"step": 6560
},
{
"epoch": 4.25,
"learning_rate": 0.0008737347788110774,
"loss": 0.7383,
"step": 6970
},
{
"epoch": 4.5,
"learning_rate": 0.0008632019729743616,
"loss": 0.7479,
"step": 7380
},
{
"epoch": 4.75,
"learning_rate": 0.0008527205466783127,
"loss": 0.789,
"step": 7790
},
{
"epoch": 5.0,
"eval_accuracy": 0.7274670771335727,
"eval_b_acc": 0.55106785419059,
"eval_f1": 0.7180205205088754,
"eval_f1_anger": 0.556758924989972,
"eval_f1_disgust": 0.40292275574112735,
"eval_f1_fear": 0.4922737306843267,
"eval_f1_joy": 0.7450199203187251,
"eval_f1_neutral": 0.8237609262733973,
"eval_f1_sadness": 0.6308104161596496,
"eval_f1_surprise": 0.37617554858934166,
"eval_loss": 0.7419339418411255,
"eval_micro_f1": 0.7274670771335727,
"eval_prec": 0.7206445931565618,
"eval_prec_anger": 0.6013864818024264,
"eval_prec_disgust": 0.40376569037656906,
"eval_prec_fear": 0.5747422680412371,
"eval_prec_joy": 0.6887661141804788,
"eval_prec_neutral": 0.806307113420534,
"eval_prec_sadness": 0.6860772895712017,
"eval_prec_surprise": 0.6224066390041494,
"eval_recall": 0.7274670771335727,
"eval_recall_anger": 0.5182972367438387,
"eval_recall_disgust": 0.40208333333333335,
"eval_recall_fear": 0.4305019305019305,
"eval_recall_joy": 0.8112798264642083,
"eval_recall_neutral": 0.8419870895312939,
"eval_recall_sadness": 0.5837837837837838,
"eval_recall_surprise": 0.2695417789757412,
"eval_runtime": 52.2211,
"eval_samples_per_second": 447.865,
"eval_steps_per_second": 13.998,
"step": 8196
},
{
"epoch": 5.0,
"learning_rate": 0.0008421877408415969,
"loss": 0.7457,
"step": 8200
},
{
"epoch": 5.25,
"learning_rate": 0.000831706314545548,
"loss": 0.7311,
"step": 8610
},
{
"epoch": 5.5,
"learning_rate": 0.0008211735087088321,
"loss": 0.7408,
"step": 9020
},
{
"epoch": 5.75,
"learning_rate": 0.0008106407028721164,
"loss": 0.7309,
"step": 9430
},
{
"epoch": 6.0,
"learning_rate": 0.0008001078970354006,
"loss": 0.7439,
"step": 9840
},
{
"epoch": 6.25,
"eval_accuracy": 0.7207114759705832,
"eval_b_acc": 0.5857766516959649,
"eval_f1": 0.7223601133500003,
"eval_f1_anger": 0.5537190082644629,
"eval_f1_disgust": 0.3732162458836443,
"eval_f1_fear": 0.5119819565830279,
"eval_f1_joy": 0.7459492509935799,
"eval_f1_neutral": 0.8227773982629062,
"eval_f1_sadness": 0.6234614418487817,
"eval_f1_surprise": 0.47541684480547247,
"eval_loss": 0.7608067989349365,
"eval_micro_f1": 0.720711475970583,
"eval_prec": 0.7316542206741192,
"eval_prec_anger": 0.6197964847363552,
"eval_prec_disgust": 0.39443155452436196,
"eval_prec_fear": 0.45559458103361766,
"eval_prec_joy": 0.6881963051755746,
"eval_prec_neutral": 0.8598674145843958,
"eval_prec_sadness": 0.7047132311186826,
"eval_prec_surprise": 0.4535073409461664,
"eval_recall": 0.7207114759705832,
"eval_recall_anger": 0.5003734129947722,
"eval_recall_disgust": 0.3541666666666667,
"eval_recall_fear": 0.5842985842985843,
"eval_recall_joy": 0.8142833305523111,
"eval_recall_neutral": 0.7887547946487042,
"eval_recall_sadness": 0.559009009009009,
"eval_recall_surprise": 0.4995507637017071,
"eval_runtime": 52.2461,
"eval_samples_per_second": 447.651,
"eval_steps_per_second": 13.991,
"step": 10245
},
{
"epoch": 6.25,
"learning_rate": 0.0007895750911986846,
"loss": 0.7377,
"step": 10250
},
{
"epoch": 6.5,
"learning_rate": 0.0007790422853619688,
"loss": 0.7175,
"step": 10660
},
{
"epoch": 6.75,
"learning_rate": 0.0007685094795252531,
"loss": 0.7252,
