lora-roberta-large-no-roller / trainer_state.json
anniew666's picture
End of training
cd66947
raw
history blame
39.4 kB
{
"best_metric": 0.6599026308980849,
"best_model_checkpoint": ".exp/lora/lora-roberta-large-no-roller/checkpoint-18544",
"epoch": 14.997573208218736,
"global_step": 23175,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15,
"learning_rate": 0.0001993097497842968,
"loss": 1.2253,
"step": 232
},
{
"epoch": 0.3,
"learning_rate": 0.0003986194995685936,
"loss": 0.8585,
"step": 464
},
{
"epoch": 0.45,
"learning_rate": 0.0005979292493528904,
"loss": 0.8047,
"step": 696
},
{
"epoch": 0.6,
"learning_rate": 0.0007981018119068161,
"loss": 0.7936,
"step": 928
},
{
"epoch": 0.75,
"eval_accuracy": 0.7151125983539839,
"eval_b_acc": 0.5608875787610796,
"eval_f1": 0.5847679854237596,
"eval_f1_anger": 0.5590382138256763,
"eval_f1_disgust": 0.376847290640394,
"eval_f1_fear": 0.6084425036390102,
"eval_f1_joy": 0.7112022832679272,
"eval_f1_neutral": 0.8162122328666176,
"eval_f1_sadness": 0.6324988190836089,
"eval_f1_surprise": 0.3891345546430828,
"eval_loss": 0.7810666561126709,
"eval_micro_f1": 0.7151125983539839,
"eval_prec": 0.6487886243372791,
"eval_prec_anger": 0.5064177362893816,
"eval_prec_disgust": 0.6071428571428571,
"eval_prec_fear": 0.8053949903660886,
"eval_prec_joy": 0.6198694029850746,
"eval_prec_neutral": 0.8561269710398846,
"eval_prec_sadness": 0.6748991935483871,
"eval_prec_surprise": 0.47166921898928027,
"eval_recall": 0.5608875787610796,
"eval_recall_anger": 0.6238620028749401,
"eval_recall_disgust": 0.2732142857142857,
"eval_recall_fear": 0.4888888888888889,
"eval_recall_joy": 0.8341004184100418,
"eval_recall_neutral": 0.7798535486293654,
"eval_recall_sadness": 0.5951111111111111,
"eval_recall_surprise": 0.3311827956989247,
"eval_runtime": 56.4382,
"eval_samples_per_second": 391.827,
"eval_steps_per_second": 24.505,
"step": 1159
},
{
"epoch": 0.75,
"learning_rate": 0.000997411561691113,
"loss": 0.7815,
"step": 1160
},
{
"epoch": 0.9,
"learning_rate": 0.0009895984738372094,
"loss": 0.7825,
"step": 1392
},
{
"epoch": 1.05,
"learning_rate": 0.0009790606831395349,
"loss": 0.7583,
"step": 1624
},
{
"epoch": 1.2,
"learning_rate": 0.0009685683139534885,
"loss": 0.7534,
"step": 1856
},
{
"epoch": 1.35,
"learning_rate": 0.000958030523255814,
"loss": 0.7404,
"step": 2088
},
{
"epoch": 1.5,
"eval_accuracy": 0.7384914533779506,
"eval_b_acc": 0.5694366063947011,
"eval_f1": 0.6007617462780054,
"eval_f1_anger": 0.5731575534903826,
"eval_f1_disgust": 0.3873417721518987,
"eval_f1_fear": 0.6370656370656371,
"eval_f1_joy": 0.7357275406615,
"eval_f1_neutral": 0.8367184035476719,
"eval_f1_sadness": 0.6255825996892802,
"eval_f1_surprise": 0.4097387173396675,
"eval_loss": 0.7121325731277466,
"eval_micro_f1": 0.7384914533779506,
"eval_prec": 0.6663565165984385,
"eval_prec_anger": 0.5220472440944882,
"eval_prec_disgust": 0.6652173913043479,
"eval_prec_fear": 0.7081545064377682,
"eval_prec_joy": 0.7692307692307693,
"eval_prec_neutral": 0.792906370818625,
"eval_prec_sadness": 0.749379652605459,
"eval_prec_surprise": 0.45755968169761274,
"eval_recall": 0.5694366063947011,
"eval_recall_anger": 0.635361763296598,
"eval_recall_disgust": 0.2732142857142857,
"eval_recall_fear": 0.5789473684210527,
"eval_recall_joy": 0.7050209205020921,
"eval_recall_neutral": 0.8856552760045062,
"eval_recall_sadness": 0.5368888888888889,
"eval_recall_surprise": 0.3709677419354839,
"eval_runtime": 56.0841,
"eval_samples_per_second": 394.3,
"eval_steps_per_second": 24.659,
"step": 2318
},
{
"epoch": 1.5,
"learning_rate": 0.0009474927325581396,
"loss": 0.7446,
"step": 2320
},
{
"epoch": 1.65,
"learning_rate": 0.0009370003633720931,
"loss": 0.8041,
"step": 2552
},
{
"epoch": 1.8,
"learning_rate": 0.0009264625726744186,
"loss": 0.7737,
"step": 2784
},
{
"epoch": 1.95,
"learning_rate": 0.0009159247819767442,
"loss": 0.7255,
"step": 3016
},
{
"epoch": 2.1,
"learning_rate": 0.0009053869912790698,
"loss": 0.713,
"step": 3248
},
{
"epoch": 2.25,
"eval_accuracy": 0.7460432305326942,
"eval_b_acc": 0.6190714329338819,
