lora-roberta-large-no-ed / trainer_state.json
anniew666's picture
End of training
b27cd81
{
"best_metric": 0.6206372407316966,
"best_model_checkpoint": ".exp/lora/lora-roberta-large-no-ed/checkpoint-26370",
"epoch": 19.996587613035317,
"global_step": 29300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2,
"learning_rate": 0.0001993174061433447,
"loss": 1.1563,
"step": 293
},
{
"epoch": 0.4,
"learning_rate": 0.0003993174061433447,
"loss": 0.843,
"step": 586
},
{
"epoch": 0.6,
"learning_rate": 0.0005993174061433447,
"loss": 0.8076,
"step": 879
},
{
"epoch": 0.8,
"learning_rate": 0.0007986348122866894,
"loss": 0.7841,
"step": 1172
},
{
"epoch": 1.0,
"learning_rate": 0.000997269624573379,
"loss": 0.7938,
"step": 1465
},
{
"epoch": 1.0,
"eval_accuracy": 0.7256572541382668,
"eval_b_acc": 0.4993304744933974,
"eval_f1": 0.5432686921853633,
"eval_f1_anger": 0.4929859719438877,
"eval_f1_disgust": 0.35524475524475524,
"eval_f1_fear": 0.5487421383647799,
"eval_f1_joy": 0.7036857419980601,
"eval_f1_neutral": 0.8260165373795926,
"eval_f1_sadness": 0.5789971617786188,
"eval_f1_surprise": 0.2972085385878489,
"eval_loss": 0.7589048147201538,
"eval_micro_f1": 0.7256572541382668,
"eval_prec": 0.6232926407057092,
"eval_prec_anger": 0.6222596964586846,
"eval_prec_disgust": 0.5358649789029536,
"eval_prec_fear": 0.5925297113752123,
"eval_prec_joy": 0.7258629314657329,
"eval_prec_neutral": 0.7564402810304449,
"eval_prec_sadness": 0.7149532710280374,
"eval_prec_surprise": 0.4151376146788991,
"eval_recall": 0.4993304744933974,
"eval_recall_anger": 0.4081858407079646,
"eval_recall_disgust": 0.26569037656903766,
"eval_recall_fear": 0.5109809663250366,
"eval_recall_joy": 0.6828235294117647,
"eval_recall_neutral": 0.9096883214419828,
"eval_recall_sadness": 0.4864864864864865,
"eval_recall_surprise": 0.23145780051150894,
"eval_runtime": 46.5427,
"eval_samples_per_second": 441.315,
"eval_steps_per_second": 13.794,
"step": 1465
},
{
"epoch": 1.2,
"learning_rate": 0.0009896173881803485,
"loss": 0.9272,
"step": 1758
},
{
"epoch": 1.4,
"learning_rate": 0.0009790910723908748,
"loss": 0.8827,
"step": 2051
},
{
"epoch": 1.6,
"learning_rate": 0.0009685647566014011,
"loss": 0.8217,
"step": 2344
},
{
"epoch": 1.8,
"learning_rate": 0.0009580384408119275,
"loss": 0.7703,
"step": 2637
},
{
"epoch": 2.0,
"learning_rate": 0.0009475480510149093,
"loss": 0.7546,
"step": 2930
},
{
"epoch": 2.0,
"eval_accuracy": 0.7242940603700098,
"eval_b_acc": 0.5498815920183304,
"eval_f1": 0.5735049733331309,
"eval_f1_anger": 0.5553202752779248,
"eval_f1_disgust": 0.3609226594301221,
"eval_f1_fear": 0.5940274414850686,
"eval_f1_joy": 0.6989024028478196,
"eval_f1_neutral": 0.8265419298837825,
"eval_f1_sadness": 0.6172381835032437,
"eval_f1_surprise": 0.3615819209039548,
"eval_loss": 0.7481706142425537,
"eval_micro_f1": 0.7242940603700097,
"eval_prec": 0.6272234980815083,
"eval_prec_anger": 0.5324873096446701,
"eval_prec_disgust": 0.5135135135135135,
"eval_prec_fear": 0.6618705035971223,
"eval_prec_joy": 0.6027630905679686,
"eval_prec_neutral": 0.8497768963807635,
"eval_prec_sadness": 0.74,
"eval_prec_surprise": 0.49015317286652077,
"eval_recall": 0.5498815920183304,
"eval_recall_anger": 0.5801991150442478,
"eval_recall_disgust": 0.27824267782426776,
"eval_recall_fear": 0.5387994143484627,
"eval_recall_joy": 0.8315294117647059,
"eval_recall_neutral": 0.804543747653023,
"eval_recall_sadness": 0.5294117647058824,
"eval_recall_surprise": 0.2864450127877238,
"eval_runtime": 46.047,
"eval_samples_per_second": 446.066,
"eval_steps_per_second": 13.942,
"step": 2930
},
{
"epoch": 2.2,
"learning_rate": 0.0009370217352254357,
"loss": 0.7432,
"step": 3223
},
{
"epoch": 2.4,
"learning_rate": 0.0009265313454284174,
"loss": 0.737,
"step": 3516
},
{
"epoch": 2.6,
"learning_rate": 0.0009160050296389439,
"loss": 0.7192,
"step": 3809
},
{
"epoch": 2.8,
"learning_rate": 0.0009054787138494701,
"loss": 0.7207,
"step": 4102
},
{
"epoch": 3.0,
"learning_rate": 0.0008949523980599964,
"loss": 0.7289,
"step": 4395
},
{
"epoch": 3.0,
"eval_accuracy": 0.7320837390457644,
"eval_b_acc": 0.5839323096679138,
"eval_f1": 0.5984237846360054,
"eval_f1_anger": 0.5667558727326791,
"eval_f1_disgust": 0.44855967078189296,