"step": 11070
},
{
"epoch": 7.0,
"learning_rate": 0.0007579766736885373,
"loss": 0.7264,
"step": 11480
},
{
"epoch": 7.25,
"learning_rate": 0.0007474438678518214,
"loss": 0.712,
"step": 11890
},
{
"epoch": 7.5,
"eval_accuracy": 0.7298187104498033,
"eval_b_acc": 0.5809376473431288,
"eval_f1": 0.7262773858274297,
"eval_f1_anger": 0.5449915110356537,
"eval_f1_disgust": 0.4205128205128206,
"eval_f1_fear": 0.5043103448275862,
"eval_f1_joy": 0.751774155813772,
"eval_f1_neutral": 0.8270924591399369,
"eval_f1_sadness": 0.6288094716071038,
"eval_f1_surprise": 0.4750733137829912,
"eval_loss": 0.7239968180656433,
"eval_micro_f1": 0.7298187104498032,
"eval_prec": 0.7269696751543612,
"eval_prec_anger": 0.6312684365781711,
"eval_prec_disgust": 0.41414141414141414,
"eval_prec_fear": 0.5707317073170731,
"eval_prec_joy": 0.705710102489019,
"eval_prec_neutral": 0.8328590400303548,
"eval_prec_sadness": 0.6125587355830842,
"eval_prec_surprise": 0.5209003215434084,
"eval_recall": 0.7298187104498033,
"eval_recall_anger": 0.479462285287528,
"eval_recall_disgust": 0.4270833333333333,
"eval_recall_fear": 0.4517374517374517,
"eval_recall_joy": 0.8042716502586351,
"eval_recall_neutral": 0.8214051828983067,
"eval_recall_sadness": 0.6459459459459459,
"eval_recall_surprise": 0.4366576819407008,
"eval_runtime": 52.2383,
"eval_samples_per_second": 447.718,
"eval_steps_per_second": 13.994,
"step": 12294
},
{
"epoch": 7.5,
"learning_rate": 0.0007369110620151056,
"loss": 0.7081,
"step": 12300
},
{
"epoch": 7.75,
"learning_rate": 0.0007263782561783898,
"loss": 0.7139,
"step": 12710
},
{
"epoch": 8.0,
"learning_rate": 0.0007158454503416739,
"loss": 0.7194,
"step": 13120
},
{
"epoch": 8.25,
"learning_rate": 0.0007053126445049581,
"loss": 0.6946,
"step": 13530
},
{
"epoch": 8.5,
"learning_rate": 0.0006947798386682424,
"loss": 0.7032,
"step": 13940
},
{
"epoch": 8.75,
"eval_accuracy": 0.7343937061741064,
"eval_b_acc": 0.5832769765478361,
"eval_f1": 0.7316967540687647,
"eval_f1_anger": 0.5795918367346938,
"eval_f1_disgust": 0.3876146788990826,
"eval_f1_fear": 0.5310033821871477,
"eval_f1_joy": 0.7517611539751762,
"eval_f1_neutral": 0.8340448973970528,
"eval_f1_sadness": 0.6301433194637078,
"eval_f1_surprise": 0.45488521089161776,
"eval_loss": 0.7095019817352295,
"eval_micro_f1": 0.7343937061741064,
"eval_prec": 0.7327970959588296,
"eval_prec_anger": 0.639063906390639,
"eval_prec_disgust": 0.43112244897959184,
"eval_prec_fear": 0.4724172517552658,
"eval_prec_joy": 0.7556904400606981,
"eval_prec_neutral": 0.8188209843158464,
"eval_prec_sadness": 0.6471984805318138,
"eval_prec_surprise": 0.5605263157894737,
"eval_recall": 0.7343937061741064,
"eval_recall_anger": 0.5302464525765497,
"eval_recall_disgust": 0.35208333333333336,
"eval_recall_fear": 0.6061776061776062,
"eval_recall_joy": 0.7478725179375939,
"eval_recall_neutral": 0.8498456357002526,
"eval_recall_sadness": 0.6139639639639639,
"eval_recall_surprise": 0.38274932614555257,
"eval_runtime": 52.2132,
"eval_samples_per_second": 447.933,
"eval_steps_per_second": 14.0,
"step": 14343
},
{
"epoch": 8.75,
"learning_rate": 0.0006842470328315265,
"loss": 0.7012,
"step": 14350
},
{
"epoch": 9.0,
"learning_rate": 0.0006737142269948107,
"loss": 0.7012,
"step": 14760
},
{
"epoch": 9.25,
"learning_rate": 0.0006631814211580948,
"loss": 0.6766,
"step": 15170
},
{
"epoch": 9.5,
"learning_rate": 0.0006526486153213791,
"loss": 0.6987,