"eval_f1": 0.626920477568903,
"eval_f1_anger": 0.5916555703506436,
"eval_f1_disgust": 0.4567699836867863,
"eval_f1_fear": 0.640675763482781,
"eval_f1_joy": 0.7454035525085696,
"eval_f1_neutral": 0.8395222989363688,
"eval_f1_sadness": 0.6792540792540793,
"eval_f1_surprise": 0.43516209476309226,
"eval_loss": 0.7057798504829407,
"eval_micro_f1": 0.7460432305326943,
"eval_prec": 0.6426986606579812,
"eval_prec_anger": 0.5510541546093427,
"eval_prec_disgust": 0.42042042042042044,
"eval_prec_fear": 0.7207602339181286,
"eval_prec_joy": 0.7402517020837631,
"eval_prec_neutral": 0.8343842729970327,
"eval_prec_sadness": 0.7142156862745098,
"eval_prec_surprise": 0.5178041543026706,
"eval_recall": 0.6190714329338819,
"eval_recall_anger": 0.6387158600862483,
"eval_recall_disgust": 0.5,
"eval_recall_fear": 0.5766081871345029,
"eval_recall_joy": 0.7506276150627615,
"eval_recall_neutral": 0.844723995493804,
"eval_recall_sadness": 0.6475555555555556,
"eval_recall_surprise": 0.37526881720430105,
"eval_runtime": 56.1029,
"eval_samples_per_second": 394.169,
"eval_steps_per_second": 24.651,
"step": 3477
},
{
"epoch": 2.25,
"learning_rate": 0.0008948492005813954,
"loss": 0.7065,
"step": 3480
},
{
"epoch": 2.4,
"learning_rate": 0.000884311409883721,
"loss": 0.7362,
"step": 3712
},
{
"epoch": 2.55,
"learning_rate": 0.0008737736191860465,
"loss": 0.7668,
"step": 3944
},
{
"epoch": 2.7,
"learning_rate": 0.0008632358284883722,
"loss": 0.7673,
"step": 4176
},
{
"epoch": 2.85,
"learning_rate": 0.0008526980377906977,
"loss": 0.7173,
"step": 4408
},
{
"epoch": 3.0,
"eval_accuracy": 0.748213801211902,
"eval_b_acc": 0.5962828887378715,
"eval_f1": 0.6210935912815152,
"eval_f1_anger": 0.5256290773532153,
"eval_f1_disgust": 0.5043069694596711,
"eval_f1_fear": 0.6573780873970868,
"eval_f1_joy": 0.7350898692810458,
"eval_f1_neutral": 0.838420659668848,
"eval_f1_sadness": 0.6803977272727273,
"eval_f1_surprise": 0.4064327485380117,
"eval_loss": 0.6973233222961426,
"eval_micro_f1": 0.748213801211902,
"eval_prec": 0.6831105248010303,
"eval_prec_anger": 0.7473498233215548,
"eval_prec_disgust": 0.4490934449093445,
"eval_prec_fear": 0.7168508287292817,
"eval_prec_joy": 0.7180766161213089,
"eval_prec_neutral": 0.7877362383428241,
"eval_prec_sadness": 0.7279635258358662,
"eval_prec_surprise": 0.634703196347032,
"eval_recall": 0.5962828887378715,
"eval_recall_anger": 0.40536655486344036,
"eval_recall_disgust": 0.575,
"eval_recall_fear": 0.6070175438596491,
"eval_recall_joy": 0.752928870292887,
"eval_recall_neutral": 0.8960758542996621,
"eval_recall_sadness": 0.6386666666666667,
"eval_recall_surprise": 0.2989247311827957,
"eval_runtime": 56.127,
"eval_samples_per_second": 393.999,
"eval_steps_per_second": 24.641,
"step": 4636
},
{
"epoch": 3.0,
"learning_rate": 0.0008421602470930233,
"loss": 0.7184,
"step": 4640
},
{
"epoch": 3.15,
"learning_rate": 0.0008316224563953489,
"loss": 0.7007,
"step": 4872
},
{
"epoch": 3.3,
"learning_rate": 0.0008210846656976745,
"loss": 0.7004,
"step": 5104
},
{
"epoch": 3.45,
"learning_rate": 0.0008105468750000001,
"loss": 0.6998,
"step": 5336
},
{
"epoch": 3.6,
"learning_rate": 0.0008000090843023255,
"loss": 0.6988,
"step": 5568
},
{
"epoch": 3.75,
"eval_accuracy": 0.7445057429682554,
"eval_b_acc": 0.5999589719177421,
"eval_f1": 0.6211744055829362,
"eval_f1_anger": 0.6095856215676485,
"eval_f1_disgust": 0.4340723453908985,
"eval_f1_fear": 0.6228915662650603,
"eval_f1_joy": 0.7373101148573548,
"eval_f1_neutral": 0.8331185874492961,
"eval_f1_sadness": 0.6804733727810651,
"eval_f1_surprise": 0.4307692307692308,
"eval_loss": 0.6958187818527222,
"eval_micro_f1": 0.7445057429682554,
"eval_prec": 0.663456251711611,
"eval_prec_anger": 0.6362688900468995,
"eval_prec_disgust": 0.6262626262626263,
"eval_prec_fear": 0.6422360248447205,
"eval_prec_joy": 0.6615691489361702,
"eval_prec_neutral": 0.8472289624381248,
"eval_prec_sadness": 0.6972947761194029,
"eval_prec_surprise": 0.5333333333333333,
"eval_recall": 0.5999589719177421,
"eval_recall_anger": 0.5850503114518447,
