lora-roberta-large-no-ed / trainer_state.json
anniew666's picture
End of training
447a2b2
raw
history blame
39.4 kB
{
"best_metric": 0.6276991641576467,
"best_model_checkpoint": ".exp/lora/lora-roberta-large-no-ed/checkpoint-17584",
"epoch": 14.99744070977649,
"global_step": 21975,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.15,
"learning_rate": 0.00019836214740673338,
"loss": 1.2151,
"step": 220
},
{
"epoch": 0.3,
"learning_rate": 0.0003976342129208371,
"loss": 0.8737,
"step": 440
},
{
"epoch": 0.45,
"learning_rate": 0.0005969062784349408,
"loss": 0.8228,
"step": 660
},
{
"epoch": 0.6,
"learning_rate": 0.0007970882620564149,
"loss": 0.8081,
"step": 880
},
{
"epoch": 0.75,
"eval_accuracy": 0.7138266796494644,
"eval_b_acc": 0.5642215512771782,
"eval_f1": 0.5601190771157161,
"eval_f1_anger": 0.515716568993074,
"eval_f1_disgust": 0.3879907621247113,
"eval_f1_fear": 0.5360230547550433,
"eval_f1_joy": 0.6877726536208402,
"eval_f1_neutral": 0.8344834105302958,
"eval_f1_sadness": 0.5870011402508551,
"eval_f1_surprise": 0.3718459495351925,
"eval_loss": 0.790067732334137,
"eval_micro_f1": 0.7138266796494644,
"eval_prec": 0.5616517829432821,
"eval_prec_anger": 0.49743062692702983,
"eval_prec_disgust": 0.4329896907216495,
"eval_prec_fear": 0.5276595744680851,
"eval_prec_joy": 0.7312483434932414,
"eval_prec_neutral": 0.8402817437654674,
"eval_prec_sadness": 0.5152121697357886,
"eval_prec_surprise": 0.3867403314917127,
"eval_recall": 0.5642215512771782,
"eval_recall_anger": 0.5353982300884956,
"eval_recall_disgust": 0.3514644351464435,
"eval_recall_fear": 0.5446559297218155,
"eval_recall_joy": 0.6491764705882352,
"eval_recall_neutral": 0.8287645512579798,
"eval_recall_sadness": 0.6820349761526232,
"eval_recall_surprise": 0.35805626598465473,
"eval_runtime": 53.9044,
"eval_samples_per_second": 381.045,
"eval_steps_per_second": 23.82,
"step": 1099
},
{
"epoch": 0.75,
"learning_rate": 0.000997270245677889,
"loss": 0.7828,
"step": 1100
},
{
"epoch": 0.9,
"learning_rate": 0.0009896052883694194,
"loss": 0.7661,
"step": 1320
},
{
"epoch": 1.05,
"learning_rate": 0.0009790668710480935,
"loss": 0.7799,
"step": 1540
},
{
"epoch": 1.2,
"learning_rate": 0.0009685284537267676,
"loss": 0.757,
"step": 1760
},
{
"epoch": 1.35,
"learning_rate": 0.0009579900364054417,
"loss": 0.7543,
"step": 1980
},
{
"epoch": 1.5,
"eval_accuracy": 0.7262901655306718,
"eval_b_acc": 0.5714411859458394,
"eval_f1": 0.573711944542916,
"eval_f1_anger": 0.5241837968561063,
"eval_f1_disgust": 0.44267198404785646,
"eval_f1_fear": 0.546070460704607,
"eval_f1_joy": 0.7150729335494327,
"eval_f1_neutral": 0.8296947358472735,
"eval_f1_sadness": 0.6172300981461288,
"eval_f1_surprise": 0.3410596026490066,
"eval_loss": 0.7482287883758545,
"eval_micro_f1": 0.7262901655306718,
"eval_prec": 0.5892369276637266,
"eval_prec_anger": 0.578,
"eval_prec_disgust": 0.4228571428571429,
"eval_prec_fear": 0.5081967213114754,
"eval_prec_joy": 0.6611388611388611,
"eval_prec_neutral": 0.8352997145575642,
"eval_prec_sadness": 0.6355979786636721,
"eval_prec_surprise": 0.4835680751173709,
"eval_recall": 0.5714411859458394,
"eval_recall_anger": 0.4795353982300885,
"eval_recall_disgust": 0.46443514644351463,
"eval_recall_fear": 0.5900439238653001,
"eval_recall_joy": 0.7785882352941177,
"eval_recall_neutral": 0.8241644761547128,
"eval_recall_sadness": 0.5998940116587176,
"eval_recall_surprise": 0.26342710997442453,
"eval_runtime": 52.5664,
"eval_samples_per_second": 390.744,
"eval_steps_per_second": 24.426,
"step": 2198
},
{
"epoch": 1.5,
"learning_rate": 0.0009474516190841157,
"loss": 0.7562,
"step": 2200
},
{
"epoch": 1.65,
"learning_rate": 0.0009369132017627898,
"loss": 0.7601,
"step": 2420
},
{
"epoch": 1.8,
"learning_rate": 0.0009263747844414639,
"loss": 0.7501,
"step": 2640
},
{
"epoch": 1.95,
"learning_rate": 0.000915836367120138,
"loss": 0.737,
"step": 2860
},
{
"epoch": 2.1,
"learning_rate": 0.0009052979497988121,
"loss": 0.7292,
"step": 3080
},
{
"epoch": 2.25,
"eval_accuracy": 0.739240506329114,
"eval_b_acc": 0.5728734605953718,