"eval_f1_fear": 0.5956375838926176,
"eval_f1_joy": 0.7127241855035551,
"eval_f1_neutral": 0.8253590792352327,
"eval_f1_sadness": 0.641439534268325,
"eval_f1_surprise": 0.39849056603773586,
"eval_loss": 0.729333221912384,
"eval_micro_f1": 0.7320837390457644,
"eval_prec": 0.6234201141460577,
"eval_prec_anger": 0.6128617363344051,
"eval_prec_disgust": 0.44129554655870445,
"eval_prec_fear": 0.6974459724950884,
"eval_prec_joy": 0.6491397641600618,
"eval_prec_neutral": 0.8364179679969154,
"eval_prec_sadness": 0.6405919661733616,
"eval_prec_surprise": 0.4861878453038674,
"eval_recall": 0.5839323096679138,
"eval_recall_anger": 0.5271017699115044,
"eval_recall_disgust": 0.4560669456066946,
"eval_recall_fear": 0.5197657393850659,
"eval_recall_joy": 0.7901176470588235,
"eval_recall_neutral": 0.8145888096132182,
"eval_recall_sadness": 0.6422893481717011,
"eval_recall_surprise": 0.3375959079283887,
"eval_runtime": 46.166,
"eval_samples_per_second": 444.916,
"eval_steps_per_second": 13.906,
"step": 4395
},
{
"epoch": 3.2,
"learning_rate": 0.0008844260822705228,
"loss": 0.7017,
"step": 4688
},
{
"epoch": 3.4,
"learning_rate": 0.0008738997664810491,
"loss": 0.7116,
"step": 4981
},
{
"epoch": 3.6,
"learning_rate": 0.0008633734506915754,
"loss": 0.7143,
"step": 5274
},
{
"epoch": 3.8,
"learning_rate": 0.0008528471349021016,
"loss": 0.7218,
"step": 5567
},
{
"epoch": 4.0,
"learning_rate": 0.000842320819112628,
"loss": 0.7076,
"step": 5860
},
{
"epoch": 4.0,
"eval_accuracy": 0.7466407010710808,
"eval_b_acc": 0.5649303370058901,
"eval_f1": 0.5972285504575797,
"eval_f1_anger": 0.5746792544178165,
"eval_f1_disgust": 0.3785166240409207,
"eval_f1_fear": 0.6040515653775322,
"eval_f1_joy": 0.7226870078740156,
"eval_f1_neutral": 0.8435877759219971,
"eval_f1_sadness": 0.6404109589041096,
"eval_f1_surprise": 0.4166666666666667,
"eval_loss": 0.6897642612457275,
"eval_micro_f1": 0.7466407010710808,
"eval_prec": 0.6572406702350582,
"eval_prec_anger": 0.5109771846749892,
"eval_prec_disgust": 0.4868421052631579,
"eval_prec_fear": 0.8138957816377171,
"eval_prec_joy": 0.7573491490458999,
"eval_prec_neutral": 0.81245109120946,
"eval_prec_sadness": 0.6938775510204082,
"eval_prec_surprise": 0.5252918287937743,
"eval_recall": 0.5649303370058901,
"eval_recall_anger": 0.6565265486725663,
"eval_recall_disgust": 0.30962343096234307,
"eval_recall_fear": 0.4802342606149341,
"eval_recall_joy": 0.6910588235294117,
"eval_recall_neutral": 0.8772061584678934,
"eval_recall_sadness": 0.5945945945945946,
"eval_recall_surprise": 0.3452685421994885,
"eval_runtime": 46.2244,
"eval_samples_per_second": 444.354,
"eval_steps_per_second": 13.889,
"step": 5860
},
{
"epoch": 4.2,
"learning_rate": 0.0008317945033231543,
"loss": 0.6977,
"step": 6153
},
{
"epoch": 4.4,
"learning_rate": 0.0008212681875336806,
"loss": 0.685,
"step": 6446
},
{
"epoch": 4.6,
"learning_rate": 0.000810741871744207,
"loss": 0.6985,
"step": 6739
},
{
"epoch": 4.8,
"learning_rate": 0.0008002155559547333,
"loss": 0.6976,
"step": 7032
},
{
"epoch": 5.0,
"learning_rate": 0.0007896892401652595,
"loss": 0.6925,
"step": 7325
},
{
"epoch": 5.0,
"eval_accuracy": 0.7402629016553067,
"eval_b_acc": 0.5916067970161544,
"eval_f1": 0.5971544894232231,
"eval_f1_anger": 0.5747069094537292,
"eval_f1_disgust": 0.3850687622789784,
"eval_f1_fear": 0.5954887218045113,
"eval_f1_joy": 0.721651810899244,
"eval_f1_neutral": 0.8404170008019246,
"eval_f1_sadness": 0.6490066225165564,
"eval_f1_surprise": 0.41374159820761763,
"eval_loss": 0.7038670182228088,
"eval_micro_f1": 0.7402629016553067,
"eval_prec": 0.6121145881871085,
"eval_prec_anger": 0.5233984552476147,
"eval_prec_disgust": 0.362962962962963,
"eval_prec_fear": 0.6120556414219475,
"eval_prec_joy": 0.693258183394754,
"eval_prec_neutral": 0.8446003602920261,
"eval_prec_sadness": 0.751219512195122,
"eval_prec_surprise": 0.49730700179533216,
"eval_recall": 0.5916067970161544,
"eval_recall_anger": 0.6371681415929203,
"eval_recall_disgust": 0.4100418410041841,
"eval_recall_fear": 0.5797950219619327,
"eval_recall_joy": 0.7524705882352941,
"eval_recall_neutral": 0.8362748779571911,
"eval_recall_sadness": 0.5712771595124536,
"eval_recall_surprise": 0.35421994884910485,