"step": 15580
},
{
"epoch": 9.75,
"learning_rate": 0.0006421158094846632,
"loss": 0.6972,
"step": 15990
},
{
"epoch": 10.0,
"eval_accuracy": 0.7343081922353344,
"eval_b_acc": 0.5923420613622242,
"eval_f1": 0.7316601301789013,
"eval_f1_anger": 0.5625479662317728,
"eval_f1_disgust": 0.40974729241877256,
"eval_f1_fear": 0.5255474452554744,
"eval_f1_joy": 0.7572113495244833,
"eval_f1_neutral": 0.8305052967094779,
"eval_f1_sadness": 0.6358187485015584,
"eval_f1_surprise": 0.46601941747572817,
"eval_loss": 0.7108047008514404,
"eval_micro_f1": 0.7343081922353344,
"eval_prec": 0.7324880260431258,
"eval_prec_anger": 0.5785319652722968,
"eval_prec_disgust": 0.3614649681528662,
"eval_prec_fear": 0.5714285714285714,
"eval_prec_joy": 0.7157503714710253,
"eval_prec_neutral": 0.8322217003287928,
"eval_prec_sadness": 0.6796514607893388,
"eval_prec_surprise": 0.5402843601895735,
"eval_recall": 0.7343081922353344,
"eval_recall_anger": 0.5474234503360716,
"eval_recall_disgust": 0.47291666666666665,
"eval_recall_fear": 0.4864864864864865,
"eval_recall_joy": 0.8037710662439512,
"eval_recall_neutral": 0.8287959584619703,
"eval_recall_sadness": 0.5972972972972973,
"eval_recall_surprise": 0.40970350404312667,
"eval_runtime": 52.2344,
"eval_samples_per_second": 447.751,
"eval_steps_per_second": 13.995,
"step": 16392
},
{
"epoch": 10.0,
"learning_rate": 0.0006315830036479474,
"loss": 0.689,
"step": 16400
},
{
"epoch": 10.25,
"learning_rate": 0.0006210501978112316,
"loss": 0.678,
"step": 16810
},
{
"epoch": 10.5,
"learning_rate": 0.0006105173919745158,
"loss": 0.6774,
"step": 17220
},
{
"epoch": 10.75,
"learning_rate": 0.0006000102759081334,
"loss": 0.6775,
"step": 17630
},
{
"epoch": 11.0,
"learning_rate": 0.0005894774700714176,
"loss": 0.6859,
"step": 18040
},
{
"epoch": 11.25,
"eval_accuracy": 0.7376432358474432,
"eval_b_acc": 0.5791605614639431,
"eval_f1": 0.7321535509780166,
"eval_f1_anger": 0.573612228479485,
"eval_f1_disgust": 0.4152892561983471,
"eval_f1_fear": 0.5193253689388616,
"eval_f1_joy": 0.7545115121344119,
"eval_f1_neutral": 0.8334647312526087,
"eval_f1_sadness": 0.6374764595103578,
"eval_f1_surprise": 0.4521835268103925,
"eval_loss": 0.7211122512817383,
"eval_micro_f1": 0.7376432358474432,
"eval_prec": 0.7321470081981006,
"eval_prec_anger": 0.6216216216216216,
"eval_prec_disgust": 0.41188524590163933,
"eval_prec_fear": 0.5719814241486069,
"eval_prec_joy": 0.7066880373014717,
"eval_prec_neutral": 0.8263748390656612,
"eval_prec_sadness": 0.6676528599605522,
"eval_prec_surprise": 0.5876436781609196,
"eval_recall": 0.7376432358474432,
"eval_recall_anger": 0.5324869305451829,
"eval_recall_disgust": 0.41875,
"eval_recall_fear": 0.47554697554697556,
"eval_recall_joy": 0.809277490405473,
"eval_recall_neutral": 0.8406773318364674,
"eval_recall_sadness": 0.6099099099099099,
"eval_recall_surprise": 0.3674752920035939,
"eval_runtime": 52.2223,
"eval_samples_per_second": 447.855,
"eval_steps_per_second": 13.998,
"step": 18441
},
{
"epoch": 11.25,
"learning_rate": 0.0005789446642347017,
"loss": 0.6627,
"step": 18450
},
{
"epoch": 11.5,
"learning_rate": 0.0005684118583979859,
"loss": 0.672,
"step": 18860
},
{
"epoch": 11.75,
"learning_rate": 0.0005578790525612702,
"loss": 0.6734,
"step": 19270
},
{
"epoch": 12.0,
"learning_rate": 0.0005473462467245543,
"loss": 0.6741,
"step": 19680
},
{
"epoch": 12.25,
"learning_rate": 0.0005368391306581719,