"eval_f1": 0.5834227565376339,
"eval_f1_anger": 0.5439560439560439,
"eval_f1_disgust": 0.41185185185185186,
"eval_f1_fear": 0.593798449612403,
"eval_f1_joy": 0.721927599723311,
"eval_f1_neutral": 0.8387907060195567,
"eval_f1_sadness": 0.6231551328304362,
"eval_f1_surprise": 0.35047951176983433,
"eval_loss": 0.7176372408866882,
"eval_micro_f1": 0.739240506329114,
"eval_prec": 0.633689371773426,
"eval_prec_anger": 0.6069482288828338,
"eval_prec_disgust": 0.31880733944954126,
"eval_prec_fear": 0.6309719934102141,
"eval_prec_joy": 0.7077305605786618,
"eval_prec_neutral": 0.8031266105480158,
"eval_prec_sadness": 0.8175559380378657,
"eval_prec_surprise": 0.5506849315068493,
"eval_recall": 0.5728734605953718,
"eval_recall_anger": 0.4928097345132743,
"eval_recall_disgust": 0.5815899581589958,
"eval_recall_fear": 0.5607613469985359,
"eval_recall_joy": 0.7367058823529412,
"eval_recall_neutral": 0.8777694329703342,
"eval_recall_sadness": 0.5034446210916799,
"eval_recall_surprise": 0.2570332480818414,
"eval_runtime": 52.5539,
"eval_samples_per_second": 390.837,
"eval_steps_per_second": 24.432,
"step": 3297
},
{
"epoch": 2.25,
"learning_rate": 0.0008948074343744013,
"loss": 0.7375,
"step": 3300
},
{
"epoch": 2.4,
"learning_rate": 0.0008842690170530752,
"loss": 0.7199,
"step": 3520
},
{
"epoch": 2.55,
"learning_rate": 0.0008737305997317494,
"loss": 0.7064,
"step": 3740
},
{
"epoch": 2.7,
"learning_rate": 0.0008631921824104235,
"loss": 0.7063,
"step": 3960
},
{
"epoch": 2.85,
"learning_rate": 0.0008526537650890975,
"loss": 0.7138,
"step": 4180
},
{
"epoch": 3.0,
"eval_accuracy": 0.7448393378773126,
"eval_b_acc": 0.5918170569783451,
"eval_f1": 0.6005073740718484,
"eval_f1_anger": 0.583310230108123,
"eval_f1_disgust": 0.4129301355578728,
"eval_f1_fear": 0.582723279648609,
"eval_f1_joy": 0.729650507328072,
"eval_f1_neutral": 0.8403856955626287,
"eval_f1_sadness": 0.6514983351831298,
"eval_f1_surprise": 0.40305343511450376,
"eval_loss": 0.688290536403656,
"eval_micro_f1": 0.7448393378773126,
"eval_prec": 0.6144786785060393,
"eval_prec_anger": 0.584769316286826,
"eval_prec_disgust": 0.41164241164241167,
"eval_prec_fear": 0.582723279648609,
"eval_prec_joy": 0.7004329004329004,
"eval_prec_neutral": 0.8380321135175504,
"eval_prec_sadness": 0.6837507280139778,
"eval_prec_surprise": 0.5,
"eval_recall": 0.5918170569783451,
"eval_recall_anger": 0.581858407079646,
"eval_recall_disgust": 0.41422594142259417,
"eval_recall_fear": 0.582723279648609,
"eval_recall_joy": 0.7614117647058823,
"eval_recall_neutral": 0.842752534735261,
"eval_recall_sadness": 0.6221515633280339,
"eval_recall_surprise": 0.3375959079283887,
"eval_runtime": 52.617,
"eval_samples_per_second": 390.368,
"eval_steps_per_second": 24.403,
"step": 4396
},
{
"epoch": 3.0,
"learning_rate": 0.0008421632496646868,
"loss": 0.7289,
"step": 4400
},
{
"epoch": 3.15,
"learning_rate": 0.0008316248323433608,
"loss": 0.6887,
"step": 4620
},
{
"epoch": 3.3,
"learning_rate": 0.0008210864150220348,
"loss": 0.6982,
"step": 4840
},
{
"epoch": 3.45,
"learning_rate": 0.0008105479977007089,
"loss": 0.701,
"step": 5060
},
{
"epoch": 3.6,
"learning_rate": 0.0008000095803793831,
"loss": 0.7046,
"step": 5280
},
{
"epoch": 3.75,
"eval_accuracy": 0.7464946445959104,
"eval_b_acc": 0.5788756560881936,
"eval_f1": 0.5986191545663104,
"eval_f1_anger": 0.5739130434782608,
"eval_f1_disgust": 0.3984476067270375,
"eval_f1_fear": 0.5746569814366425,
"eval_f1_joy": 0.730888607885964,
"eval_f1_neutral": 0.8425003475279181,
"eval_f1_sadness": 0.6517333333333334,
"eval_f1_surprise": 0.418194161575017,
"eval_loss": 0.682627260684967,
"eval_micro_f1": 0.7464946445959104,
"eval_prec": 0.6275132039697725,
"eval_prec_anger": 0.5822424587364826,
"eval_prec_disgust": 0.5220338983050847,
"eval_prec_fear": 0.6402877697841727,
"eval_prec_joy": 0.7145425938413127,
"eval_prec_neutral": 0.8318235886174399,
"eval_prec_sadness": 0.6559312936124531,
"eval_prec_surprise": 0.44573082489146165,
"eval_recall": 0.5788756560881936,
"eval_recall_anger": 0.5658185840707964,
"eval_recall_disgust": 0.32217573221757323,