"eval_runtime": 46.1526,
"eval_samples_per_second": 445.045,
"eval_steps_per_second": 13.91,
"step": 7325
},
{
"epoch": 5.2,
"learning_rate": 0.0007791629243757859,
"loss": 0.6851,
"step": 7618
},
{
"epoch": 5.4,
"learning_rate": 0.0007686366085863123,
"loss": 0.671,
"step": 7911
},
{
"epoch": 5.6,
"learning_rate": 0.000758146218789294,
"loss": 0.6817,
"step": 8204
},
{
"epoch": 5.8,
"learning_rate": 0.0007476558289922759,
"loss": 0.683,
"step": 8497
},
{
"epoch": 6.0,
"learning_rate": 0.0007371295132028022,
"loss": 0.6841,
"step": 8790
},
{
"epoch": 6.0,
"eval_accuracy": 0.7516066212268744,
"eval_b_acc": 0.5820003637019402,
"eval_f1": 0.6075976734562277,
"eval_f1_anger": 0.5587018771874006,
"eval_f1_disgust": 0.4760180995475113,
"eval_f1_fear": 0.5998107852412488,
"eval_f1_joy": 0.7342120343839541,
"eval_f1_neutral": 0.8439233370913191,
"eval_f1_sadness": 0.6554338668913225,
"eval_f1_surprise": 0.3850837138508371,
"eval_loss": 0.6704264283180237,
"eval_micro_f1": 0.7516066212268744,
"eval_prec": 0.6607440078057637,
"eval_prec_anger": 0.6576779026217229,
"eval_prec_disgust": 0.4194577352472089,
"eval_prec_fear": 0.8475935828877005,
"eval_prec_joy": 0.7157541899441341,
"eval_prec_neutral": 0.8120281176776881,
"eval_prec_sadness": 0.6971326164874552,
"eval_prec_surprise": 0.4755639097744361,
"eval_recall": 0.5820003637019402,
"eval_recall_anger": 0.4856194690265487,
"eval_recall_disgust": 0.5502092050209205,
"eval_recall_fear": 0.46412884333821375,
"eval_recall_joy": 0.7536470588235294,
"eval_recall_neutral": 0.8784265865565152,
"eval_recall_sadness": 0.6184419713831478,
"eval_recall_surprise": 0.3235294117647059,
"eval_runtime": 46.0795,
"eval_samples_per_second": 445.752,
"eval_steps_per_second": 13.932,
"step": 8790
},
{
"epoch": 6.2,
"learning_rate": 0.0007266031974133286,
"loss": 0.6618,
"step": 9083
},
{
"epoch": 6.4,
"learning_rate": 0.0007160768816238548,
"loss": 0.6658,
"step": 9376
},
{
"epoch": 6.6,
"learning_rate": 0.0007055505658343812,
"loss": 0.6721,
"step": 9669
},
{
"epoch": 6.8,
"learning_rate": 0.0006950242500449076,
"loss": 0.6664,
"step": 9962
},
{
"epoch": 7.0,
"learning_rate": 0.0006844979342554338,
"loss": 0.6715,
"step": 10255
},
{
"epoch": 7.0,
"eval_accuracy": 0.7411879259980526,
"eval_b_acc": 0.6179791982250035,
"eval_f1": 0.611239662539826,
"eval_f1_anger": 0.5761816741484025,
"eval_f1_disgust": 0.45527156549520764,
"eval_f1_fear": 0.6020128087831657,
"eval_f1_joy": 0.7317787540835867,
"eval_f1_neutral": 0.8391440250060112,
"eval_f1_sadness": 0.6545357238426546,
"eval_f1_surprise": 0.4197530864197531,
"eval_loss": 0.6918847560882568,
"eval_micro_f1": 0.7411879259980525,
"eval_prec": 0.6245536912240063,
"eval_prec_anger": 0.551288529560384,
"eval_prec_disgust": 0.3682170542635659,
"eval_prec_fear": 0.802439024390244,
"eval_prec_joy": 0.7019667170953101,
"eval_prec_neutral": 0.860199152124618,
"eval_prec_sadness": 0.6610810810810811,
"eval_prec_surprise": 0.42668428005284015,
"eval_recall": 0.6179791982250035,
"eval_recall_anger": 0.603429203539823,
"eval_recall_disgust": 0.5962343096234309,
"eval_recall_fear": 0.4816983894582723,
"eval_recall_joy": 0.764235294117647,
"eval_recall_neutral": 0.8190950056327451,
"eval_recall_sadness": 0.6481187069422364,
"eval_recall_surprise": 0.41304347826086957,
"eval_runtime": 46.1915,
"eval_samples_per_second": 444.671,
"eval_steps_per_second": 13.899,
"step": 10255
},
{
"epoch": 7.2,
"learning_rate": 0.0006739716184659601,
"loss": 0.6479,
"step": 10548
},
{
"epoch": 7.4,
"learning_rate": 0.0006634453026764866,
"loss": 0.6561,
"step": 10841
},
{
"epoch": 7.6,
"learning_rate": 0.0006529189868870128,
"loss": 0.6625,
"step": 11134
},
{
"epoch": 7.8,
"learning_rate": 0.0006423926710975391,
"loss": 0.658,
"step": 11427
},
{
"epoch": 8.0,
"learning_rate": 0.0006318663553080653,
"loss": 0.6562,
"step": 11720
},
{
"epoch": 8.0,
"eval_accuracy": 0.7325219084712755,
"eval_b_acc": 0.6128679845265063,
"eval_f1": 0.6013536581571658,
"eval_f1_anger": 0.5731053840265374,
"eval_f1_disgust": 0.42007434944237915,
"eval_f1_fear": 0.5870646766169154,
"eval_f1_joy": 0.7238035658429777,
"eval_f1_neutral": 0.8292248292248293,
"eval_f1_sadness": 0.6645180193378261,