"loss": 0.6542,
"step": 20090
},
{
"epoch": 12.5,
"eval_accuracy": 0.7347357619291944,
"eval_b_acc": 0.5816682643851953,
"eval_f1": 0.7307386267588237,
"eval_f1_anger": 0.5803607214428858,
"eval_f1_disgust": 0.3860021208907741,
"eval_f1_fear": 0.5130927105449399,
"eval_f1_joy": 0.7583697234352255,
"eval_f1_neutral": 0.8282762773891694,
"eval_f1_sadness": 0.6398268398268399,
"eval_f1_surprise": 0.4600309437854564,
"eval_loss": 0.7143167853355408,
"eval_micro_f1": 0.7347357619291943,
"eval_prec": 0.7293955660159446,
"eval_prec_anger": 0.6262975778546713,
"eval_prec_disgust": 0.3930885529157667,
"eval_prec_fear": 0.5699685534591195,
"eval_prec_joy": 0.735760238506198,
"eval_prec_neutral": 0.820334006239677,
"eval_prec_sadness": 0.6158333333333333,
"eval_prec_surprise": 0.5399515738498789,
"eval_recall": 0.7347357619291944,
"eval_recall_anger": 0.5407020164301718,
"eval_recall_disgust": 0.37916666666666665,
"eval_recall_fear": 0.46653796653796653,
"eval_recall_joy": 0.7824128149507759,
"eval_recall_neutral": 0.8363738422677519,
"eval_recall_sadness": 0.6657657657657657,
"eval_recall_surprise": 0.40071877807726863,
"eval_runtime": 52.2156,
"eval_samples_per_second": 447.912,
"eval_steps_per_second": 14.0,
"step": 20490
},
{
"epoch": 12.5,
"learning_rate": 0.0005263063248214561,
"loss": 0.6562,
"step": 20500
},
{
"epoch": 12.75,
"learning_rate": 0.0005157735189847404,
"loss": 0.6563,
"step": 20910
},
{
"epoch": 13.0,
"learning_rate": 0.0005052407131480245,
"loss": 0.6569,
"step": 21320
},
{
"epoch": 13.25,
"learning_rate": 0.0004947079073113087,
"loss": 0.6391,
"step": 21730
},
{
"epoch": 13.5,
"learning_rate": 0.0004841751014745928,
"loss": 0.6463,
"step": 22140
},
{
"epoch": 13.75,
"eval_accuracy": 0.736916367367881,
"eval_b_acc": 0.5947417537959515,
"eval_f1": 0.7353543182480966,
"eval_f1_anger": 0.5885183911997249,
"eval_f1_disgust": 0.3927648578811369,
"eval_f1_fear": 0.5167693360711841,
"eval_f1_joy": 0.7609590699927343,
"eval_f1_neutral": 0.833475661827498,
"eval_f1_sadness": 0.634156820622986,
"eval_f1_surprise": 0.4865919063871283,
"eval_loss": 0.7021653056144714,
"eval_micro_f1": 0.736916367367881,
"eval_prec": 0.7366478429202861,
"eval_prec_anger": 0.5452229299363057,
"eval_prec_disgust": 0.5170068027210885,
"eval_prec_fear": 0.5519005847953217,
"eval_prec_joy": 0.7370972786987801,
"eval_prec_neutral": 0.8455096736933295,
"eval_prec_sadness": 0.6061601642710472,
"eval_prec_surprise": 0.5319829424307037,
"eval_recall": 0.736916367367881,
"eval_recall_anger": 0.6392830470500374,
"eval_recall_disgust": 0.31666666666666665,
"eval_recall_fear": 0.48584298584298585,
"eval_recall_joy": 0.7864174870682463,
"eval_recall_neutral": 0.8217793993825429,
"eval_recall_sadness": 0.6648648648648648,
"eval_recall_surprise": 0.44833782569631625,
"eval_runtime": 52.3587,
"eval_samples_per_second": 446.688,
"eval_steps_per_second": 13.961,
"step": 22539
},
{
"epoch": 13.75,
"learning_rate": 0.00047364229563787706,
"loss": 0.6502,
"step": 22550
},
{
"epoch": 14.0,
"learning_rate": 0.0004631094898011612,
"loss": 0.6445,
"step": 22960
},
{
"epoch": 14.25,
"learning_rate": 0.00045260237373477883,
"loss": 0.6274,
"step": 23370
},
{
"epoch": 14.5,
"learning_rate": 0.000442069567898063,
"loss": 0.6373,
"step": 23780
},
{
"epoch": 14.75,
"learning_rate": 0.0004315367620613472,
"loss": 0.6333,
"step": 24190
},
{
"epoch": 15.0,
"eval_accuracy": 0.7404651958269198,