"eval_recall_fear": 0.5212298682284041,
"eval_recall_joy": 0.748,
"eval_recall_neutral": 0.8534547502816372,
"eval_recall_sadness": 0.6475887652358241,
"eval_recall_surprise": 0.3938618925831202,
"eval_runtime": 54.8263,
"eval_samples_per_second": 374.638,
"eval_steps_per_second": 23.419,
"step": 5495
},
{
"epoch": 3.75,
"learning_rate": 0.0007894711630580571,
"loss": 0.7145,
"step": 5500
},
{
"epoch": 3.9,
"learning_rate": 0.0007789806476336463,
"loss": 0.7056,
"step": 5720
},
{
"epoch": 4.05,
"learning_rate": 0.0007684422303123204,
"loss": 0.6911,
"step": 5940
},
{
"epoch": 4.2,
"learning_rate": 0.0007579038129909944,
"loss": 0.6777,
"step": 6160
},
{
"epoch": 4.35,
"learning_rate": 0.0007473653956696685,
"loss": 0.6767,
"step": 6380
},
{
"epoch": 4.5,
"eval_accuracy": 0.7435735150925025,
"eval_b_acc": 0.5648744699236212,
"eval_f1": 0.592256565822076,
"eval_f1_anger": 0.5643717196665637,
"eval_f1_disgust": 0.36467236467236464,
"eval_f1_fear": 0.6036536934074663,
"eval_f1_joy": 0.7215847324556106,
"eval_f1_neutral": 0.8374881666140739,
"eval_f1_sadness": 0.6377816291161179,
"eval_f1_surprise": 0.416243654822335,
"eval_loss": 0.6971003413200378,
"eval_micro_f1": 0.7435735150925025,
"eval_prec": 0.6422939486456166,
"eval_prec_anger": 0.6387141858839972,
"eval_prec_disgust": 0.5714285714285714,
"eval_prec_fear": 0.6597222222222222,
"eval_prec_joy": 0.7413750310250683,
"eval_prec_neutral": 0.80556760038158,
"eval_prec_sadness": 0.5985130111524164,
"eval_prec_surprise": 0.4807370184254606,
"eval_recall": 0.5648744699236212,
"eval_recall_anger": 0.5055309734513275,
"eval_recall_disgust": 0.26778242677824265,
"eval_recall_fear": 0.5563689604685212,
"eval_recall_joy": 0.7028235294117647,
"eval_recall_neutral": 0.8720428088621855,
"eval_recall_sadness": 0.6825649178590355,
"eval_recall_surprise": 0.3670076726342711,
"eval_runtime": 52.3013,
"eval_samples_per_second": 392.725,
"eval_steps_per_second": 24.55,
"step": 6594
},
{
"epoch": 4.5,
"learning_rate": 0.0007368269783483425,
"loss": 0.6834,
"step": 6600
},
{
"epoch": 4.65,
"learning_rate": 0.0007262885610270167,
"loss": 0.6924,
"step": 6820
},
{
"epoch": 4.8,
"learning_rate": 0.0007157501437056908,
"loss": 0.6872,
"step": 7040
},
{
"epoch": 4.95,
"learning_rate": 0.0007052117263843648,
"loss": 0.6681,
"step": 7260
},
{
"epoch": 5.1,
"learning_rate": 0.000694673309063039,
"loss": 0.661,
"step": 7480
},
{
"epoch": 5.25,
"eval_accuracy": 0.7383641674780915,
"eval_b_acc": 0.602771097930762,
"eval_f1": 0.6030709415406346,
"eval_f1_anger": 0.5770609318996416,
"eval_f1_disgust": 0.41814595660749504,
"eval_f1_fear": 0.6160198183319571,
"eval_f1_joy": 0.7286771805600258,
"eval_f1_neutral": 0.8364084854464726,
"eval_f1_sadness": 0.6574813998346651,
"eval_f1_surprise": 0.38770281810418444,
"eval_loss": 0.7123843431472778,
"eval_micro_f1": 0.7383641674780915,
"eval_prec": 0.6294789669741513,
"eval_prec_anger": 0.48493975903614456,
"eval_prec_disgust": 0.39552238805970147,
"eval_prec_fear": 0.7064393939393939,
"eval_prec_joy": 0.6696903963715244,
"eval_prec_neutral": 0.88136826783115,
"eval_prec_sadness": 0.6848450057405281,
"eval_prec_surprise": 0.583547557840617,
"eval_recall": 0.602771097930762,
"eval_recall_anger": 0.7123893805309734,
"eval_recall_disgust": 0.4435146443514644,
"eval_recall_fear": 0.5461200585651538,
"eval_recall_joy": 0.7990588235294117,
"eval_recall_neutral": 0.7958129928651896,
"eval_recall_sadness": 0.6322204557498675,
"eval_recall_surprise": 0.29028132992327366,
"eval_runtime": 52.258,
"eval_samples_per_second": 393.05,
"eval_steps_per_second": 24.57,
"step": 7693
},
{
"epoch": 5.26,
"learning_rate": 0.000684134891741713,
"loss": 0.6623,
"step": 7700
},
{
"epoch": 5.41,
"learning_rate": 0.000673596474420387,
"loss": 0.6663,
"step": 7920
},
{
"epoch": 5.56,
"learning_rate": 0.0006630580570990611,
"loss": 0.6669,
"step": 8140
},
{
"epoch": 5.71,
"learning_rate": 0.0006525196397777352,
"loss": 0.6691,
"step": 8360
},
{
"epoch": 5.86,
"learning_rate": 0.0006419812224564093,
"loss": 0.6652,