"eval_f1_surprise": 0.4116847826086957,
"eval_loss": 0.7244542241096497,
"eval_micro_f1": 0.7325219084712755,
"eval_prec": 0.5985056915840363,
"eval_prec_anger": 0.5319753671245855,
"eval_prec_disgust": 0.3779264214046823,
"eval_prec_fear": 0.5704419889502762,
"eval_prec_joy": 0.6498782999438307,
"eval_prec_neutral": 0.8770680628272252,
"eval_prec_sadness": 0.7431192660550459,
"eval_prec_surprise": 0.4391304347826087,
"eval_recall": 0.6128679845265063,
"eval_recall_anger": 0.6211283185840708,
"eval_recall_disgust": 0.47280334728033474,
"eval_recall_fear": 0.6046852122986823,
"eval_recall_joy": 0.8167058823529412,
"eval_recall_neutral": 0.7863312054074352,
"eval_recall_sadness": 0.6009538950715422,
"eval_recall_surprise": 0.3874680306905371,
"eval_runtime": 46.2278,
"eval_samples_per_second": 444.321,
"eval_steps_per_second": 13.888,
"step": 11720
},
{
"epoch": 8.2,
"learning_rate": 0.0006213400395185917,
"loss": 0.6406,
"step": 12013
},
{
"epoch": 8.4,
"learning_rate": 0.0006108137237291181,
"loss": 0.6459,
"step": 12306
},
{
"epoch": 8.6,
"learning_rate": 0.0006002874079396443,
"loss": 0.6482,
"step": 12599
},
{
"epoch": 8.8,
"learning_rate": 0.0005897610921501707,
"loss": 0.6502,
"step": 12892
},
{
"epoch": 9.0,
"learning_rate": 0.000579234776360697,
"loss": 0.6426,
"step": 13185
},
{
"epoch": 9.0,
"eval_accuracy": 0.7510223953261927,
"eval_b_acc": 0.6108946329415156,
"eval_f1": 0.6175413637878915,
"eval_f1_anger": 0.588235294117647,
"eval_f1_disgust": 0.42267050912584053,
"eval_f1_fear": 0.6240409207161126,
"eval_f1_joy": 0.7357859531772576,
"eval_f1_neutral": 0.8457566654149455,
"eval_f1_sadness": 0.6677704194260485,
"eval_f1_surprise": 0.4385297845373891,
"eval_loss": 0.6683408617973328,
"eval_micro_f1": 0.7510223953261927,
"eval_prec": 0.6304447087675242,
"eval_prec_anger": 0.5768208399787347,
"eval_prec_disgust": 0.3907637655417407,
"eval_prec_fear": 0.746938775510204,
"eval_prec_joy": 0.7215562090024882,
"eval_prec_neutral": 0.8457566654149455,
"eval_prec_sadness": 0.6966033390903857,
"eval_prec_surprise": 0.43467336683417085,
"eval_recall": 0.6108946329415156,
"eval_recall_anger": 0.6001106194690266,
"eval_recall_disgust": 0.4602510460251046,
"eval_recall_fear": 0.5358711566617862,
"eval_recall_joy": 0.7505882352941177,
"eval_recall_neutral": 0.8457566654149455,
"eval_recall_sadness": 0.6412294647588765,
"eval_recall_surprise": 0.4424552429667519,
"eval_runtime": 46.02,
"eval_samples_per_second": 446.328,
"eval_steps_per_second": 13.95,
"step": 13185
},
{
"epoch": 9.2,
"learning_rate": 0.0005687084605712233,
"loss": 0.6219,
"step": 13478
},
{
"epoch": 9.4,
"learning_rate": 0.0005581821447817496,
"loss": 0.629,
"step": 13771
},
{
"epoch": 9.6,
"learning_rate": 0.000547655828992276,
"loss": 0.6295,
"step": 14064
},
{
"epoch": 9.8,
"learning_rate": 0.0005371295132028022,
"loss": 0.6341,
"step": 14357
},
{
"epoch": 10.0,
"learning_rate": 0.0005266031974133285,
"loss": 0.6278,
"step": 14650
},
{
"epoch": 10.0,
"eval_accuracy": 0.7544790652385589,
"eval_b_acc": 0.5967589307999713,
"eval_f1": 0.6141821019437051,
"eval_f1_anger": 0.5878859857482185,
"eval_f1_disgust": 0.44155844155844154,
"eval_f1_fear": 0.6228143213988342,
"eval_f1_joy": 0.7319787131107887,
"eval_f1_neutral": 0.8493716172828181,
"eval_f1_sadness": 0.6534983341266064,
"eval_f1_surprise": 0.41216730038022814,
"eval_loss": 0.6661337018013,
"eval_micro_f1": 0.7544790652385589,
"eval_prec": 0.642724018193579,
"eval_prec_anger": 0.6346153846153846,
"eval_prec_disgust": 0.45739910313901344,
"eval_prec_fear": 0.722007722007722,
"eval_prec_joy": 0.75311100049776,
"eval_prec_neutral": 0.8304035874439462,
"eval_prec_sadness": 0.5930885529157668,
"eval_prec_surprise": 0.5084427767354597,
"eval_recall": 0.5967589307999713,
"eval_recall_anger": 0.547566371681416,
"eval_recall_disgust": 0.42677824267782427,
"eval_recall_fear": 0.5475841874084919,
"eval_recall_joy": 0.712,
"eval_recall_neutral": 0.8692264363499812,
"eval_recall_sadness": 0.7276099629040805,
"eval_recall_surprise": 0.34654731457800514,
"eval_runtime": 46.1343,
"eval_samples_per_second": 445.222,
"eval_steps_per_second": 13.916,
"step": 14650
},
{
"epoch": 10.2,
"learning_rate": 0.0005161128076163104,
"loss": 0.6132,