"eval_b_acc": 0.598152273776674,
"eval_f1": 0.7387479859330638,
"eval_f1_anger": 0.594402837997635,
"eval_f1_disgust": 0.4209328782707622,
"eval_f1_fear": 0.5314520870076425,
"eval_f1_joy": 0.758746779689188,
"eval_f1_neutral": 0.8385366079274779,
"eval_f1_sadness": 0.6361726954492415,
"eval_f1_surprise": 0.4774640911342249,
"eval_loss": 0.7106355428695679,
"eval_micro_f1": 0.7404651958269197,
"eval_prec": 0.7386648012356265,
"eval_prec_anger": 0.6293823038397329,
"eval_prec_disgust": 0.46365914786967416,
"eval_prec_fear": 0.48917748917748916,
"eval_prec_joy": 0.7557947019867549,
"eval_prec_neutral": 0.8292169776802049,
"eval_prec_sadness": 0.660048426150121,
"eval_prec_surprise": 0.5320088300220751,
"eval_recall": 0.7404651958269198,
"eval_recall_anger": 0.5631067961165048,
"eval_recall_disgust": 0.3854166666666667,
"eval_recall_fear": 0.5817245817245817,
"eval_recall_joy": 0.7617220090105122,
"eval_recall_neutral": 0.8480681074001309,
"eval_recall_sadness": 0.6139639639639639,
"eval_recall_surprise": 0.4330637915543576,
"eval_runtime": 52.1895,
"eval_samples_per_second": 448.136,
"eval_steps_per_second": 14.007,
"step": 24588
},
{
"epoch": 15.0,
"learning_rate": 0.00042100395622463136,
"loss": 0.6432,
"step": 24600
},
{
"epoch": 15.25,
"learning_rate": 0.00041047115038791553,
"loss": 0.6199,
"step": 25010
},
{
"epoch": 15.5,
"learning_rate": 0.0003999383445511997,
"loss": 0.6174,
"step": 25420
},
{
"epoch": 15.75,
"learning_rate": 0.00038940553871448394,
"loss": 0.6308,
"step": 25830
},
{
"epoch": 16.0,
"learning_rate": 0.00037887273287776806,
"loss": 0.6184,
"step": 26240
},
{
"epoch": 16.25,
"eval_accuracy": 0.7337523516333162,
"eval_b_acc": 0.6077119026145958,
"eval_f1": 0.7348413799234946,
"eval_f1_anger": 0.5841816758026626,
"eval_f1_disgust": 0.396917148362235,
"eval_f1_fear": 0.5457218465157306,
"eval_f1_joy": 0.7586152386974392,
"eval_f1_neutral": 0.8300653594771242,
"eval_f1_sadness": 0.6336822074215033,
"eval_f1_surprise": 0.48513449740443604,
"eval_loss": 0.719868540763855,
"eval_micro_f1": 0.7337523516333162,
"eval_prec": 0.7388716422973962,
"eval_prec_anger": 0.6139917695473252,
"eval_prec_disgust": 0.36917562724014336,
"eval_prec_fear": 0.5024363833243097,
"eval_prec_joy": 0.7206787805976873,
"eval_prec_neutral": 0.8534440162071351,
"eval_prec_sadness": 0.6713709677419355,
"eval_prec_surprise": 0.510934393638171,
"eval_recall": 0.7337523516333162,
"eval_recall_anger": 0.5571321882001493,
"eval_recall_disgust": 0.42916666666666664,
"eval_recall_fear": 0.5971685971685972,
"eval_recall_joy": 0.8007675621558485,
"eval_recall_neutral": 0.807933389465806,
"eval_recall_sadness": 0.6,
"eval_recall_surprise": 0.4618149146451033,
"eval_runtime": 52.0741,
"eval_samples_per_second": 449.129,
"eval_steps_per_second": 14.038,
"step": 26637
},
{
"epoch": 16.25,
"learning_rate": 0.00036833992704105224,
"loss": 0.6063,
"step": 26650
},
{
"epoch": 16.51,
"learning_rate": 0.00035780712120433647,
"loss": 0.6049,
"step": 27060
},
{
"epoch": 16.76,
"learning_rate": 0.0003472743153676206,
"loss": 0.611,
"step": 27470
},
{
"epoch": 17.01,
"learning_rate": 0.0003367671993012383,
"loss": 0.6121,
"step": 27880
},
{
"epoch": 17.26,
"learning_rate": 0.0003262343934645224,
"loss": 0.5916,
"step": 28290
},
{
"epoch": 17.5,
"eval_accuracy": 0.736788096459723,
"eval_b_acc": 0.6002649432660556,
"eval_f1": 0.7362620116350573,