"step": 8580
},
{
"epoch": 6.0,
"eval_accuracy": 0.752921129503408,
"eval_b_acc": 0.594191766213012,
"eval_f1": 0.6135563471911549,
"eval_f1_anger": 0.5377977217811529,
"eval_f1_disgust": 0.4477933261571583,
"eval_f1_fear": 0.6142208774583964,
"eval_f1_joy": 0.7345635202271116,
"eval_f1_neutral": 0.8443846671149968,
"eval_f1_sadness": 0.659697386519945,
"eval_f1_surprise": 0.4564369310793238,
"eval_loss": 0.670600414276123,
"eval_micro_f1": 0.752921129503408,
"eval_prec": 0.6441161632494222,
"eval_prec_anger": 0.7153351698806244,
"eval_prec_disgust": 0.4611973392461197,
"eval_prec_fear": 0.6353677621283255,
"eval_prec_joy": 0.7385823025689819,
"eval_prec_neutral": 0.8081180811808119,
"eval_prec_sadness": 0.6859267734553776,
"eval_prec_surprise": 0.4642857142857143,
"eval_recall": 0.594191766213012,
"eval_recall_anger": 0.43086283185840707,
"eval_recall_disgust": 0.4351464435146444,
"eval_recall_fear": 0.5944363103953147,
"eval_recall_joy": 0.7305882352941176,
"eval_recall_neutral": 0.8840593315809238,
"eval_recall_sadness": 0.6354001059883413,
"eval_recall_surprise": 0.44884910485933505,
"eval_runtime": 52.6277,
"eval_samples_per_second": 390.289,
"eval_steps_per_second": 24.398,
"step": 8792
},
{
"epoch": 6.01,
"learning_rate": 0.0006314428051350833,
"loss": 0.66,
"step": 8800
},
{
"epoch": 6.16,
"learning_rate": 0.0006209043878137575,
"loss": 0.6414,
"step": 9020
},
{
"epoch": 6.31,
"learning_rate": 0.0006103659704924315,
"loss": 0.6445,
"step": 9240
},
{
"epoch": 6.46,
"learning_rate": 0.0005998275531711056,
"loss": 0.6405,
"step": 9460
},
{
"epoch": 6.61,
"learning_rate": 0.0005892891358497796,
"loss": 0.6532,
"step": 9680
},
{
"epoch": 6.75,
"eval_accuracy": 0.7581791626095423,
"eval_b_acc": 0.5852602000181494,
"eval_f1": 0.614564401804941,
"eval_f1_anger": 0.5887445887445888,
"eval_f1_disgust": 0.4246079613992763,
"eval_f1_fear": 0.6189300411522632,
"eval_f1_joy": 0.7366662689416538,
"eval_f1_neutral": 0.8483534354248544,
"eval_f1_sadness": 0.6636794939377966,
"eval_f1_surprise": 0.42096902303415407,
"eval_loss": 0.6566693782806396,
"eval_micro_f1": 0.7581791626095423,
"eval_prec": 0.6577687706916829,
"eval_prec_anger": 0.6155703077851539,
"eval_prec_disgust": 0.5014245014245015,
"eval_prec_fear": 0.706766917293233,
"eval_prec_joy": 0.7472766884531591,
"eval_prec_neutral": 0.8175881584675664,
"eval_prec_sadness": 0.6601992658626115,
"eval_prec_surprise": 0.5555555555555556,
"eval_recall": 0.5852602000181494,
"eval_recall_anger": 0.5641592920353983,
"eval_recall_disgust": 0.3682008368200837,
"eval_recall_fear": 0.5505124450951684,
"eval_recall_joy": 0.7263529411764705,
"eval_recall_neutral": 0.88152459631994,
"eval_recall_sadness": 0.6671966083730789,
"eval_recall_surprise": 0.3388746803069054,
"eval_runtime": 52.2302,
"eval_samples_per_second": 393.259,
"eval_steps_per_second": 24.583,
"step": 9891
},
{
"epoch": 6.76,
"learning_rate": 0.0005787507185284537,
"loss": 0.6566,
"step": 9900
},
{
"epoch": 6.91,
"learning_rate": 0.0005682602031040429,
"loss": 0.6528,
"step": 10120
},
{
"epoch": 7.06,
"learning_rate": 0.000557769687679632,
"loss": 0.6419,
"step": 10340
},
{
"epoch": 7.21,
"learning_rate": 0.0005472312703583062,
"loss": 0.6305,
"step": 10560
},
{
"epoch": 7.36,
"learning_rate": 0.0005366928530369802,
"loss": 0.6314,
"step": 10780
},
{
"epoch": 7.5,
"eval_accuracy": 0.7554527750730282,
"eval_b_acc": 0.5864396115457234,
"eval_f1": 0.6141846408191719,
"eval_f1_anger": 0.6100183582480986,
"eval_f1_disgust": 0.4005235602094241,
"eval_f1_fear": 0.6080586080586081,
"eval_f1_joy": 0.7392614080107107,
"eval_f1_neutral": 0.8438656485688855,
"eval_f1_sadness": 0.6687747035573123,
"eval_f1_surprise": 0.4287901990811639,
"eval_loss": 0.6726419925689697,
"eval_micro_f1": 0.7554527750730282,
"eval_prec": 0.6673306947742298,
"eval_prec_anger": 0.5800498753117207,
"eval_prec_disgust": 0.534965034965035,
"eval_prec_fear": 0.8117359413202934,
"eval_prec_joy": 0.7029492892000849,
"eval_prec_neutral": 0.8421692379616643,
"eval_prec_sadness": 0.6650943396226415,