"step": 14943
},
{
"epoch": 10.4,
"learning_rate": 0.0005055864918268367,
"loss": 0.6134,
"step": 15236
},
{
"epoch": 10.6,
"learning_rate": 0.0004950961020298186,
"loss": 0.6153,
"step": 15529
},
{
"epoch": 10.8,
"learning_rate": 0.0004845697862403449,
"loss": 0.6115,
"step": 15822
},
{
"epoch": 11.0,
"learning_rate": 0.0004740434704508712,
"loss": 0.6218,
"step": 16115
},
{
"epoch": 11.0,
"eval_accuracy": 0.750730282375852,
"eval_b_acc": 0.5958006635298841,
"eval_f1": 0.6142987968349727,
"eval_f1_anger": 0.5728,
"eval_f1_disgust": 0.45192307692307687,
"eval_f1_fear": 0.6015971606033718,
"eval_f1_joy": 0.7337797782412998,
"eval_f1_neutral": 0.8416802042237178,
"eval_f1_sadness": 0.6666666666666666,
"eval_f1_surprise": 0.431644691186676,
"eval_loss": 0.6714352965354919,
"eval_micro_f1": 0.750730282375852,
"eval_prec": 0.647849574337048,
"eval_prec_anger": 0.6795747911921033,
"eval_prec_disgust": 0.4181494661921708,
"eval_prec_fear": 0.7635135135135135,
"eval_prec_joy": 0.6877958427660013,
"eval_prec_neutral": 0.832369411548701,
"eval_prec_sadness": 0.6816168327796235,
"eval_prec_surprise": 0.47192716236722304,
"eval_recall": 0.5958006635298841,
"eval_recall_anger": 0.4950221238938053,
"eval_recall_disgust": 0.4916317991631799,
"eval_recall_fear": 0.49633967789165445,
"eval_recall_joy": 0.7863529411764706,
"eval_recall_neutral": 0.8512016522718738,
"eval_recall_sadness": 0.6523582405935348,
"eval_recall_surprise": 0.3976982097186701,
"eval_runtime": 46.0325,
"eval_samples_per_second": 446.206,
"eval_steps_per_second": 13.947,
"step": 16115
},
{
"epoch": 11.2,
"learning_rate": 0.00046351715466139755,
"loss": 0.5966,
"step": 16408
},
{
"epoch": 11.4,
"learning_rate": 0.0004529908388719238,
"loss": 0.5988,
"step": 16701
},
{
"epoch": 11.6,
"learning_rate": 0.0004424645230824502,
"loss": 0.6077,
"step": 16994
},
{
"epoch": 11.8,
"learning_rate": 0.0004319382072929765,
"loss": 0.6089,
"step": 17287
},
{
"epoch": 12.0,
"learning_rate": 0.0004214118915035028,
"loss": 0.6077,
"step": 17580
},
{
"epoch": 12.0,
"eval_accuracy": 0.7543330087633885,
"eval_b_acc": 0.6171055294678581,
"eval_f1": 0.6187242211015894,
"eval_f1_anger": 0.6074972436604189,
"eval_f1_disgust": 0.429035752979415,
"eval_f1_fear": 0.6134515890613451,
"eval_f1_joy": 0.7370813397129187,
"eval_f1_neutral": 0.8496555576242785,
"eval_f1_sadness": 0.6629986244841817,
"eval_f1_surprise": 0.431349440188568,
"eval_loss": 0.6648654341697693,
"eval_micro_f1": 0.7543330087633885,
"eval_prec": 0.6216330895487993,
"eval_prec_anger": 0.6054945054945055,
"eval_prec_disgust": 0.4449438202247191,
"eval_prec_fear": 0.6194029850746269,
"eval_prec_joy": 0.7496350364963503,
"eval_prec_neutral": 0.842596011816839,
"eval_prec_sadness": 0.6893592677345538,
"eval_prec_surprise": 0.4,
"eval_recall": 0.6171055294678581,
"eval_recall_anger": 0.6095132743362832,
"eval_recall_disgust": 0.41422594142259417,
"eval_recall_fear": 0.6076134699853587,
"eval_recall_joy": 0.7249411764705882,
"eval_recall_neutral": 0.8568343972962824,
"eval_recall_sadness": 0.6385797562268151,
"eval_recall_surprise": 0.4680306905370844,
"eval_runtime": 46.1374,
"eval_samples_per_second": 445.192,
"eval_steps_per_second": 13.915,
"step": 17580
},
{
"epoch": 12.2,
"learning_rate": 0.0004108855757140291,
"loss": 0.5841,
"step": 17873
},
{
"epoch": 12.4,
"learning_rate": 0.0004003592599245554,
"loss": 0.5891,
"step": 18166
},
{
"epoch": 12.6,
"learning_rate": 0.00038983294413508175,
"loss": 0.5867,
"step": 18459
},
{
"epoch": 12.8,
"learning_rate": 0.000379306628345608,
"loss": 0.5906,
"step": 18752
},
{
"epoch": 13.0,
"learning_rate": 0.0003687803125561344,
"loss": 0.5868,
"step": 19045
},
{
"epoch": 13.0,
"eval_accuracy": 0.7583739045764363,
"eval_b_acc": 0.6026010025373034,
"eval_f1": 0.6223744496289562,
"eval_f1_anger": 0.6024734982332155,
"eval_f1_disgust": 0.44166666666666665,
"eval_f1_fear": 0.6313213703099511,
"eval_f1_joy": 0.735365152386429,
"eval_f1_neutral": 0.8496863696717184,
"eval_f1_sadness": 0.6641961231470923,
"eval_f1_surprise": 0.43191196698762035,
"eval_loss": 0.6679861545562744,
"eval_micro_f1": 0.7583739045764363,
"eval_prec": 0.64731907895135,
"eval_prec_anger": 0.6442065491183879,