"eval_f1_anger": 0.5784499054820416,
"eval_f1_disgust": 0.39246778989098113,
"eval_f1_fear": 0.5149572649572649,
"eval_f1_joy": 0.7636186770428015,
"eval_f1_neutral": 0.8366824644549764,
"eval_f1_sadness": 0.6251845602193629,
"eval_f1_surprise": 0.4932147870846982,
"eval_loss": 0.7219593524932861,
"eval_micro_f1": 0.736788096459723,
"eval_prec": 0.7375843989348974,
"eval_prec_anger": 0.5857580398162328,
"eval_prec_disgust": 0.3742911153119093,
"eval_prec_fear": 0.5765550239234449,
"eval_prec_joy": 0.7425508434494719,
"eval_prec_neutral": 0.8478532321582941,
"eval_prec_sadness": 0.5878619595398651,
"eval_prec_surprise": 0.5146484375,
"eval_recall": 0.736788096459723,
"eval_recall_anger": 0.5713218820014937,
"eval_recall_disgust": 0.4125,
"eval_recall_fear": 0.46525096525096526,
"eval_recall_joy": 0.7859169030535625,
"eval_recall_neutral": 0.8258022265880812,
"eval_recall_sadness": 0.6675675675675675,
"eval_recall_surprise": 0.47349505840071876,
"eval_runtime": 52.1004,
"eval_samples_per_second": 448.902,
"eval_steps_per_second": 14.031,
"step": 28686
},
{
"epoch": 17.51,
"learning_rate": 0.0003157015876278066,
"loss": 0.6019,
"step": 28700
},
{
"epoch": 17.76,
"learning_rate": 0.0003051687817910908,
"loss": 0.5998,
"step": 29110
},
{
"epoch": 18.01,
"learning_rate": 0.00029463597595437495,
"loss": 0.5937,
"step": 29520
},
{
"epoch": 18.26,
"learning_rate": 0.0002841031701176591,
"loss": 0.5805,
"step": 29930
},
{
"epoch": 18.51,
"learning_rate": 0.00027357036428094335,
"loss": 0.5823,
"step": 30340
},
{
"epoch": 18.75,
"eval_accuracy": 0.7375577219086711,
"eval_b_acc": 0.5959965915979468,
"eval_f1": 0.7364086067599112,
"eval_f1_anger": 0.5850769838136597,
"eval_f1_disgust": 0.3828382838283828,
"eval_f1_fear": 0.5406240345999382,
"eval_f1_joy": 0.7610117406035773,
"eval_f1_neutral": 0.8328186612190602,
"eval_f1_sadness": 0.6353655687923382,
"eval_f1_surprise": 0.48747591522157996,
"eval_loss": 0.7228219509124756,
"eval_micro_f1": 0.737557721908671,
"eval_prec": 0.7374470363297007,
"eval_prec_anger": 0.6206030150753769,
"eval_prec_disgust": 0.40559440559440557,
"eval_prec_fear": 0.5199049316696376,
"eval_prec_joy": 0.7209614810391162,
"eval_prec_neutral": 0.846042471042471,
"eval_prec_sadness": 0.6598738476467734,
"eval_prec_surprise": 0.5254413291796469,
"eval_recall": 0.7375577219086711,
"eval_recall_anger": 0.5533980582524272,
"eval_recall_disgust": 0.3625,
"eval_recall_fear": 0.5630630630630631,
"eval_recall_joy": 0.8057734023026865,
"eval_recall_neutral": 0.8200018710824212,
"eval_recall_sadness": 0.6126126126126126,
"eval_recall_surprise": 0.4546271338724169,
"eval_runtime": 52.2209,
"eval_samples_per_second": 447.867,
"eval_steps_per_second": 13.998,
"step": 30735
},
{
"epoch": 18.76,
"learning_rate": 0.00026306324821456095,
"loss": 0.5816,
"step": 30750
},
{
"epoch": 19.01,
"learning_rate": 0.0002525304423778452,
"loss": 0.5868,
"step": 31160
},
{
"epoch": 19.26,
"learning_rate": 0.00024199763654112933,
"loss": 0.5698,
"step": 31570
},
{
"epoch": 19.51,
"learning_rate": 0.0002314648307044135,
"loss": 0.5696,
"step": 31980
},
{
"epoch": 19.76,
"learning_rate": 0.0002209320248676977,
"loss": 0.5728,
"step": 32390
},
{
"epoch": 20.0,
"eval_accuracy": 0.7344364631434924,
"eval_b_acc": 0.6090238361567221,
"eval_f1": 0.7349132691412003,
"eval_f1_anger": 0.5850591715976332,
"eval_f1_disgust": 0.4091816367265469,
"eval_f1_fear": 0.5293729372937294,