"eval_recall_disgust": 0.33214285714285713,
"eval_recall_fear": 0.6046783625730994,
"eval_recall_joy": 0.8326359832635983,
"eval_recall_neutral": 0.8194705219677056,
"eval_recall_sadness": 0.6644444444444444,
"eval_recall_surprise": 0.36129032258064514,
"eval_runtime": 56.0148,
"eval_samples_per_second": 394.789,
"eval_steps_per_second": 24.69,
"step": 5795
},
{
"epoch": 3.75,
"learning_rate": 0.0007894712936046511,
"loss": 0.6905,
"step": 5800
},
{
"epoch": 3.9,
"learning_rate": 0.0007789335029069767,
"loss": 0.6874,
"step": 6032
},
{
"epoch": 4.05,
"learning_rate": 0.0007683957122093023,
"loss": 0.6806,
"step": 6264
},
{
"epoch": 4.2,
"learning_rate": 0.0007578579215116279,
"loss": 0.6675,
"step": 6496
},
{
"epoch": 4.35,
"learning_rate": 0.0007473201308139535,
"loss": 0.661,
"step": 6728
},
{
"epoch": 4.5,
"eval_accuracy": 0.7542733110246902,
"eval_b_acc": 0.608132558469346,
"eval_f1": 0.6333487463713535,
"eval_f1_anger": 0.6156993096394784,
"eval_f1_disgust": 0.4106463878326997,
"eval_f1_fear": 0.6582781456953642,
"eval_f1_joy": 0.7460507898420317,
"eval_f1_neutral": 0.8415254632871213,
"eval_f1_sadness": 0.6814723421756118,
"eval_f1_surprise": 0.4797687861271676,
"eval_loss": 0.6763387322425842,
"eval_micro_f1": 0.7542733110246903,
"eval_prec": 0.6900758491310965,
"eval_prec_anger": 0.6600877192982456,
"eval_prec_disgust": 0.7074235807860262,
"eval_prec_fear": 0.7587786259541984,
"eval_prec_joy": 0.7144772117962467,
"eval_prec_neutral": 0.8368767988116238,
"eval_prec_sadness": 0.6341370072713356,
"eval_prec_surprise": 0.51875,
"eval_recall": 0.608132558469346,
"eval_recall_anger": 0.5769046478198371,
"eval_recall_disgust": 0.2892857142857143,
"eval_recall_fear": 0.5812865497076023,
"eval_recall_joy": 0.7805439330543933,
"eval_recall_neutral": 0.8462260608336463,
"eval_recall_sadness": 0.7364444444444445,
"eval_recall_surprise": 0.44623655913978494,
"eval_runtime": 56.0547,
"eval_samples_per_second": 394.508,
"eval_steps_per_second": 24.672,
"step": 6954
},
{
"epoch": 4.5,
"learning_rate": 0.000736827761627907,
"loss": 0.6799,
"step": 6960
},
{
"epoch": 4.65,
"learning_rate": 0.0007262899709302326,
"loss": 0.6697,
"step": 7192
},
{
"epoch": 4.8,
"learning_rate": 0.0007157521802325582,
"loss": 0.6735,
"step": 7424
},
{
"epoch": 4.95,
"learning_rate": 0.0007052143895348837,
"loss": 0.6784,
"step": 7656
},
{
"epoch": 5.1,
"learning_rate": 0.0006946765988372094,
"loss": 0.6632,
"step": 7888
},
{
"epoch": 5.25,
"eval_accuracy": 0.7542733110246902,
"eval_b_acc": 0.6177156484929304,
"eval_f1": 0.6385739358409929,
"eval_f1_anger": 0.6169852407452213,
"eval_f1_disgust": 0.4698581560283688,
"eval_f1_fear": 0.6753585397653195,
"eval_f1_joy": 0.7463021524023257,
"eval_f1_neutral": 0.8425508671309573,
"eval_f1_sadness": 0.670199343931365,
"eval_f1_surprise": 0.44876325088339225,
"eval_loss": 0.6744649410247803,
"eval_micro_f1": 0.7542733110246903,
"eval_prec": 0.6671415982006162,
"eval_prec_anger": 0.6231671554252199,
"eval_prec_disgust": 0.4665492957746479,
"eval_prec_fear": 0.7628865979381443,
"eval_prec_joy": 0.7282500497710531,
"eval_prec_neutral": 0.8177962357515243,
"eval_prec_sadness": 0.7752481027437245,
"eval_prec_surprise": 0.49609375,
"eval_recall": 0.6177156484929304,
"eval_recall_anger": 0.610924772400575,
"eval_recall_disgust": 0.4732142857142857,
"eval_recall_fear": 0.6058479532163743,
"eval_recall_joy": 0.7652719665271966,
"eval_recall_neutral": 0.8688509200150206,
"eval_recall_sadness": 0.5902222222222222,
"eval_recall_surprise": 0.4096774193548387,
"eval_runtime": 56.0695,
"eval_samples_per_second": 394.403,
"eval_steps_per_second": 24.666,
"step": 8113
},
{
"epoch": 5.25,
"learning_rate": 0.0006841388081395349,
"loss": 0.6602,
"step": 8120
},
{
"epoch": 5.4,
"learning_rate": 0.0006736464389534884,
"loss": 0.6574,
"step": 8352
},
{
"epoch": 5.56,
"learning_rate": 0.000663108648255814,
"loss": 0.653,
"step": 8584
},
{
"epoch": 5.71,
"learning_rate": 0.0006525708575581395,
"loss": 0.6498,
"step": 8816
},
{
"epoch": 5.86,
"learning_rate": 0.0006420330668604652,