"eval_prec_disgust": 0.43983402489626555,
"eval_prec_fear": 0.712707182320442,
"eval_prec_joy": 0.7192350956130483,
"eval_prec_neutral": 0.8292966306193583,
"eval_prec_sadness": 0.7186921653300432,
"eval_prec_surprise": 0.46726190476190477,
"eval_recall": 0.6026010025373034,
"eval_recall_anger": 0.5658185840707964,
"eval_recall_disgust": 0.4435146443514644,
"eval_recall_fear": 0.5666178623718887,
"eval_recall_joy": 0.7522352941176471,
"eval_recall_neutral": 0.8711040180247841,
"eval_recall_sadness": 0.6173820879703232,
"eval_recall_surprise": 0.40153452685422,
"eval_runtime": 46.0652,
"eval_samples_per_second": 445.89,
"eval_steps_per_second": 13.937,
"step": 19045
},
{
"epoch": 13.2,
"learning_rate": 0.0003582539967666607,
"loss": 0.5689,
"step": 19338
},
{
"epoch": 13.4,
"learning_rate": 0.000347727680977187,
"loss": 0.5716,
"step": 19631
},
{
"epoch": 13.6,
"learning_rate": 0.0003372372911801689,
"loss": 0.5675,
"step": 19924
},
{
"epoch": 13.8,
"learning_rate": 0.00032674690138315073,
"loss": 0.5758,
"step": 20217
},
{
"epoch": 14.0,
"learning_rate": 0.00031622058559367704,
"loss": 0.5747,
"step": 20510
},
{
"epoch": 14.0,
"eval_accuracy": 0.755111976630964,
"eval_b_acc": 0.6048530634576196,
"eval_f1": 0.6154691317356998,
"eval_f1_anger": 0.6074639062925634,
"eval_f1_disgust": 0.4108352144469526,
"eval_f1_fear": 0.607483492296405,
"eval_f1_joy": 0.7358854935817335,
"eval_f1_neutral": 0.8482922954725973,
"eval_f1_sadness": 0.6642149929278642,
"eval_f1_surprise": 0.43410852713178294,
"eval_loss": 0.6692087054252625,
"eval_micro_f1": 0.755111976630964,
"eval_prec": 0.6292971112960697,
"eval_prec_anger": 0.5984970477724101,
"eval_prec_disgust": 0.44607843137254904,
"eval_prec_fear": 0.6088235294117647,
"eval_prec_joy": 0.711399077531298,
"eval_prec_neutral": 0.8443865686912845,
"eval_prec_sadness": 0.712378640776699,
"eval_prec_surprise": 0.4835164835164835,
"eval_recall": 0.6048530634576196,
"eval_recall_anger": 0.6167035398230089,
"eval_recall_disgust": 0.3807531380753138,
"eval_recall_fear": 0.6061493411420205,
"eval_recall_joy": 0.7621176470588236,
"eval_recall_neutral": 0.8522343221930154,
"eval_recall_sadness": 0.6221515633280339,
"eval_recall_surprise": 0.3938618925831202,
"eval_runtime": 46.1819,
"eval_samples_per_second": 444.763,
"eval_steps_per_second": 13.902,
"step": 20510
},
{
"epoch": 14.2,
"learning_rate": 0.00030569426980420336,
"loss": 0.5521,
"step": 20803
},
{
"epoch": 14.4,
"learning_rate": 0.00029516795401472967,
"loss": 0.55,
"step": 21096
},
{
"epoch": 14.6,
"learning_rate": 0.000284641638225256,
"loss": 0.5572,
"step": 21389
},
{
"epoch": 14.8,
"learning_rate": 0.0002741153224357823,
"loss": 0.5615,
"step": 21682
},
{
"epoch": 15.0,
"learning_rate": 0.00026358900664630856,
"loss": 0.5632,
"step": 21975
},
{
"epoch": 15.0,
"eval_accuracy": 0.7550632911392405,
"eval_b_acc": 0.6104260663388762,
"eval_f1": 0.6185386561537733,
"eval_f1_anger": 0.6062717770034843,
"eval_f1_disgust": 0.4662349676225717,
"eval_f1_fear": 0.5972434915773354,
"eval_f1_joy": 0.7371225577264653,
"eval_f1_neutral": 0.8455345440928667,
"eval_f1_sadness": 0.669596264762428,
"eval_f1_surprise": 0.4077669902912621,
"eval_loss": 0.6762722134590149,
"eval_micro_f1": 0.7550632911392405,
"eval_prec": 0.6390061654621464,
"eval_prec_anger": 0.6381418092909535,
"eval_prec_disgust": 0.417910447761194,
"eval_prec_fear": 0.6260032102728732,
"eval_prec_joy": 0.6977721731820092,
"eval_prec_neutral": 0.8431665421956684,
"eval_prec_sadness": 0.6949828962371721,
"eval_prec_surprise": 0.5550660792951542,
"eval_recall": 0.6104260663388762,
"eval_recall_anger": 0.577433628318584,
"eval_recall_disgust": 0.5271966527196653,
"eval_recall_fear": 0.5710102489019033,
"eval_recall_joy": 0.7811764705882352,
"eval_recall_neutral": 0.8479158843409689,
"eval_recall_sadness": 0.6459989401165872,
"eval_recall_surprise": 0.32225063938618925,
"eval_runtime": 46.0659,
"eval_samples_per_second": 445.883,
"eval_steps_per_second": 13.937,
"step": 21975
},
{
"epoch": 15.2,
"learning_rate": 0.0002530626908568349,
"loss": 0.5379,
"step": 22268
},
{
"epoch": 15.4,
"learning_rate": 0.00024253637506736124,
"loss": 0.5403,
"step": 22561
},
{
"epoch": 15.6,
"learning_rate": 0.00023201005927788758,