"eval_prec_surprise": 0.5343511450381679,
"eval_recall": 0.5864396115457234,
"eval_recall_anger": 0.6432522123893806,
"eval_recall_disgust": 0.3200836820083682,
"eval_recall_fear": 0.486090775988287,
"eval_recall_joy": 0.7795294117647059,
"eval_recall_neutral": 0.8455689072474653,
"eval_recall_sadness": 0.6724960254372019,
"eval_recall_surprise": 0.35805626598465473,
"eval_runtime": 52.4759,
"eval_samples_per_second": 391.418,
"eval_steps_per_second": 24.468,
"step": 10990
},
{
"epoch": 7.51,
"learning_rate": 0.0005261544357156543,
"loss": 0.6297,
"step": 11000
},
{
"epoch": 7.66,
"learning_rate": 0.0005156160183943285,
"loss": 0.6373,
"step": 11220
},
{
"epoch": 7.81,
"learning_rate": 0.0005050776010730025,
"loss": 0.6278,
"step": 11440
},
{
"epoch": 7.96,
"learning_rate": 0.0004945391837516765,
"loss": 0.6321,
"step": 11660
},
{
"epoch": 8.11,
"learning_rate": 0.0004840007664303506,
"loss": 0.6045,
"step": 11880
},
{
"epoch": 8.25,
"eval_accuracy": 0.7577896786757546,
"eval_b_acc": 0.6005624120936303,
"eval_f1": 0.6238197827942396,
"eval_f1_anger": 0.6038186157517901,
"eval_f1_disgust": 0.4337078651685393,
"eval_f1_fear": 0.6333907056798622,
"eval_f1_joy": 0.7377106333527018,
"eval_f1_neutral": 0.8465511724642318,
"eval_f1_sadness": 0.6661166116611661,
"eval_f1_surprise": 0.4454428754813864,
"eval_loss": 0.6667613387107849,
"eval_micro_f1": 0.7577896786757546,
"eval_prec": 0.6550680878375978,
"eval_prec_anger": 0.655440414507772,
"eval_prec_disgust": 0.4684466019417476,
"eval_prec_fear": 0.7682672233820459,
"eval_prec_joy": 0.7288174512055109,
"eval_prec_neutral": 0.8249443207126949,
"eval_prec_sadness": 0.6923956546598056,
"eval_prec_surprise": 0.44716494845360827,
"eval_recall": 0.6005624120936303,
"eval_recall_anger": 0.5597345132743363,
"eval_recall_disgust": 0.40376569037656906,
"eval_recall_fear": 0.5387994143484627,
"eval_recall_joy": 0.7468235294117647,
"eval_recall_neutral": 0.8693203154337213,
"eval_recall_sadness": 0.6417594064652888,
"eval_recall_surprise": 0.4437340153452685,
"eval_runtime": 54.5559,
"eval_samples_per_second": 376.494,
"eval_steps_per_second": 23.535,
"step": 12089
},
{
"epoch": 8.26,
"learning_rate": 0.00047346234910902474,
"loss": 0.6078,
"step": 12100
},
{
"epoch": 8.41,
"learning_rate": 0.0004629239317876988,
"loss": 0.6091,
"step": 12320
},
{
"epoch": 8.56,
"learning_rate": 0.0004523855144663729,
"loss": 0.6127,
"step": 12540
},
{
"epoch": 8.71,
"learning_rate": 0.00044184709714504693,
"loss": 0.6243,
"step": 12760
},
{
"epoch": 8.86,
"learning_rate": 0.000431308679823721,
"loss": 0.6182,
"step": 12980
},
{
"epoch": 9.0,
"eval_accuracy": 0.7570593962999026,
"eval_b_acc": 0.6044499151869599,
"eval_f1": 0.6204901474344295,
"eval_f1_anger": 0.6087460179554011,
"eval_f1_disgust": 0.44725738396624476,
"eval_f1_fear": 0.6212361331220285,
"eval_f1_joy": 0.7376712328767122,
"eval_f1_neutral": 0.8463038632986627,
"eval_f1_sadness": 0.6678737713398861,
"eval_f1_surprise": 0.41434262948207173,
"eval_loss": 0.6659196615219116,
"eval_micro_f1": 0.7570593962999026,
"eval_prec": 0.6461033688057751,
"eval_prec_anger": 0.6389057750759879,
"eval_prec_disgust": 0.451063829787234,
"eval_prec_fear": 0.6770293609671848,
"eval_prec_joy": 0.7164079822616408,
"eval_prec_neutral": 0.8372840867328188,
"eval_prec_sadness": 0.6523496715512885,
"eval_prec_surprise": 0.5496828752642706,
"eval_recall": 0.6044499151869599,
"eval_recall_anger": 0.5813053097345132,
"eval_recall_disgust": 0.4435146443514644,
"eval_recall_fear": 0.5739385065885798,
"eval_recall_joy": 0.760235294117647,
"eval_recall_neutral": 0.8555200901239204,
"eval_recall_sadness": 0.6841547429782724,
"eval_recall_surprise": 0.33248081841432225,
"eval_runtime": 53.1364,
"eval_samples_per_second": 386.552,
"eval_steps_per_second": 24.164,
"step": 13188
},
{
"epoch": 9.01,
"learning_rate": 0.0004207702625023951,
"loss": 0.6299,
"step": 13200
},
{
"epoch": 9.16,
"learning_rate": 0.00041023184518106917,
"loss": 0.5991,
"step": 13420
},
{
"epoch": 9.31,
"learning_rate": 0.00039969342785974325,
"loss": 0.5962,