"eval_f1_joy": 0.760131084645512,
"eval_f1_neutral": 0.8284622731614136,
"eval_f1_sadness": 0.6423658872077029,
"eval_f1_surprise": 0.49303996407723394,
"eval_loss": 0.7313103675842285,
"eval_micro_f1": 0.7344364631434924,
"eval_prec": 0.7365301337731266,
"eval_prec_anger": 0.5794871794871795,
"eval_prec_disgust": 0.39272030651340994,
"eval_prec_fear": 0.5433604336043361,
"eval_prec_joy": 0.7295182571340902,
"eval_prec_neutral": 0.8461613501121842,
"eval_prec_sadness": 0.65406162464986,
"eval_prec_surprise": 0.49281867145421904,
"eval_recall": 0.7344364631434924,
"eval_recall_anger": 0.590739357729649,
"eval_recall_disgust": 0.4270833333333333,
"eval_recall_fear": 0.5160875160875161,
"eval_recall_joy": 0.7934256632738195,
"eval_recall_neutral": 0.8114884460660492,
"eval_recall_sadness": 0.6310810810810811,
"eval_recall_surprise": 0.49326145552560646,
"eval_runtime": 53.2758,
"eval_samples_per_second": 438.999,
"eval_steps_per_second": 13.721,
"step": 32784
},
{
"epoch": 20.01,
"learning_rate": 0.00021039921903098186,
"loss": 0.5687,
"step": 32800
},
{
"epoch": 20.26,
"learning_rate": 0.0001998921029645995,
"loss": 0.5589,
"step": 33210
},
{
"epoch": 20.51,
"learning_rate": 0.00018935929712788369,
"loss": 0.5561,
"step": 33620
},
{
"epoch": 20.76,
"learning_rate": 0.00017882649129116783,
"loss": 0.5543,
"step": 34030
},
{
"epoch": 21.01,
"learning_rate": 0.00016829368545445204,
"loss": 0.5562,
"step": 34440
},
{
"epoch": 21.25,
"eval_accuracy": 0.7375577219086711,
"eval_b_acc": 0.5994500729257896,
"eval_f1": 0.7366274505530668,
"eval_f1_anger": 0.5735234215885947,
"eval_f1_disgust": 0.4092276830491474,
"eval_f1_fear": 0.5332476710568583,
"eval_f1_joy": 0.764285140239492,
"eval_f1_neutral": 0.8349395313681028,
"eval_f1_sadness": 0.625414364640884,
"eval_f1_surprise": 0.4867469879518072,
"eval_loss": 0.7413733005523682,
"eval_micro_f1": 0.737557721908671,
"eval_prec": 0.7371596076951062,
"eval_prec_anger": 0.6308243727598566,
"eval_prec_disgust": 0.3945841392649903,
"eval_prec_fear": 0.5323925593329057,
"eval_prec_joy": 0.7372093023255814,
"eval_prec_neutral": 0.8433056589369214,
"eval_prec_sadness": 0.613882863340564,
"eval_prec_surprise": 0.524948024948025,
"eval_recall": 0.7375577219086711,
"eval_recall_anger": 0.5257654966392831,
"eval_recall_disgust": 0.425,
"eval_recall_fear": 0.5341055341055341,
"eval_recall_joy": 0.7934256632738195,
"eval_recall_neutral": 0.8267377677986716,
"eval_recall_sadness": 0.6373873873873874,
"eval_recall_surprise": 0.4537286612758311,
"eval_runtime": 56.258,
"eval_samples_per_second": 415.728,
"eval_steps_per_second": 12.994,
"step": 34833
},
{
"epoch": 21.26,
"learning_rate": 0.00015776087961773621,
"loss": 0.5488,
"step": 34850
},
{
"epoch": 21.51,
"learning_rate": 0.00014722807378102042,
"loss": 0.5439,
"step": 35260
},
{
"epoch": 21.76,
"learning_rate": 0.0001366952679443046,
"loss": 0.5457,
"step": 35670
},
{
"epoch": 22.01,
"learning_rate": 0.00012616246210758874,
"loss": 0.5452,
"step": 36080
},
{
"epoch": 22.26,
"learning_rate": 0.00011562965627087293,
"loss": 0.5348,
"step": 36490
},
{
"epoch": 22.5,
"eval_accuracy": 0.737001881306653,
"eval_b_acc": 0.6016861275031393,
"eval_f1": 0.7364691206284374,
"eval_f1_anger": 0.5868352547415396,
"eval_f1_disgust": 0.39747634069400634,
"eval_f1_fear": 0.5283998701720221,
"eval_f1_joy": 0.763428933607986,
"eval_f1_neutral": 0.8322205265165968,