"loss": 0.6427,
"step": 9048
},
{
"epoch": 6.0,
"eval_accuracy": 0.75142443700823,
"eval_b_acc": 0.6305765766002346,
"eval_f1": 0.6403003135406875,
"eval_f1_anger": 0.6199337241906704,
"eval_f1_disgust": 0.4776386404293381,
"eval_f1_fear": 0.6750629722921915,
"eval_f1_joy": 0.7306289881494986,
"eval_f1_neutral": 0.8441443042473787,
"eval_f1_sadness": 0.6788177339901477,
"eval_f1_surprise": 0.4558758314855876,
"eval_loss": 0.6728894710540771,
"eval_micro_f1": 0.75142443700823,
"eval_prec": 0.6606971877116719,
"eval_prec_anger": 0.6623093681917211,
"eval_prec_disgust": 0.478494623655914,
"eval_prec_fear": 0.7312414733969986,
"eval_prec_joy": 0.8023023023023023,
"eval_prec_neutral": 0.8012820512820513,
"eval_prec_sadness": 0.7613259668508288,
"eval_prec_surprise": 0.3879245283018868,
"eval_recall": 0.6305765766002346,
"eval_recall_anger": 0.582654528030666,
"eval_recall_disgust": 0.4767857142857143,
"eval_recall_fear": 0.6269005847953216,
"eval_recall_joy": 0.6707112970711298,
"eval_recall_neutral": 0.8918512955313556,
"eval_recall_sadness": 0.6124444444444445,
"eval_recall_surprise": 0.5526881720430108,
"eval_runtime": 56.4508,
"eval_samples_per_second": 391.739,
"eval_steps_per_second": 24.499,
"step": 9272
},
{
"epoch": 6.01,
"learning_rate": 0.0006314952761627907,
"loss": 0.656,
"step": 9280
},
{
"epoch": 6.16,
"learning_rate": 0.0006209574854651163,
"loss": 0.627,
"step": 9512
},
{
"epoch": 6.31,
"learning_rate": 0.0006104196947674419,
"loss": 0.646,
"step": 9744
},
{
"epoch": 6.46,
"learning_rate": 0.0005998819040697675,
"loss": 0.6438,
"step": 9976
},
{
"epoch": 6.61,
"learning_rate": 0.0005893441133720931,
"loss": 0.6363,
"step": 10208
},
{
"epoch": 6.75,
"eval_accuracy": 0.7578909288233698,
"eval_b_acc": 0.6367461440021368,
"eval_f1": 0.6474798485755483,
"eval_f1_anger": 0.627286753361252,
"eval_f1_disgust": 0.47420634920634924,
"eval_f1_fear": 0.6633416458852867,
"eval_f1_joy": 0.7608476286579212,
"eval_f1_neutral": 0.8410081485692629,
"eval_f1_sadness": 0.6988062442607897,
"eval_f1_surprise": 0.46686217008797654,
"eval_loss": 0.658396303653717,
"eval_micro_f1": 0.7578909288233697,
"eval_prec": 0.663515380429498,
"eval_prec_anger": 0.5808163265306122,
"eval_prec_disgust": 0.5334821428571429,
"eval_prec_fear": 0.7102803738317757,
"eval_prec_joy": 0.7348927875243665,
"eval_prec_neutral": 0.8488905891354246,
"eval_prec_sadness": 0.7226970560303894,
"eval_prec_surprise": 0.5135483870967742,
"eval_recall": 0.6367461440021368,
"eval_recall_anger": 0.6818399616674653,
"eval_recall_disgust": 0.42678571428571427,
"eval_recall_fear": 0.6222222222222222,
"eval_recall_joy": 0.7887029288702929,
"eval_recall_neutral": 0.8332707472775066,
"eval_recall_sadness": 0.6764444444444444,
"eval_recall_surprise": 0.42795698924731185,
"eval_runtime": 55.941,
"eval_samples_per_second": 395.309,
"eval_steps_per_second": 24.722,
"step": 10431
},
{
"epoch": 6.76,
"learning_rate": 0.0005788063226744186,
"loss": 0.6369,
"step": 10440
},
{
"epoch": 6.91,
"learning_rate": 0.0005682685319767443,
"loss": 0.6358,
"step": 10672
},
{
"epoch": 7.06,
"learning_rate": 0.0005577307412790698,
"loss": 0.6334,
"step": 10904
},
{
"epoch": 7.21,
"learning_rate": 0.0005471929505813954,
"loss": 0.6179,
"step": 11136
},
{
"epoch": 7.36,
"learning_rate": 0.000536655159883721,
"loss": 0.6134,
"step": 11368
},
{
"epoch": 7.5,
"eval_accuracy": 0.7634077959663561,
"eval_b_acc": 0.635084721240985,
"eval_f1": 0.6537551153465847,
"eval_f1_anger": 0.6306132303235152,
"eval_f1_disgust": 0.48577235772357713,
"eval_f1_fear": 0.6887914840325611,
"eval_f1_joy": 0.7543015923907236,
"eval_f1_neutral": 0.8475751631005065,
"eval_f1_sadness": 0.6944444444444444,
"eval_f1_surprise": 0.4747875354107649,
"eval_loss": 0.6490016579627991,
"eval_micro_f1": 0.7634077959663561,
"eval_prec": 0.6768287307705253,
"eval_prec_anger": 0.6355231143552311,
"eval_prec_disgust": 0.5636792452830188,
"eval_prec_fear": 0.7412398921832885,
"eval_prec_joy": 0.771029058335154,
"eval_prec_neutral": 0.82444306381468,
"eval_prec_sadness": 0.7000903342366757,