"step": 13640
},
{
"epoch": 9.46,
"learning_rate": 0.00038915501053841733,
"loss": 0.6014,
"step": 13860
},
{
"epoch": 9.61,
"learning_rate": 0.0003786165932170914,
"loss": 0.5927,
"step": 14080
},
{
"epoch": 9.75,
"eval_accuracy": 0.7466407010710808,
"eval_b_acc": 0.5639997332284856,
"eval_f1": 0.595181302839129,
"eval_f1_anger": 0.5956719817767653,
"eval_f1_disgust": 0.3489736070381232,
"eval_f1_fear": 0.6333059885151764,
"eval_f1_joy": 0.7182098034572578,
"eval_f1_neutral": 0.8372471833853672,
"eval_f1_sadness": 0.6523649521840268,
"eval_f1_surprise": 0.38049560351718625,
"eval_loss": 0.7097288966178894,
"eval_micro_f1": 0.7466407010710808,
"eval_prec": 0.6560660561913124,
"eval_prec_anger": 0.613849765258216,
"eval_prec_disgust": 0.5833333333333334,
"eval_prec_fear": 0.7201492537313433,
"eval_prec_joy": 0.7228312678741659,
"eval_prec_neutral": 0.8081055113983754,
"eval_prec_sadness": 0.6367305751765893,
"eval_prec_surprise": 0.5074626865671642,
"eval_recall": 0.5639997332284856,
"eval_recall_anger": 0.5785398230088495,
"eval_recall_disgust": 0.2489539748953975,
"eval_recall_fear": 0.5651537335285505,
"eval_recall_joy": 0.7136470588235294,
"eval_recall_neutral": 0.8685692827638002,
"eval_recall_sadness": 0.6687864334923158,
"eval_recall_surprise": 0.30434782608695654,
"eval_runtime": 53.7235,
"eval_samples_per_second": 382.328,
"eval_steps_per_second": 23.9,
"step": 14287
},
{
"epoch": 9.76,
"learning_rate": 0.0003680781758957655,
"loss": 0.5977,
"step": 14300
},
{
"epoch": 9.91,
"learning_rate": 0.00035753975857443957,
"loss": 0.6181,
"step": 14520
},
{
"epoch": 10.06,
"learning_rate": 0.00034704924315002875,
"loss": 0.595,
"step": 14740
},
{
"epoch": 10.21,
"learning_rate": 0.00033651082582870283,
"loss": 0.5668,
"step": 14960
},
{
"epoch": 10.36,
"learning_rate": 0.0003259724085073769,
"loss": 0.5736,
"step": 15180
},
{
"epoch": 10.5,
"eval_accuracy": 0.758666017526777,
"eval_b_acc": 0.6092103490403898,
"eval_f1": 0.6224896550246998,
"eval_f1_anger": 0.6192840344917692,
"eval_f1_disgust": 0.42822966507177035,
"eval_f1_fear": 0.6338028169014085,
"eval_f1_joy": 0.742619926199262,
"eval_f1_neutral": 0.8472516603080401,
"eval_f1_sadness": 0.672,
"eval_f1_surprise": 0.4142394822006473,
"eval_loss": 0.6662837862968445,
"eval_micro_f1": 0.758666017526777,
"eval_prec": 0.6494125401879046,
"eval_prec_anger": 0.586924219910847,
"eval_prec_disgust": 0.5,
"eval_prec_fear": 0.680672268907563,
"eval_prec_joy": 0.7281772953414745,
"eval_prec_neutral": 0.8501748747518669,
"eval_prec_sadness": 0.6360624704212021,
"eval_prec_surprise": 0.5638766519823789,
"eval_recall": 0.6092103490403898,
"eval_recall_anger": 0.6554203539823009,
"eval_recall_disgust": 0.37447698744769875,
"eval_recall_fear": 0.5929721815519766,
"eval_recall_joy": 0.7576470588235295,
"eval_recall_neutral": 0.8443484791588434,
"eval_recall_sadness": 0.712241653418124,
"eval_recall_surprise": 0.3273657289002558,
"eval_runtime": 52.4006,
"eval_samples_per_second": 391.98,
"eval_steps_per_second": 24.504,
"step": 15386
},
{
"epoch": 10.51,
"learning_rate": 0.000315433991186051,
"loss": 0.5779,
"step": 15400
},
{
"epoch": 10.66,
"learning_rate": 0.00030489557386472507,
"loss": 0.5816,
"step": 15620
},
{
"epoch": 10.81,
"learning_rate": 0.0002943571565433991,
"loss": 0.5866,
"step": 15840
},
{
"epoch": 10.96,
"learning_rate": 0.0002838187392220732,
"loss": 0.5797,
"step": 16060
},
{
"epoch": 11.11,
"learning_rate": 0.00027328032190074725,
"loss": 0.5687,
"step": 16280
},
{
"epoch": 11.25,
"eval_accuracy": 0.7633398247322298,
"eval_b_acc": 0.6147514191038456,
"eval_f1": 0.6337188907871468,
"eval_f1_anger": 0.6268229911352589,
"eval_f1_disgust": 0.470076169749728,
"eval_f1_fear": 0.6422018348623854,
"eval_f1_joy": 0.7406107406107406,
"eval_f1_neutral": 0.8523923886938851,
"eval_f1_sadness": 0.6596455175956846,
"eval_f1_surprise": 0.4442825928623452,
"eval_loss": 0.6598661541938782,
"eval_micro_f1": 0.7633398247322298,
"eval_prec": 0.6594926170544204,
"eval_prec_anger": 0.6489046773238603,
"eval_prec_disgust": 0.4897959183673469,