"loss": 0.5446,
"step": 22854
},
{
"epoch": 15.8,
"learning_rate": 0.00022148374348841387,
"loss": 0.5467,
"step": 23147
},
{
"epoch": 16.0,
"learning_rate": 0.00021095742769894018,
"loss": 0.546,
"step": 23440
},
{
"epoch": 16.0,
"eval_accuracy": 0.7537000973709834,
"eval_b_acc": 0.6088681990875895,
"eval_f1": 0.6204872320296809,
"eval_f1_anger": 0.6185002736726875,
"eval_f1_disgust": 0.41638225255972694,
"eval_f1_fear": 0.6321401370906321,
"eval_f1_joy": 0.7359859309738404,
"eval_f1_neutral": 0.8420753645142964,
"eval_f1_sadness": 0.6701657458563536,
"eval_f1_surprise": 0.4281609195402299,
"eval_loss": 0.6880349516868591,
"eval_micro_f1": 0.7537000973709834,
"eval_prec": 0.6365138577031803,
"eval_prec_anger": 0.6121343445287107,
"eval_prec_disgust": 0.456359102244389,
"eval_prec_fear": 0.6587301587301587,
"eval_prec_joy": 0.6905940594059405,
"eval_prec_neutral": 0.8493124522536287,
"eval_prec_sadness": 0.6999422965954991,
"eval_prec_surprise": 0.4885245901639344,
"eval_recall": 0.6088681990875895,
"eval_recall_anger": 0.625,
"eval_recall_disgust": 0.38284518828451886,
"eval_recall_fear": 0.6076134699853587,
"eval_recall_joy": 0.7877647058823529,
"eval_recall_neutral": 0.8349605707848291,
"eval_recall_sadness": 0.6428192898781134,
"eval_recall_surprise": 0.38107416879795397,
"eval_runtime": 46.5188,
"eval_samples_per_second": 441.542,
"eval_steps_per_second": 13.801,
"step": 23440
},
{
"epoch": 16.2,
"learning_rate": 0.0002004311119094665,
"loss": 0.5239,
"step": 23733
},
{
"epoch": 16.4,
"learning_rate": 0.0001899047961199928,
"loss": 0.5223,
"step": 24026
},
{
"epoch": 16.6,
"learning_rate": 0.00017941440632297467,
"loss": 0.5312,
"step": 24319
},
{
"epoch": 16.8,
"learning_rate": 0.00016888809053350098,
"loss": 0.5308,
"step": 24612
},
{
"epoch": 17.0,
"learning_rate": 0.0001583617747440273,
"loss": 0.5354,
"step": 24905
},
{
"epoch": 17.0,
"eval_accuracy": 0.7544790652385589,
"eval_b_acc": 0.6097199422404823,
"eval_f1": 0.6222181238744549,
"eval_f1_anger": 0.6241173275393808,
"eval_f1_disgust": 0.42105263157894735,
"eval_f1_fear": 0.632506004803843,
"eval_f1_joy": 0.7375304810463312,
"eval_f1_neutral": 0.8440314781454441,
"eval_f1_sadness": 0.663218077865505,
"eval_f1_surprise": 0.4330708661417323,
"eval_loss": 0.6822559833526611,
"eval_micro_f1": 0.7544790652385589,
"eval_prec": 0.6398646312953825,
"eval_prec_anger": 0.6131270010672358,
"eval_prec_disgust": 0.49162011173184356,
"eval_prec_fear": 0.6978798586572438,
"eval_prec_joy": 0.6971919530595139,
"eval_prec_neutral": 0.8525186745834131,
"eval_prec_sadness": 0.6819708846584547,
"eval_prec_surprise": 0.444743935309973,
"eval_recall": 0.6097199422404823,
"eval_recall_anger": 0.6355088495575221,
"eval_recall_disgust": 0.3682008368200837,
"eval_recall_fear": 0.5783308931185944,
"eval_recall_joy": 0.7828235294117647,
"eval_recall_neutral": 0.8357116034547503,
"eval_recall_sadness": 0.6454689984101749,
"eval_recall_surprise": 0.4219948849104859,
"eval_runtime": 46.2493,
"eval_samples_per_second": 444.115,
"eval_steps_per_second": 13.881,
"step": 24905
},
{
"epoch": 17.2,
"learning_rate": 0.0001478354589545536,
"loss": 0.5058,
"step": 25198
},
{
"epoch": 17.4,
"learning_rate": 0.00013730914316507995,
"loss": 0.5182,
"step": 25491
},
{
"epoch": 17.6,
"learning_rate": 0.00012678282737560627,
"loss": 0.5132,
"step": 25784
},
{
"epoch": 17.8,
"learning_rate": 0.00011629243757858811,
"loss": 0.5169,
"step": 26077
},
{
"epoch": 18.0,
"learning_rate": 0.00010576612178911443,
"loss": 0.5103,
"step": 26370
},
{
"epoch": 18.0,
"eval_accuracy": 0.7581304771178189,
"eval_b_acc": 0.6039152175326364,
"eval_f1": 0.6206372407316966,
"eval_f1_anger": 0.624553694040099,
"eval_f1_disgust": 0.4259259259259259,
"eval_f1_fear": 0.6247049567269867,
"eval_f1_joy": 0.7396948303347757,
"eval_f1_neutral": 0.8471082089552239,
"eval_f1_sadness": 0.6643598615916955,
"eval_f1_surprise": 0.41811320754716985,
"eval_loss": 0.6852018237113953,
"eval_micro_f1": 0.758130477117819,
"eval_prec": 0.6440153151637059,
"eval_prec_anger": 0.6202945990180033,
"eval_prec_disgust": 0.47668393782383417,
"eval_prec_fear": 0.6751700680272109,
"eval_prec_joy": 0.7166813768755517,