"eval_prec_surprise": 0.5017964071856288,
"eval_recall": 0.635084721240985,
"eval_recall_anger": 0.6257786296118831,
"eval_recall_disgust": 0.42678571428571427,
"eval_recall_fear": 0.6432748538011696,
"eval_recall_joy": 0.7382845188284519,
"eval_recall_neutral": 0.8720428088621855,
"eval_recall_sadness": 0.6888888888888889,
"eval_recall_surprise": 0.4505376344086022,
"eval_runtime": 56.0262,
"eval_samples_per_second": 394.708,
"eval_steps_per_second": 24.685,
"step": 11590
},
{
"epoch": 7.51,
"learning_rate": 0.0005261173691860464,
"loss": 0.6153,
"step": 11600
},
{
"epoch": 7.66,
"learning_rate": 0.0005155795784883721,
"loss": 0.6253,
"step": 11832
},
{
"epoch": 7.81,
"learning_rate": 0.0005050417877906976,
"loss": 0.6252,
"step": 12064
},
{
"epoch": 7.96,
"learning_rate": 0.0004945039970930233,
"loss": 0.6225,
"step": 12296
},
{
"epoch": 8.11,
"learning_rate": 0.00048396620639534884,
"loss": 0.6045,
"step": 12528
},
{
"epoch": 8.25,
"eval_accuracy": 0.7612372252871484,
"eval_b_acc": 0.652548308537905,
"eval_f1": 0.6555027527583773,
"eval_f1_anger": 0.6239253254728567,
"eval_f1_disgust": 0.5019011406844106,
"eval_f1_fear": 0.6824887748556767,
"eval_f1_joy": 0.7568754574924187,
"eval_f1_neutral": 0.846870961786967,
"eval_f1_sadness": 0.6986857825567503,
"eval_f1_surprise": 0.4777718264595608,
"eval_loss": 0.6494194269180298,
"eval_micro_f1": 0.7612372252871484,
"eval_prec": 0.6648498812409536,
"eval_prec_anger": 0.6401209677419355,
"eval_prec_disgust": 0.4370860927152318,
"eval_prec_fear": 0.7556818181818182,
"eval_prec_joy": 0.7566380932469161,
"eval_prec_neutral": 0.8328794480755265,
"eval_prec_sadness": 0.7555555555555555,
"eval_prec_surprise": 0.4759871931696905,
"eval_recall": 0.652548308537905,
"eval_recall_anger": 0.6085289889793962,
"eval_recall_disgust": 0.5892857142857143,
"eval_recall_fear": 0.6222222222222222,
"eval_recall_joy": 0.757112970711297,
"eval_recall_neutral": 0.8613405933158093,
"eval_recall_sadness": 0.6497777777777778,
"eval_recall_surprise": 0.47956989247311826,
"eval_runtime": 56.4204,
"eval_samples_per_second": 391.95,
"eval_steps_per_second": 24.512,
"step": 12749
},
{
"epoch": 8.26,
"learning_rate": 0.00047342841569767444,
"loss": 0.5995,
"step": 12760
},
{
"epoch": 8.41,
"learning_rate": 0.00046289062500000003,
"loss": 0.6077,
"step": 12992
},
{
"epoch": 8.56,
"learning_rate": 0.0004523528343023256,
"loss": 0.6048,
"step": 13224
},
{
"epoch": 8.71,
"learning_rate": 0.00044181504360465116,
"loss": 0.6098,
"step": 13456
},
{
"epoch": 8.86,
"learning_rate": 0.00043127725290697676,
"loss": 0.6139,
"step": 13688
},
{
"epoch": 9.0,
"eval_accuracy": 0.7561273401465135,
"eval_b_acc": 0.6387964114128805,
"eval_f1": 0.6499473605201531,
"eval_f1_anger": 0.63791289711761,
"eval_f1_disgust": 0.48,
"eval_f1_fear": 0.6700443318556049,
"eval_f1_joy": 0.7569511958001167,
"eval_f1_neutral": 0.8374455732946299,
"eval_f1_sadness": 0.6991417304569705,
"eval_f1_surprise": 0.46813579511614056,
"eval_loss": 0.6584597229957581,
"eval_micro_f1": 0.7561273401465135,
"eval_prec": 0.6729729046510193,
"eval_prec_anger": 0.568642160540135,
"eval_prec_disgust": 0.5846153846153846,
"eval_prec_fear": 0.7306629834254144,
"eval_prec_joy": 0.7070468579731203,
"eval_prec_neutral": 0.8639448991814733,
"eval_prec_sadness": 0.7311984473556526,
"eval_prec_surprise": 0.5246995994659546,
"eval_recall": 0.6387964114128805,
"eval_recall_anger": 0.7264015333013896,
"eval_recall_disgust": 0.40714285714285714,
"eval_recall_fear": 0.6187134502923977,
"eval_recall_joy": 0.8144351464435147,
"eval_recall_neutral": 0.812523469770935,
"eval_recall_sadness": 0.6697777777777778,
"eval_recall_surprise": 0.42258064516129035,
"eval_runtime": 56.0752,
"eval_samples_per_second": 394.363,
"eval_steps_per_second": 24.663,
"step": 13908
},
{
"epoch": 9.01,
"learning_rate": 0.0004207394622093023,
"loss": 0.6008,
"step": 13920
},
{
"epoch": 9.16,
"learning_rate": 0.0004102016715116279,
"loss": 0.5747,
"step": 14152
},
{
"epoch": 9.31,
"learning_rate": 0.0003997093023255814,
"loss": 0.5784,