"eval_f1_sadness": 0.6372369624885635,
"eval_f1_surprise": 0.48638318203535597,
"eval_loss": 0.7397785782814026,
"eval_micro_f1": 0.7370018813066531,
"eval_prec": 0.73744814726634,
"eval_prec_anger": 0.5844444444444444,
"eval_prec_disgust": 0.4012738853503185,
"eval_prec_fear": 0.5330713817943681,
"eval_prec_joy": 0.7268064564791069,
"eval_prec_neutral": 0.8488179784025683,
"eval_prec_sadness": 0.6473048327137546,
"eval_prec_surprise": 0.5193877551020408,
"eval_recall": 0.737001881306653,
"eval_recall_anger": 0.5892457057505601,
"eval_recall_disgust": 0.39375,
"eval_recall_fear": 0.5238095238095238,
"eval_recall_joy": 0.8039379275821792,
"eval_recall_neutral": 0.8162597062400598,
"eval_recall_sadness": 0.6274774774774775,
"eval_recall_surprise": 0.4573225516621743,
"eval_runtime": 54.191,
"eval_samples_per_second": 431.585,
"eval_steps_per_second": 13.489,
"step": 36882
},
{
"epoch": 22.51,
"learning_rate": 0.00010509685043415712,
"loss": 0.5275,
"step": 36900
},
{
"epoch": 22.76,
"learning_rate": 9.456404459744131e-05,
"loss": 0.5375,
"step": 37310
},
{
"epoch": 23.01,
"learning_rate": 8.403123876072547e-05,
"loss": 0.5249,
"step": 37720
},
{
"epoch": 23.26,
"learning_rate": 7.352412269434311e-05,
"loss": 0.5238,
"step": 38130
},
{
"epoch": 23.51,
"learning_rate": 6.29913168576273e-05,
"loss": 0.5202,
"step": 38540
},
{
"epoch": 23.75,
"eval_accuracy": 0.7389259449290234,
"eval_b_acc": 0.6013150721994661,
"eval_f1": 0.738139896893294,
"eval_f1_anger": 0.5870646766169154,
"eval_f1_disgust": 0.3953488372093023,
"eval_f1_fear": 0.5318255250403877,
"eval_f1_joy": 0.7646298092466861,
"eval_f1_neutral": 0.8346932037919161,
"eval_f1_sadness": 0.6373725934314837,
"eval_f1_surprise": 0.4868667917448405,
"eval_loss": 0.7423349618911743,
"eval_micro_f1": 0.7389259449290234,
"eval_prec": 0.7379281962820202,
"eval_prec_anger": 0.6020408163265306,
"eval_prec_disgust": 0.4012875536480687,
"eval_prec_fear": 0.5340687865022713,
"eval_prec_joy": 0.7414955322150807,
"eval_prec_neutral": 0.8416397184706106,
"eval_prec_sadness": 0.6410022779043281,
"eval_prec_surprise": 0.5093228655544652,
"eval_recall": 0.7389259449290234,
"eval_recall_anger": 0.5728155339805825,
"eval_recall_disgust": 0.38958333333333334,
"eval_recall_fear": 0.5296010296010296,
"eval_recall_joy": 0.7892541298181212,
"eval_recall_neutral": 0.8278604172513799,
"eval_recall_sadness": 0.6337837837837837,
"eval_recall_surprise": 0.46630727762803237,
"eval_runtime": 54.5174,
"eval_samples_per_second": 429.001,
"eval_steps_per_second": 13.409,
"step": 38931
},
{
"epoch": 23.76,
"learning_rate": 5.245851102091148e-05,
"loss": 0.5257,
"step": 38950
},
{
"epoch": 24.01,
"learning_rate": 4.1925705184195654e-05,
"loss": 0.5132,
"step": 39360
},
{
"epoch": 24.26,
"learning_rate": 3.139289934747983e-05,
"loss": 0.5149,
"step": 39770
},
{
"epoch": 24.51,
"learning_rate": 2.0860093510764016e-05,
"loss": 0.5047,
"step": 40180
},
{
"epoch": 24.76,
"learning_rate": 1.0352977444381647e-05,
"loss": 0.52,
"step": 40590
},
{
"epoch": 24.99,
"step": 40975,
"total_flos": 1.2293541171245507e+18,
"train_loss": 0.6590935281284558,
"train_runtime": 28744.9325,
"train_samples_per_second": 182.51,
"train_steps_per_second": 1.425
}
],
"logging_steps": 410,
"max_steps": 40975,
"num_train_epochs": 25,
"save_steps": 4098,
"total_flos": 1.2293541171245507e+18,
"trial_name": null,
"trial_params": null
}