"eval_prec_neutral": 0.8417686318131257,
"eval_prec_sadness": 0.667379679144385,
"eval_prec_surprise": 0.5101289134438306,
"eval_recall": 0.6039152175326364,
"eval_recall_anger": 0.6288716814159292,
"eval_recall_disgust": 0.38493723849372385,
"eval_recall_fear": 0.5812591508052709,
"eval_recall_joy": 0.764235294117647,
"eval_recall_neutral": 0.8525159594442359,
"eval_recall_sadness": 0.6613672496025437,
"eval_recall_surprise": 0.35421994884910485,
"eval_runtime": 46.0432,
"eval_samples_per_second": 446.103,
"eval_steps_per_second": 13.943,
"step": 26370
},
{
"epoch": 18.2,
"learning_rate": 9.523980599964074e-05,
"loss": 0.5041,
"step": 26663
},
{
"epoch": 18.4,
"learning_rate": 8.471349021016706e-05,
"loss": 0.5066,
"step": 26956
},
{
"epoch": 18.6,
"learning_rate": 7.418717442069338e-05,
"loss": 0.5007,
"step": 27249
},
{
"epoch": 18.8,
"learning_rate": 6.369678462367523e-05,
"loss": 0.4965,
"step": 27542
},
{
"epoch": 19.0,
"learning_rate": 5.3170468834201544e-05,
"loss": 0.4972,
"step": 27835
},
{
"epoch": 19.0,
"eval_accuracy": 0.7535053554040896,
"eval_b_acc": 0.6039050483043659,
"eval_f1": 0.6162485458896193,
"eval_f1_anger": 0.6241059602649006,
"eval_f1_disgust": 0.41258741258741255,
"eval_f1_fear": 0.6275430359937403,
"eval_f1_joy": 0.7361095521382872,
"eval_f1_neutral": 0.8437618147448016,
"eval_f1_sadness": 0.6601011445302103,
"eval_f1_surprise": 0.4095309009679821,
"eval_loss": 0.6947867274284363,
"eval_micro_f1": 0.7535053554040896,
"eval_prec": 0.635037226488908,
"eval_prec_anger": 0.5988815455007626,
"eval_prec_disgust": 0.46578947368421053,
"eval_prec_fear": 0.6739495798319328,
"eval_prec_joy": 0.7037990985189955,
"eval_prec_neutral": 0.849543205177008,
"eval_prec_sadness": 0.6631016042780749,
"eval_prec_surprise": 0.49019607843137253,
"eval_recall": 0.6039050483043659,
"eval_recall_anger": 0.6515486725663717,
"eval_recall_disgust": 0.3702928870292887,
"eval_recall_fear": 0.5871156661786238,
"eval_recall_joy": 0.7715294117647059,
"eval_recall_neutral": 0.8380585805482539,
"eval_recall_sadness": 0.6571277159512454,
"eval_recall_surprise": 0.3516624040920716,
"eval_runtime": 46.2834,
"eval_samples_per_second": 443.788,
"eval_steps_per_second": 13.871,
"step": 27835
},
{
"epoch": 19.2,
"learning_rate": 4.264415304472786e-05,
"loss": 0.4927,
"step": 28128
},
{
"epoch": 19.4,
"learning_rate": 3.211783725525418e-05,
"loss": 0.4867,
"step": 28421
},
{
"epoch": 19.6,
"learning_rate": 2.1591521465780493e-05,
"loss": 0.4917,
"step": 28714
},
{
"epoch": 19.8,
"learning_rate": 1.1065205676306808e-05,
"loss": 0.4916,
"step": 29007
},
{
"epoch": 20.0,
"learning_rate": 5.388898868331237e-07,
"loss": 0.4801,
"step": 29300
},
{
"epoch": 20.0,
"eval_accuracy": 0.7549172346640701,
"eval_b_acc": 0.6105911461962804,
"eval_f1": 0.6198802361438264,
"eval_f1_anger": 0.6221737946063742,
"eval_f1_disgust": 0.42093784078516905,
"eval_f1_fear": 0.6232558139534883,
"eval_f1_joy": 0.7376322074377345,
"eval_f1_neutral": 0.8454656747339674,
"eval_f1_sadness": 0.6622481442205725,
"eval_f1_surprise": 0.4274481772694782,
"eval_loss": 0.6945263743400574,
"eval_micro_f1": 0.7549172346640701,
"eval_prec": 0.6320068488618952,
"eval_prec_anger": 0.6129898013955984,
"eval_prec_disgust": 0.4396355353075171,
"eval_prec_fear": 0.6622734761120264,
"eval_prec_joy": 0.713845476557341,
"eval_prec_neutral": 0.8481012658227848,
"eval_prec_sadness": 0.6625994694960212,
"eval_prec_surprise": 0.4846029173419773,
"eval_recall": 0.6105911461962804,
"eval_recall_anger": 0.6316371681415929,
"eval_recall_disgust": 0.40376569037656906,
"eval_recall_fear": 0.5885797950219619,
"eval_recall_joy": 0.7630588235294118,
"eval_recall_neutral": 0.8428464138190012,
"eval_recall_sadness": 0.661897191308956,
"eval_recall_surprise": 0.38235294117647056,
"eval_runtime": 46.1785,
"eval_samples_per_second": 444.796,
"eval_steps_per_second": 13.903,
"step": 29300
},
{
"epoch": 20.0,
"step": 29300,
"total_flos": 8.789779081685053e+17,
"train_loss": 0.6315777759747294,
"train_runtime": 20512.0097,
"train_samples_per_second": 182.843,
"train_steps_per_second": 1.428
}
],
"max_steps": 29300,
"num_train_epochs": 20,
"total_flos": 8.789779081685053e+17,
"trial_name": null,
"trial_params": null
}