"step": 14384
},
{
"epoch": 9.46,
"learning_rate": 0.000389171511627907,
"loss": 0.5861,
"step": 14616
},
{
"epoch": 9.61,
"learning_rate": 0.0003786337209302326,
"loss": 0.5942,
"step": 14848
},
{
"epoch": 9.75,
"eval_accuracy": 0.7660757890928823,
"eval_b_acc": 0.6435975553792159,
"eval_f1": 0.6605178711530704,
"eval_f1_anger": 0.6503480799461037,
"eval_f1_disgust": 0.4919678714859438,
"eval_f1_fear": 0.6890862944162437,
"eval_f1_joy": 0.7607211979219721,
"eval_f1_neutral": 0.8455292141123762,
"eval_f1_sadness": 0.7070992007522332,
"eval_f1_surprise": 0.47887323943661975,
"eval_loss": 0.6422432065010071,
"eval_micro_f1": 0.7660757890928823,
"eval_prec": 0.6838085930410494,
"eval_prec_anger": 0.6120033812341504,
"eval_prec_disgust": 0.5619266055045872,
"eval_prec_fear": 0.753120665742025,
"eval_prec_joy": 0.7413142743696645,
"eval_prec_neutral": 0.8406644394951744,
"eval_prec_sadness": 0.7504990019960079,
"eval_prec_surprise": 0.5271317829457365,
"eval_recall": 0.6435975553792159,
"eval_recall_anger": 0.6938188787733589,
"eval_recall_disgust": 0.4375,
"eval_recall_fear": 0.6350877192982456,
"eval_recall_joy": 0.7811715481171548,
"eval_recall_neutral": 0.8504506196019527,
"eval_recall_sadness": 0.6684444444444444,
"eval_recall_surprise": 0.43870967741935485,
"eval_runtime": 56.0549,
"eval_samples_per_second": 394.506,
"eval_steps_per_second": 24.672,
"step": 15067
},
{
"epoch": 9.76,
"learning_rate": 0.00036809593023255817,
"loss": 0.584,
"step": 15080
},
{
"epoch": 9.91,
"learning_rate": 0.00035755813953488376,
"loss": 0.5916,
"step": 15312
},
{
"epoch": 10.06,
"learning_rate": 0.0003470203488372093,
"loss": 0.578,
"step": 15544
},
{
"epoch": 10.21,
"learning_rate": 0.0003364825581395349,
"loss": 0.5671,
"step": 15776
},
{
"epoch": 10.36,
"learning_rate": 0.0003259447674418605,
"loss": 0.5798,
"step": 16008
},
{
"epoch": 10.5,
"eval_accuracy": 0.7614181061770824,
"eval_b_acc": 0.6358205520515465,
"eval_f1": 0.6494513520201605,
"eval_f1_anger": 0.6408716922392707,
"eval_f1_disgust": 0.43099273607748184,
"eval_f1_fear": 0.6889428918590523,
"eval_f1_joy": 0.7588158027685157,
"eval_f1_neutral": 0.8438946076116726,
"eval_f1_sadness": 0.6985446985446987,
"eval_f1_surprise": 0.4840970350404312,
"eval_loss": 0.6553025245666504,
"eval_micro_f1": 0.7614181061770824,
"eval_prec": 0.6827663455650473,
"eval_prec_anger": 0.5979253112033195,
"eval_prec_disgust": 0.6691729323308271,
"eval_prec_fear": 0.7168141592920354,
"eval_prec_joy": 0.7338284150869651,
"eval_prec_neutral": 0.8489454683640509,
"eval_prec_sadness": 0.7272727272727273,
"eval_prec_surprise": 0.4854054054054054,
"eval_recall": 0.6358205520515465,
"eval_recall_anger": 0.6904647819837086,
"eval_recall_disgust": 0.31785714285714284,
"eval_recall_fear": 0.6631578947368421,
"eval_recall_joy": 0.7855648535564853,
"eval_recall_neutral": 0.8389034923019152,
"eval_recall_sadness": 0.672,
"eval_recall_surprise": 0.4827956989247312,
"eval_runtime": 56.4554,
"eval_samples_per_second": 391.708,
"eval_steps_per_second": 24.497,
"step": 16226
},
{
"epoch": 10.51,
"learning_rate": 0.0003154069767441861,
"loss": 0.5624,
"step": 16240
},
{
"epoch": 10.66,
"learning_rate": 0.0003048691860465116,
"loss": 0.5667,
"step": 16472
},
{
"epoch": 10.81,
"learning_rate": 0.0002943313953488372,
"loss": 0.5613,
"step": 16704
},
{
"epoch": 10.96,
"learning_rate": 0.00028379360465116276,
"loss": 0.5675,
"step": 16936
},
{
"epoch": 11.11,
"learning_rate": 0.00027325581395348835,
"loss": 0.5513,
"step": 17168
},
{
"epoch": 11.25,
"eval_accuracy": 0.7612372252871484,
"eval_b_acc": 0.6499251376052093,
"eval_f1": 0.655028014245718,
"eval_f1_anger": 0.6530223702998573,
"eval_f1_disgust": 0.4823529411764706,
"eval_f1_fear": 0.6685616827743036,
"eval_f1_joy": 0.7561095298851702,
"eval_f1_neutral": 0.8428858482441872,
"eval_f1_sadness": 0.6970917225950782,
"eval_f1_surprise": 0.4851720047449585,
"eval_loss": 0.6538241505622864,
"eval_micro_f1": 0.7612372252871484,
"eval_prec": 0.6640418571067893,
"eval_prec_anger": 0.6486997635933807,