"eval_prec_fear": 0.7461240310077519,
"eval_prec_joy": 0.7365603909704445,
"eval_prec_neutral": 0.8389090909090909,
"eval_prec_sadness": 0.6400797607178464,
"eval_prec_surprise": 0.5160744500846024,
"eval_recall": 0.6147514191038456,
"eval_recall_anger": 0.6061946902654868,
"eval_recall_disgust": 0.45188284518828453,
"eval_recall_fear": 0.5636896046852123,
"eval_recall_joy": 0.7447058823529412,
"eval_recall_neutral": 0.8663161847540368,
"eval_recall_sadness": 0.6804451510333863,
"eval_recall_surprise": 0.3900255754475703,
"eval_runtime": 54.1532,
"eval_samples_per_second": 379.294,
"eval_steps_per_second": 23.711,
"step": 16485
},
{
"epoch": 11.26,
"learning_rate": 0.0002627419045794214,
"loss": 0.5575,
"step": 16500
},
{
"epoch": 11.41,
"learning_rate": 0.00025220348725809547,
"loss": 0.5672,
"step": 16720
},
{
"epoch": 11.56,
"learning_rate": 0.00024166506993676952,
"loss": 0.5582,
"step": 16940
},
{
"epoch": 11.71,
"learning_rate": 0.00023112665261544357,
"loss": 0.5607,
"step": 17160
},
{
"epoch": 11.86,
"learning_rate": 0.00022058823529411765,
"loss": 0.5652,
"step": 17380
},
{
"epoch": 12.0,
"eval_accuracy": 0.7630963972736124,
"eval_b_acc": 0.6053830892588602,
"eval_f1": 0.6276991641576467,
"eval_f1_anger": 0.6168702073274639,
"eval_f1_disgust": 0.43303571428571425,
"eval_f1_fear": 0.638801261829653,
"eval_f1_joy": 0.7379285799027169,
"eval_f1_neutral": 0.8519039622384605,
"eval_f1_sadness": 0.6683630195080577,
"eval_f1_surprise": 0.44699140401146126,
"eval_loss": 0.6577332019805908,
"eval_micro_f1": 0.7630963972736124,
"eval_prec": 0.6548174460459298,
"eval_prec_anger": 0.6339754816112084,
"eval_prec_disgust": 0.46411483253588515,
"eval_prec_fear": 0.6923076923076923,
"eval_prec_joy": 0.7441971763579803,
"eval_prec_neutral": 0.8246199806695369,
"eval_prec_sadness": 0.7163636363636363,
"eval_prec_surprise": 0.50814332247557,
"eval_recall": 0.6053830892588602,
"eval_recall_anger": 0.6006637168141593,
"eval_recall_disgust": 0.40585774058577406,
"eval_recall_fear": 0.5929721815519766,
"eval_recall_joy": 0.731764705882353,
"eval_recall_neutral": 0.8810552009012392,
"eval_recall_sadness": 0.6263910969793323,
"eval_recall_surprise": 0.3989769820971867,
"eval_runtime": 53.0543,
"eval_samples_per_second": 387.151,
"eval_steps_per_second": 24.202,
"step": 17584
},
{
"epoch": 12.01,
"learning_rate": 0.00021004981797279173,
"loss": 0.5559,
"step": 17600
},
{
"epoch": 12.16,
"learning_rate": 0.00019951140065146582,
"loss": 0.5439,
"step": 17820
},
{
"epoch": 12.31,
"learning_rate": 0.00018897298333013987,
"loss": 0.5438,
"step": 18040
},
{
"epoch": 12.46,
"learning_rate": 0.00017843456600881395,
"loss": 0.543,
"step": 18260
},
{
"epoch": 12.61,
"learning_rate": 0.00016789614868748803,
"loss": 0.5377,
"step": 18480
},
{
"epoch": 12.75,
"eval_accuracy": 0.7619766309639727,
"eval_b_acc": 0.6124179118880813,
"eval_f1": 0.6250179854378021,
"eval_f1_anger": 0.6205983584855705,
"eval_f1_disgust": 0.41743119266055045,
"eval_f1_fear": 0.6180981595092024,
"eval_f1_joy": 0.7463065558633425,
"eval_f1_neutral": 0.8512547315295107,
"eval_f1_sadness": 0.6756976429151992,
"eval_f1_surprise": 0.44573925710123824,
"eval_loss": 0.6680665612220764,
"eval_micro_f1": 0.7619766309639727,
"eval_prec": 0.6421501390714648,
"eval_prec_anger": 0.595226003047232,
"eval_prec_disgust": 0.4619289340101523,
"eval_prec_fear": 0.6489533011272142,
"eval_prec_joy": 0.732442229270503,
"eval_prec_neutral": 0.8474923234390993,
"eval_prec_sadness": 0.6912416851441242,
"eval_prec_surprise": 0.5177664974619289,
"eval_recall": 0.6124179118880813,
"eval_recall_anger": 0.6482300884955752,
"eval_recall_disgust": 0.3807531380753138,
"eval_recall_fear": 0.5900439238653001,
"eval_recall_joy": 0.7607058823529412,
"eval_recall_neutral": 0.8550506947052197,
"eval_recall_sadness": 0.6608373078961314,
"eval_recall_surprise": 0.391304347826087,
"eval_runtime": 53.2844,
"eval_samples_per_second": 385.479,
"eval_steps_per_second": 24.097,
"step": 18683
},
{
"epoch": 12.76,
"learning_rate": 0.0001573577313661621,