"eval_prec_disgust": 0.5347826086956522,
"eval_prec_fear": 0.6504424778761062,
"eval_prec_joy": 0.7121464226289518,
"eval_prec_neutral": 0.8594146341463414,
"eval_prec_sadness": 0.7018018018018019,
"eval_prec_surprise": 0.541005291005291,
"eval_recall": 0.6499251376052093,
"eval_recall_anger": 0.6574029707714423,
"eval_recall_disgust": 0.4392857142857143,
"eval_recall_fear": 0.6877192982456141,
"eval_recall_joy": 0.8058577405857741,
"eval_recall_neutral": 0.826980848666917,
"eval_recall_sadness": 0.6924444444444444,
"eval_recall_surprise": 0.4397849462365591,
"eval_runtime": 56.1197,
"eval_samples_per_second": 394.05,
"eval_steps_per_second": 24.644,
"step": 17385
},
{
"epoch": 11.26,
"learning_rate": 0.00026276344476744185,
"loss": 0.5456,
"step": 17400
},
{
"epoch": 11.41,
"learning_rate": 0.00025222565406976744,
"loss": 0.5495,
"step": 17632
},
{
"epoch": 11.56,
"learning_rate": 0.00024168786337209303,
"loss": 0.5578,
"step": 17864
},
{
"epoch": 11.71,
"learning_rate": 0.00023115007267441863,
"loss": 0.5475,
"step": 18096
},
{
"epoch": 11.86,
"learning_rate": 0.0002206122819767442,
"loss": 0.5544,
"step": 18328
},
{
"epoch": 12.0,
"eval_accuracy": 0.7692864248892105,
"eval_b_acc": 0.6473316796627765,
"eval_f1": 0.6599026308980849,
"eval_f1_anger": 0.6526917579799905,
"eval_f1_disgust": 0.4974271012006861,
"eval_f1_fear": 0.6937537901758642,
"eval_f1_joy": 0.7607195147458691,
"eval_f1_neutral": 0.8510657804263121,
"eval_f1_sadness": 0.7018284106891702,
"eval_f1_surprise": 0.4618320610687023,
"eval_loss": 0.6492074131965637,
"eval_micro_f1": 0.7692864248892105,
"eval_prec": 0.6782942019153151,
"eval_prec_anger": 0.6489815253434391,
"eval_prec_disgust": 0.47854785478547857,
"eval_prec_fear": 0.7204030226700252,
"eval_prec_joy": 0.76056043496445,
"eval_prec_neutral": 0.8315864910866254,
"eval_prec_sadness": 0.7425595238095238,
"eval_prec_surprise": 0.5654205607476636,
"eval_recall": 0.6473316796627765,
"eval_recall_anger": 0.6564446574029708,
"eval_recall_disgust": 0.5178571428571429,
"eval_recall_fear": 0.6690058479532164,
"eval_recall_joy": 0.7608786610878661,
"eval_recall_neutral": 0.8714795343597447,
"eval_recall_sadness": 0.6653333333333333,
"eval_recall_surprise": 0.3903225806451613,
"eval_runtime": 56.0752,
"eval_samples_per_second": 394.363,
"eval_steps_per_second": 24.663,
"step": 18544
},
{
"epoch": 12.01,
"learning_rate": 0.00021007449127906976,
"loss": 0.5492,
"step": 18560
},
{
"epoch": 12.16,
"learning_rate": 0.00019953670058139535,
"loss": 0.5325,
"step": 18792
},
{
"epoch": 12.31,
"learning_rate": 0.00018899890988372092,
"loss": 0.5335,
"step": 19024
},
{
"epoch": 12.46,
"learning_rate": 0.00017846111918604651,
"loss": 0.5342,
"step": 19256
},
{
"epoch": 12.61,
"learning_rate": 0.00016796875000000001,
"loss": 0.5229,
"step": 19488
},
{
"epoch": 12.75,
"eval_accuracy": 0.7700551686714299,
"eval_b_acc": 0.6449320699710849,
"eval_f1": 0.6612081678146966,
"eval_f1_anger": 0.6615310544053924,
"eval_f1_disgust": 0.48046875,
"eval_f1_fear": 0.6843769765970904,
"eval_f1_joy": 0.7624681285058644,
"eval_f1_neutral": 0.8504032446039811,
"eval_f1_sadness": 0.7066578773895847,
"eval_f1_surprise": 0.48255114320096265,
"eval_loss": 0.6428395509719849,
"eval_micro_f1": 0.7700551686714299,
"eval_prec": 0.6821742308604415,
"eval_prec_anger": 0.6647314949201741,
"eval_prec_disgust": 0.5301724137931034,
"eval_prec_fear": 0.7451790633608816,
"eval_prec_joy": 0.7438805970149254,
"eval_prec_neutral": 0.8446152421520511,
"eval_prec_sadness": 0.6988265971316818,
"eval_prec_surprise": 0.5478142076502732,
"eval_recall": 0.6449320699710849,
"eval_recall_anger": 0.6583612841399138,
"eval_recall_disgust": 0.4392857142857143,
"eval_recall_fear": 0.632748538011696,
"eval_recall_joy": 0.7820083682008369,
"eval_recall_neutral": 0.8562711227938415,
"eval_recall_sadness": 0.7146666666666667,
"eval_recall_surprise": 0.4311827956989247,
"eval_runtime": 56.2641,
"eval_samples_per_second": 393.039,
"eval_steps_per_second": 24.58,
"step": 19703
},
{
"epoch": 12.76,
"learning_rate": 0.0001574309593023256,