"loss": 0.5457,
"step": 18700
},
{
"epoch": 12.91,
"learning_rate": 0.00014681931404483616,
"loss": 0.5445,
"step": 18920
},
{
"epoch": 13.06,
"learning_rate": 0.0001363287986204254,
"loss": 0.5323,
"step": 19140
},
{
"epoch": 13.21,
"learning_rate": 0.00012579038129909945,
"loss": 0.5214,
"step": 19360
},
{
"epoch": 13.36,
"learning_rate": 0.00011525196397777351,
"loss": 0.5312,
"step": 19580
},
{
"epoch": 13.5,
"eval_accuracy": 0.7594449853943525,
"eval_b_acc": 0.6161690104230055,
"eval_f1": 0.62474808335526,
"eval_f1_anger": 0.6223776223776223,
"eval_f1_disgust": 0.4353448275862069,
"eval_f1_fear": 0.6165413533834586,
"eval_f1_joy": 0.742164744261913,
"eval_f1_neutral": 0.8496567185091775,
"eval_f1_sadness": 0.6675588865096359,
"eval_f1_surprise": 0.4395924308588064,
"eval_loss": 0.6776713132858276,
"eval_micro_f1": 0.7594449853943525,
"eval_prec": 0.636197719648956,
"eval_prec_anger": 0.6057591623036649,
"eval_prec_disgust": 0.4488888888888889,
"eval_prec_fear": 0.633693972179289,
"eval_prec_joy": 0.7350565428109854,
"eval_prec_neutral": 0.8454317315735663,
"eval_prec_sadness": 0.6744186046511628,
"eval_prec_surprise": 0.5101351351351351,
"eval_recall": 0.6161690104230055,
"eval_recall_anger": 0.639933628318584,
"eval_recall_disgust": 0.4225941422594142,
"eval_recall_fear": 0.6002928257686676,
"eval_recall_joy": 0.7494117647058823,
"eval_recall_neutral": 0.8539241457003379,
"eval_recall_sadness": 0.6608373078961314,
"eval_recall_surprise": 0.38618925831202044,
"eval_runtime": 52.4495,
"eval_samples_per_second": 391.615,
"eval_steps_per_second": 24.481,
"step": 19782
},
{
"epoch": 13.51,
"learning_rate": 0.00010471354665644759,
"loss": 0.5261,
"step": 19800
},
{
"epoch": 13.66,
"learning_rate": 9.417512933512167e-05,
"loss": 0.5282,
"step": 20020
},
{
"epoch": 13.81,
"learning_rate": 8.363671201379575e-05,
"loss": 0.5201,
"step": 20240
},
{
"epoch": 13.96,
"learning_rate": 7.309829469246983e-05,
"loss": 0.5292,
"step": 20460
},
{
"epoch": 14.11,
"learning_rate": 6.25598773711439e-05,
"loss": 0.512,
"step": 20680
},
{
"epoch": 14.25,
"eval_accuracy": 0.7568646543330088,
"eval_b_acc": 0.6172231293216093,
"eval_f1": 0.6274045304621182,
"eval_f1_anger": 0.6168593177332957,
"eval_f1_disgust": 0.44719101123595506,
"eval_f1_fear": 0.621580547112462,
"eval_f1_joy": 0.7408979227161047,
"eval_f1_neutral": 0.8446776328228398,
"eval_f1_sadness": 0.6684141546526867,
"eval_f1_surprise": 0.4522111269614835,
"eval_loss": 0.6823310852050781,
"eval_micro_f1": 0.7568646543330088,
"eval_prec": 0.6409438141857619,
"eval_prec_anger": 0.6290971822886716,
"eval_prec_disgust": 0.4830097087378641,
"eval_prec_fear": 0.6461295418641391,
"eval_prec_joy": 0.7051445578231292,
"eval_prec_neutral": 0.8506283320639756,
"eval_prec_sadness": 0.6613070539419087,
"eval_prec_surprise": 0.5112903225806451,
"eval_recall": 0.6172231293216093,
"eval_recall_anger": 0.6050884955752213,
"eval_recall_disgust": 0.41631799163179917,
"eval_recall_fear": 0.5988286969253295,
"eval_recall_joy": 0.7804705882352941,
"eval_recall_neutral": 0.838809613218175,
"eval_recall_sadness": 0.6756756756756757,
"eval_recall_surprise": 0.4053708439897698,
"eval_runtime": 53.2289,
"eval_samples_per_second": 385.881,
"eval_steps_per_second": 24.122,
"step": 20881
},
{
"epoch": 14.26,
"learning_rate": 5.202146004981798e-05,
"loss": 0.5179,
"step": 20900
},
{
"epoch": 14.41,
"learning_rate": 4.148304272849205e-05,
"loss": 0.5085,
"step": 21120
},
{
"epoch": 14.56,
"learning_rate": 3.099252730408124e-05,
"loss": 0.5083,
"step": 21340
},
{
"epoch": 14.71,
"learning_rate": 2.0454109982755316e-05,
"loss": 0.5121,
"step": 21560
},
{
"epoch": 14.86,
"learning_rate": 9.915692661429392e-06,
"loss": 0.5026,
"step": 21780
},
{
"epoch": 15.0,
"step": 21975,
"total_flos": 6.592350719428977e+17,
"train_loss": 0.6400373776102771,
"train_runtime": 15988.8097,
"train_samples_per_second": 175.927,
"train_steps_per_second": 1.374
}
],
"max_steps": 21975,
"num_train_epochs": 15,
"total_flos": 6.592350719428977e+17,
"trial_name": null,
"trial_params": null
}