"loss": 0.5282,
"step": 19720
},
{
"epoch": 12.91,
"learning_rate": 0.00014689316860465115,
"loss": 0.5382,
"step": 19952
},
{
"epoch": 13.06,
"learning_rate": 0.00013635537790697674,
"loss": 0.5309,
"step": 20184
},
{
"epoch": 13.21,
"learning_rate": 0.00012581758720930233,
"loss": 0.5091,
"step": 20416
},
{
"epoch": 13.36,
"learning_rate": 0.00011527979651162791,
"loss": 0.5222,
"step": 20648
},
{
"epoch": 13.5,
"eval_accuracy": 0.7656235868680474,
"eval_b_acc": 0.6486004046928688,
"eval_f1": 0.6586089996935094,
"eval_f1_anger": 0.6556036556036556,
"eval_f1_disgust": 0.4864359214218896,
"eval_f1_fear": 0.6754883427851291,
"eval_f1_joy": 0.7605747824327059,
"eval_f1_neutral": 0.8472235272009772,
"eval_f1_sadness": 0.705244122965642,
"eval_f1_surprise": 0.47969264544456647,
"eval_loss": 0.6564837098121643,
"eval_micro_f1": 0.7656235868680473,
"eval_prec": 0.670454025124884,
"eval_prec_anger": 0.6581361661033317,
"eval_prec_disgust": 0.5108055009823183,
"eval_prec_fear": 0.73224043715847,
"eval_prec_joy": 0.7365738925911407,
"eval_prec_neutral": 0.8479405679894677,
"eval_prec_sadness": 0.7175712971481141,
"eval_prec_surprise": 0.4899103139013453,
"eval_recall": 0.6486004046928688,
"eval_recall_anger": 0.6530905606133206,
"eval_recall_disgust": 0.4642857142857143,
"eval_recall_fear": 0.6269005847953216,
"eval_recall_joy": 0.7861924686192469,
"eval_recall_neutral": 0.8465076980848667,
"eval_recall_sadness": 0.6933333333333334,
"eval_recall_surprise": 0.4698924731182796,
"eval_runtime": 56.2079,
"eval_samples_per_second": 393.433,
"eval_steps_per_second": 24.605,
"step": 20862
},
{
"epoch": 13.51,
"learning_rate": 0.00010474200581395349,
"loss": 0.5138,
"step": 20880
},
{
"epoch": 13.66,
"learning_rate": 9.420421511627906e-05,
"loss": 0.5072,
"step": 21112
},
{
"epoch": 13.81,
"learning_rate": 8.366642441860465e-05,
"loss": 0.5158,
"step": 21344
},
{
"epoch": 13.96,
"learning_rate": 7.312863372093023e-05,
"loss": 0.5226,
"step": 21576
},
{
"epoch": 14.11,
"learning_rate": 6.263626453488372e-05,
"loss": 0.4972,
"step": 21808
},
{
"epoch": 14.25,
"eval_accuracy": 0.7672062946549697,
"eval_b_acc": 0.6502239168708824,
"eval_f1": 0.6595929877662392,
"eval_f1_anger": 0.6547147846332945,
"eval_f1_disgust": 0.4893617021276596,
"eval_f1_fear": 0.68,
"eval_f1_joy": 0.7619244697361615,
"eval_f1_neutral": 0.8486122792262405,
"eval_f1_sadness": 0.7050711743772242,
"eval_f1_surprise": 0.47746650426309384,
"eval_loss": 0.6573865413665771,
"eval_micro_f1": 0.7672062946549697,
"eval_prec": 0.6725190183062367,
"eval_prec_anger": 0.6367753623188406,
"eval_prec_disgust": 0.4859154929577465,
"eval_prec_fear": 0.7302013422818792,
"eval_prec_joy": 0.7537359263050154,
"eval_prec_neutral": 0.8447441860465116,
"eval_prec_sadness": 0.7056990204808549,
"eval_prec_surprise": 0.550561797752809,
"eval_recall": 0.6502239168708824,
"eval_recall_anger": 0.6736942980354576,
"eval_recall_disgust": 0.4928571428571429,
"eval_recall_fear": 0.6362573099415205,
"eval_recall_joy": 0.7702928870292887,
"eval_recall_neutral": 0.8525159594442359,
"eval_recall_sadness": 0.7044444444444444,
"eval_recall_surprise": 0.421505376344086,
"eval_runtime": 56.0593,
"eval_samples_per_second": 394.475,
"eval_steps_per_second": 24.67,
"step": 22021
},
{
"epoch": 14.26,
"learning_rate": 5.2098473837209305e-05,
"loss": 0.5053,
"step": 22040
},
{
"epoch": 14.41,
"learning_rate": 4.1560683139534885e-05,
"loss": 0.5027,
"step": 22272
},
{
"epoch": 14.56,
"learning_rate": 3.1022892441860465e-05,
"loss": 0.5008,
"step": 22504
},
{
"epoch": 14.71,
"learning_rate": 2.048510174418605e-05,
"loss": 0.5048,
"step": 22736
},
{
"epoch": 14.86,
"learning_rate": 9.947311046511628e-06,
"loss": 0.5051,
"step": 22968
},
{
"epoch": 15.0,
"step": 23175,
"total_flos": 6.952524009415557e+17,
"train_loss": 0.6324699354120314,
"train_runtime": 16542.718,
"train_samples_per_second": 179.325,
"train_steps_per_second": 1.401
}
],
"max_steps": 23175,
"num_train_epochs": 15,
"total_flos": 6.952524009415557e+17,
"trial_name": null,
"trial_params": null
}